You are on page 1of 55

PROJECT REPORT ON

CONTENT BASED IMAGE RETRIEVAL
BY

1. TEJASVI SHARMA(0909131114) 2. RISHI PATEL(0909131088) 3. RAHUL KUMAR JAISWAL(0909131082)

Under the Guidance of 1. Mrs. Chhaya Grover 2. Mrs. Payal Kaushik

DEPARTMENT OF ELECTRONICS & COMMUNICATION ENGINEERING JSS ACADEMY OF TECHNICAL EDUCATION C-20/1 SECTOR-62, NOIDA April, 2013

i

Project Report On

CONTENT BASED IMAGE RETRIEVAL
by 1. TEJASVI SHARMA (0909131114) 2. RISHI PATEL ( 0909131088 ) 3. RAHUL KUMAR JAISWAL ( 0909131082 )

Under the Guidance of 1. Mrs.Chhaya Grover 2. Mrs. Payal Kaushik

Submitted to the Department of Electronics & Communication Engineering in partial fulfillment of the requirements for the degree of Bachelor of Technology in Electronics & Communication Engineering JSS Academy of Technical Education, Noida Gautam Buddh Technical University, Lucknow
April – 2013

DECLARATION
ii

We hereby declare that this submission is our own work and that, to the best of our knowledge and belief, it contains no material previously published or written by another person nor material which to a substantial extent has been accepted for the award of any other degree or diploma of the university or other institute of higher learning, except where due acknowledgment has been made in the text.

Signature 1. Tejasvi Sharma 0909131114

Signature 2. Rishi Patel 0909131088

Signature 3. Rahul Kumar Jaiswal 0909131082

iii

CERTIFICATE

This is to certify that Project Report entitled ―Content Based Image Retrieval‖ which is submitted by Tejasvi Sharma, Rishi Patel and Rahul Kumar Jaiswal for partial fulfillment of the requirement for the award of degree B. Tech. in department of Electronics and Communication Engineering of G. B. Technical University, Lucknow is a record of the candidate own work carried out by him under my/our supervision. The matter embodied in this thesis is original and has not been submitted for the award of any other degree.

Signature 1. Mrs. Chhaya Grover Associate Professor

Signature 2. Mrs. Parul Jaiswal Associate Professor

Date:

iv

ACKNOWLEDGEMENT

The successful completion of this report would not have been possible without the help and guidance of many people. We avail this opportunity to convey our gratitude to these people. We would like to show our greatest appreciation to Prof. Dinesh Chandra, Head of Department, Electronics and Communication. We can‘t say thank you enough for his tremendous support and help. I feel motivated and encouraged every time. Without his encouragement and guidance this report would not have been materialized. We feel privileged to express our deep regards and gratitude to our mentors, Mrs. Chhaya Grover and Mrs. Parul Kaushik without whose active support; this project would not have been possible. We owe sincere regards towards the Department Evaluation Committee , ECE who motivate us to achieve the desired goal.

Signature 1.Tejasvi Sharma 0909131114

Signature 2. Rishi Patel 0909131088

Signature 3. Rahul Kumar Jaiswal 0909131082

v

searches must rely on metadata such as captions or keywords. "Content-based" means that the search will analyze the actual contents of the image. This project is mainly divided into four parts –Three search algorithms namely based on colour. that is. The term 'content' in this context might refer colors. the problem of searching for digital images in large databases. shapes. which may be laborious or expensive to produce. shape and texture last part is the application using graphical user interface. vi . In this project query by example is used which is a query technique that involves providing the CBIR system with an example image that it will then base its search upon. Algorithms enlisted in this project are also implemented using Matlab2012b software which is also showing favorable results. also known as query by image content (QBIC) and content-based visual information retrieval (CBVIR) is the application of computer vision to the image retrieval problem. Without the ability to examine image content. textures.ABSTRACT Content-based image retrieval (CBIR). or any other information that can be derived from the image itself.

........TABLE OF CONTENTS DECLARATION...............Power Supply 2......... CHAPTER 2..2 A Prompt Edge Detection Method 4.......2 Polar Representation and Distance Sequences 4......................2 Bridge Wave Rctifier........... CHAPTER 4.........1.................................. ABSTRACT .................................. LIST OF TABLES.................................................................3 Mountain Climbing Sequence (MCS) vii 20 9 11 12 7 8 8 4 5 4 2 3 Page No..2 Flow chart image retrieval based on color content………………............................. ACKNOWLEDGEMENT.................................................. 3.................. 3...............................Introduction 1. Shape Representation 4..1 Central Point Determination 4......... 2...............3........1 Sobel Operation 4............2..... CHAPTER 3.................................3...................2........................ CERTIFICATE................... LIST OF ABBREVIATIONS………………………………………………...................1 Architecture of CBIR Sysytem …………………………................. 1..............................1 Algorithm………………………………………………………… 3........................................1 Background of the problem…..................................................... Introduction...........................D…………. Edge Detection 4................2....................3.............SHAPE BASED IMAGE RETRIEVAL 4........................................................ LIST OF FIGURES................. 2..........................2 Color Based Search Based On Mean And Standard Deviation…………...................................... LIST OF SYMBOLS................................... iii iv v vi x xi xii xiii ........3.........2..........2...................3 Image Retrieval Based on Query in Color Percentage Form……………… 3... 3..3 Voltage regulator...................................2 Problem Statement…………………………………………………......... CHAPTER 1...... 4..3........2 Flowchart for image retrieval based on Mean and S..............................................1 Introduction..................Color Based Search 3................

4....3.........3............... 6........1 Introduction.. Texture Analysis 5.... What is Hausdorff distance ? 4...2 Medical Image Analysis 5........TEXTURE BASED IMAGE RETRIEVAL...2 Features and offsets used CHAPTER 6..........3... Document Processing 5..4......2..2.... Application Examples CHAPTER 5....4.1 Introduction.1... viii .2 History 6.3......2.. Shape Matching 4.......3......2 Applications 5.2..4.......... Statistical Methods 5.1.......1 Introduction 4.3.4............ Inspection 5...4 Hausdorff Distance Technique 4.... 5.GRAPHICAL USER INTERFACE 6..3 Image Search GUI 41 27 27 5....

4: Retrieved Images……………………………………………..1: Architecture of CBIR.2: Grayscale Image…………………….…………………………… Figure 3..15 : Application Example…………….………………………………. Figure 3. Figure 4.B))………….……………………….….………………………………………. Figure 4.LIST OF FIGURES Page Figure 1.…………………………………..………………………. Figure 3.8-14 : Hausdorff Distance Calculation Steps………………….. Figure 4.6: Connectivity Examples………….……………………………….3: Additive Model of RGB…………...7 : Limitation of min(D(A...4: Additive Model of CMYK..3: Example Query…………………………. Figure 4.. Figure 2.2: Search Example ………………………………….1: Sobel Operator….1:Search Example ……….…………………………………… Figure 4. Figure 1.……………..3 : Distance and angle of Contour…………………………………. Figure 2. Figure 2.………………………… Figure 2.…….….2: Algorithm Example…………………………………..….………………….....………………………. Figure 2.1: An Image……………………………………………………...………....……………….. Figure 3. Figure 4...5: Color % Example………………………...5 : Feature Selection…………….. 04 05 06 07 08 09 10 11 13 14 16 16 17 20 20 22 22 23 25 26 28 29 ix . Figure 4. Figure 4..4: Polar Representation……………. Figure 4..…………………………………… Figure 2..5: Additive Model of Gamut…………………….16 : Edge Detection…………….6.…………….……………………………....….……………………………… Figure 3.2 : Prompt Edge Detector……………………….…………………………….

32 33 38 42 42 43 x .6 : Offsets Used……………………………………………………. Figure 5.1 : Texture Application…………….4 : Texture Analysis Example…………….………………………………. Figure 5.5 : Texture Features From Power Spectru…………………………. Figure 5..Figure 5.. Figure 5.…………………………….3 : Stastical Methods………………………………………………. Figure 5.……………………….…….2 : Texture Analysis…………….

. 16 xi .LIST OF TABLES Page Table 5.1: Autocorrelation Feature…………………………………………..

Recent retrieval systems have incorporated users' relevance feedback to modify the retrieval process in order to generate perceptually and semantically more meaningful retrieval results. images just consist of pure pixel data with no inherent meaning. Commercial image catalogues therefore use manual annotation and rely on text retrieval techniques for searching particular images. In contrast to text.CHAPTER 1 INTRODUCTION The use of images for illustration in human communication has its roots millennia ago. users provide the retrieval system with example images or sketched figures. 1 . This project is based on the search performed on three ways. In this part of the report we are dealing only with the colour based search. nowadays we observe a rapid increase in digital media caused by an ever increasing growth of computing power. An important part of digital media is image data. The similarities /distances between the feature vectors of the query example or sketch and those of the images in the database are then calculated and retrieval is performed with the aid of an indexing scheme. shape. decreasing cost of storage and steady improvement of communication infrastructure technology. But all that information is only useful if one can access it efficiently. Our stone age ancestors painted pictures on the walls of their caves and certainly the use of maps was known in pre-Roman times already. The indexing scheme provides an efficient way to search for the image database. and spatial layout to represent and index the image. the visual contents of the images in the database are extracted and described by multi-dimensional feature vectors. through Colour Shape and Texture. The feature vectors of the images in the database form a feature database. This does not only mean fast access from a storage management point of view but also means that one should be able to find the desired information without scanning all information manually. To retrieve images. The system then changes these examples into its internal representation of feature vectors. Similar as the increase in printed media through the invention of book-printing. In typical content-based image retrieval systems . In this we introduce these fundamental techniques for contentbased image retrieval. texture. Content-based image retrieval uses the visual contents of an image such as color.

context-sensitive and incomplete. and is often subjective. annotating images manually is a cumbersome and expensive task for large image databases. it is difficult for the traditional text-based methods to support a variety of task-dependent queries. and other applications available to users increased dramatically. the application potential of image database management techniques has attracted the attention of researchers . most text-based image retrieval systems require manual annotation of images. medical. Researchers from the communities of computer vision. In the early 1990s. Early techniques were not generally based on visual features but on the textual annotation of images. images were first annotated with text and then searched using a text-based approach from traditional database management systems. human-computer interface. In 1992. database management. educational. However. Through text descriptions. In other words. as a result of advances in the Internet and new digital image sensor technologies.1 Background Of The Problem Early work on image retrieval can be traced back to the late 1970s. since automatically generating descriptive texts for a wide spectrum of images is not feasible. Obviously. The efficient management of the rapidly expanding visual information became an urgent problem. industrial. In 1979. As a result. images can be organized by topical or semantic hierarchies to facilitate easy navigation and browsing based on standard Boolean queries. It was widely recognized that a more efficient and intuitive way to represent and index visual information would be based on properties that are inherent in the images themselves. This need formed the driving force behind the emergence of content-based image retrieval techniques. the National Science Foundation of the United States organized a workshop on visual information management systems to identify new directions in image database management systems.1. Since then. the volume of digital images produced by scientific. Textbased image retrieval uses traditional database techniques to manage images. and information retrieval were attracted to this field. Comprehensive surveys of early text-based image retrieval methods can be found in. The difficulties faced by text-based retrieval became more and more severe. 2 . a conference on Database Techniques for Pictorial Applications [6] was held in Florence.

The system then changes these examples into its internal representation of feature vectors.Since then. Within a general image database it may be sufficient to just add an annotation like ‘butterfly‘ whereas this obviously is not sufficient for a biologist‘s database consisting of different types of butterflies only  The second problem with manual annotation is that it is very time consuming.2 Problem Statement Commercial image catalogues therefore use manual annotation and rely on text retrieval techniques for searching particular images. Since 1997. The similarities /distances between the feature vectors of the query example or sketch and those of the images in the database are then calculated and retrieval is performed with the aid of an indexing scheme. users provide the retrieval system with example images or sketched figures. Content-based image retrieval. research on content-based image retrieval has developed rapidly . organization. In typical content-based image retrieval systems . indexing. shape. and database management has increased enormoulsy. The indexing scheme provides an efficient way to search for the image database. and hospitals. uses the visual contents of an image such as color. such an annotation has two main drawbacks:  The annotation depends on the person who adds it. it is prohibitive for 3 . While it may be worthwhile for commercial image collections. Naturally the result may vary from person to person and furthermore may depend on the context. Comprehensive surveys of these techniques and systems can be found . companies. However. Recent retrieval systems have incorporated users' relevance feedback to modify the retrieval process in order to generate perceptually and semantically more meaningful retrieval results 1. and spatial layout to represent and index the image. texture. government organizations. To retrieve images. a large number of academic and commercial retrieval systems have been developed by universities. user query and interaction. the number of research publications on the techniques of visual information extraction. The feature vectors of the images in the database form a feature database. Similarly. the visual contents of the images in the database are extracted and described by multi-dimensional feature vectors.

appearing on the first page for text query rose black. One could not even keep up with the growth of available image data. are shown in Figure 1 Figure 1. This method also provides too much responsibility to the end user. 4 .1   Another problem with manual annotation is that of each user may name the query image in their own language which would be hectic to deal with.It means that it totally depends on human perception of how to name the image and how to form the query text.indexing of images within the World Wide Web. As perception varies from person to person the method becomes very ineffective. The image search results.

Figure 1. Such images may or may not be extracted by this method. 5 .2  Also there are some images which require greater description which cannot be described by words.

1 Introduction 2. In a (8-bit) grayscale image each picture element has an assigned intensity that ranges from 0 to 255.1. 6 .CHAPTER 2 IMAGE PROCESSING 2.1 What is an image? An image is an array.2 Each pixel has a value from 0 (black) to 255 (white). or a matrix. but the name emphasizes that such an image will also include many shades of grey. Figure 2.1: An image — an array or a matrix of pixels arranged in columns and rows. of square pixels (picture elements) arranged in columns and rows . Figure 2. A grey scale image is what people normally call a black and white image.

Widely used.710.474. green and blue to make cyan. Some of the most common file formats are: GIF — an 8-bit (256 colour). especially for web and Internet (bandwidthlimited). A normal greyscale image has 8 bit colour depth = 256 greyscales. There are two general groups of ‗images‘: vector graphics (or line art) and bitmaps (pixel-based or ‗images‘). Lempel-Ziv-Welch (LZW) compression. but it cannot be used for print production. much information per byte) destructively compressed 24 bit (16 million colours) bitmap format. Red and green combine to make yellow. the two main colour spaces are RGB and CMYK. A ―true colour‖ image has 24 bit colour depth = 8 x 8 x 8 bits = 256 x 256 x 256 colours = ~16 million colours. green or blue) and excluding the third colour. for instance.The possible range of the pixel values depend on the colour depth of the image. Compresses nondestructively with. The combination of red.The secondary colours of RGB – cyan. This is analogous to stacking slide images on top of each other and shining light through them.656 greyscales.2 Colours For science communication. and blue in full intensity makes white. g and b receptors in our retinas.976. and blue and red form magenta. Mostly used for web. a standard vector format. 2. It is the basic colour model used in computers and for web graphics. Some greyscale images have more greyscales. PS — Postscript. magenta. PSD – a dedicated Photoshop format that keeps all the information in an image including all the layers. 7 . 2. green. Has several sub-standards one of which is the animated GIF. RGB uses additive colour mixing and is the basic colour model used in television or any other medium that projects colour with light. TIFF — the standard 24 bit publication bitmap format.2. and yellow – are formed by mixing two of the primary colours (red.1 RGB The RGB colour model relates very closely to the way we perceive colour with the r.In Photoshop using the ―screen‖ mode for the different layers in an image will make the intensities mix together according to the additive colour mixing model.e. here 8 bit = 256 tones or greyscales. JPEG — a very efficient (i. non-destructively compressed bitmap format. In principle three greyscale images can be combined to form an image with 281. Has numerous sub-standards and can be difficult to transport across platforms and operating systems. for instance 16 bit = 65536 greyscales.

Figure 2. Figure 2. 2. and blue are the primary stimuli for human colour perception and are the primary additive colours. magenta (M) and yellow (Y) inks.4 8 . Red. The CMYK model uses the subtractive colour model.2.2 CMYK The 4-colour CMYK model used in printing lays down overlapping layers of varying percentages of transparent cyan (C). green. In addition a layer of black (K) ink can be added.3: The additive model of RGB.

The two colour spaces discussed here span only a fraction of the colours we can see. 9 . Furthermore the two spaces do not have the same gamut. • Rectangular sampling – In most cases.2.The colours created by the subtractive model of CMYK don't look exactly like the colours created in the additive model of RGB Most importantly. CMYK cannot reproduce the brightness of RGB colours. Figure 2. It is therefore important to understand how images can be sampled and how that relates to the various neighborhoods that can be used to process an image. meaning that converting from one colour space to the other may cause problems for colours in the outer regions of the gamut. the CMYK gamut is much smaller than the RGB gamut. This results in the type of sampling shown in figure.5 2. or gamut. • Hexagonal sampling – An alternative sampling scheme is shown in Figure c and is termed hexagonal sampling.3 Gamut The range. of human colour perception is quite large. images are sampled by laying a rectangular grid over an image as illustrated. In addition.3 Types Of Neighbourhoods Neighborhood operations play a key role in modern digital image processing. 2.

Some of the most common neighborhoods are the 4-connected neighborhood and the 8-connected neighborhood in the case of rectangular sampling and the 6-connected neighborhood in the case of hexagonal sampling illustrated in figure.Both sampling schemes have been studied extensively and both represent a possible periodic tiling of the continuous image space. Figure 2. (c) 10 . We will restrict our attention.n=no ]. however. to only rectangular sampling as it remains.n=no ] based upon the pixel values in the neighborhood of a[m=mo . the method of choice. (b).6 (a). due to hardware and software considerations. Local operations produce an output pixel value b[m=mo .

texture. The main reason for color based search is that it is independent of image size and orientation. In order to deal with these data. Advances in data storage and image acquisition technologies have enabled the creation of large image datasets. The indexing scheme provides an efficient way to search for the image database. in order to find color-based techniques that are more closely aligned with the ways that humans perceive color. Color is one of the most widely used visual features in content-based image retrieval. user has to provide a query image. The similarities distances between the feature vectors of the query image and those of the images in the database are then calculated and retrieval is performed with the help of indexing schemes. statistically describing combined probabilistic properties of the various color channels (such as the Red. the device characteristics. by capturing the number of pixels having particular properties. Also it is one of the most straight-forward features utilized by humans for visual recognition and discrimination. Colour is an important cue for image retrieval. The color histogram has been the most commonly used representation technique. Green. as it depends not only on surface characteristics but also capturing conditions such as illumination. The image retrieval based on colour features has proved effective for a large image database. and Blue channels). It is relatively robust and simple to represent. The system then performs certain feature extraction procedures on it and represents it in the form of feature vectors.CHAPTER 3 COLOR BASED SEARCH Content based Image retrieval is an efficient way to search through an image database by means of image features such as colour. angle of the device. pattern or any combinations of them. it is necessary to develop appropriate information systems to efficiently manage these collections. 11 . however it is neglected that colour is not a stable parameter. To retrieve desired images. Image searching is one of the most important services that need to be supported by such systems. Various studies of color perception and color spaces have been proposed. shape.

Figure 3. it ranks the database images in a decreasing order of similarity to the query image and forwards the most similar images to the interface module. The data insertion subsystem is responsible for extracting appropriate features from images and storing them into the image database (see dashed modules and arrows).3. in turn.1 Architecture of CBIR Systems Figure shows a typical architecture of a content-based image retrieval system. Next. Note that database images are often indexed according to their feature vectors to speed up retrieval and similarity computation. The query processing. The queryprocessing module extracts a feature vector from a query pattern and applies a metric (such as the Euclidean distance) to evaluate the similarity between the query image and the database images. is organized as follows: the interface allows a user to specify a query by means of a query pattern and to visualize the retrieved similar images.1 12 . This process is usually performed off-line. Note that both the data insertion and the query processing functionalities use the feature vector extraction module. Two main functionalities are supported: data insertion and query processing.

Pictorially the average row and column mean is calculated as follows The average mean is calculated by adding up the mean of every row. E.1 Algorithm Step1: Three color planes namely Red . Step2: For each plane row mean and column mean of colours are calculated.2 Step3: The average of all row means and all columns means is calculated for each plane.3.: (3+8+13+18+23) = 13. Once the feature vectors are generated for all images in the database.2. 13 . Steps of the algorithm are given below. Green and Blue are separated. Similarly with column it would be (11+12+13+14+15) = 13 shown as in fig given below. 3. they are stored in a feature database Step5: The Euclidian distances between the feature vector of query image and the feature database are calculated using Eq given below. Step4: The features of all 3 planes are combined to form a feature vector.g. Figure 3.2 Color Based Search Based On Mean And Standard Deviation The method of image searching and retrieval proposed here mainly focuses on the generation of the feature vector by calculating the average means.

D. Query Image The algorithm is applied on the first database of 300 images to generate feature vector for each image in the database and the query image and hence calculate the Euclidian distance to find the better match. Start Select the query image Convert query and database images from RGB to Gray Calculate mean and standard deviation of the query and database images Compare the database and query images on the basis of mean and sd Retrieve the images into a separate directory Stop To discuss the performance of the algorithm we have considered the beach class as an example.2.2 Flowchart for image retrieval based on Mean and S. 3. The algorithm has produced very good results as it can be seen in the fig below where the first 20 retrieved images found are shown. 14 . The query image for the same is shown in the Fig This query image is used for both the databases.The value of d is calculated by summation of the squares of difference of the features of database image and query image as mentioned in figure.

15 . defined as Precision =No of relevant images retrieved/Total number of images retrieved Recall =No.3 Query Figure 3.4 Retrieved Images Retrieval Efficiency The common evaluation measures used in CBIR systems are precision.of relevant images in the database.of relevant images retrieved/Total no.Figure 3.

Step 2: Extract the RGB metrics of each images in the database Step 3: Compare the RGB content extracted above with the query colour content Step 4: Extract those images which nearly satisfy whose colour content nearly satisfy with the input colour content.3 Image Retrieval Based on Query in Color Percentage Form To make the algorithm clear we will first start with the example as shown below Figure 3.3.1 Algorithm: Step 1: Get the input for the required colour content according to which the image from our database is to be sorted out.5 3.3. Step 5: Retrieve the images into separate direct 16 .

3.2 Flow chart image retrieval based on color content Start Set the required color content Extract RGB intensity matrics from the data base images Compare the required content with that of database images Retrieve the images into a separate directory Stop 17 .3.

the gradient of f at pixel 18 . Earlier researchers paid a lot of attention to edge detection. For the gray-level function f(x.y). The sobel operation computes the partial derivatives of a local pixel to form the gradient. In addition. In this section.2. shape.1 Sobel Operation Another common edge detection method is the sobel method.6 The goal of any of these algorithms is to approximate the perceptual judgments of the user. Algorithms which more closely approximate the perceptual judgments of the user are considered to be more successful.CHAPTER 4 SHAPE BASED IMAGE RETRIEVAL 4. No mathematically rigorous definition of shape similarity accounts for the various semantic qualities that humans assign to shapes. improving the technology for content-based querying systems becomes more challenging. we introduce a simple and efficient method for edge detection. content-based retrieval has received considerable attention and. and point out their drawbacks. increasing interest has developed in automatic information retrieval from huge databases. we will briefly illustrate two common edge detection methods. 4. texture. In particular. edge detection is still highly challenging.5 and schemes for matching turning angle around the perimeter of a shape.1 Introduction Because of recent advances in computer technology and the revolution in the way information is processed. There are four important feature components for content-based image retrieval: color. Edge Detection Edge detection is a necessary pre-processing step in most of computer vision and image understanding systems. including moment-based matching algorithms hausdorff-distance based metrics. One of the most challenging aspects to content based image retrieval is retrieval by shape. consequently. but up to now. 4.2. The accuracy and reliability of edge detection is critical to the overall performance of these systems. The sobel operation uses four masks to detect edge points.1 Without textual tags or other semantic descriptors. There have been a variety of proposed methods for determining similarity between planar shapes.4. we can only approximate shape similarity from the 2D image.

y) from that of its neighbour in direction d. we 19 .y) is indicated as an edge point if the following inequalities hold : 3 ≤ Bd (x.y) be the number of differences that exceed a threshold T.y) is defined as a vector. y) . we take the value 2 for c and. y) ≤ 6 These inequalities can also avoid indicating noisy points as edge points. The Prompt edge detector detects edge points by checking the differences in the gray value for each point from those of its neighbors. shape is the most important for recognizing objects. where T = a + c. c is a constant.y) denote the gray values of its neighbors in 8 directions .3. the Prompt edge detection method. and g7(x. an easy and effective edge detection method. 4.2.y). y) = g(x. g1(x. Among these features.y). it would help achieve a high recognition rate for a content-based image retrieval system.y) with gray value g(x.1 4. and a is the average difference between all pairs of adjacent pixels' gray values in the image. is introduced. Figure 4.gd (x.2 A Prompt Edge Detection Method In this subsection. Shape Representation A good representation can manifest an object‘s characteristics. we take the local average differences for T by dividing the hole image into M ×M blocks and computing the average difference for each block.2 Let hd (x. …. y) be the difference in the gray value of pixel (x. For a pixel (x. The magnitude of∇ f can be approximated as the following equation: Figure 4. In this work.(x. In this section. Some researchers have shown that objects are very distinguishable based on their visible features. instead of taking a single value for T. The pixel (x.y). Let B d(x. Furthermore. let g0(x.

2 Polar Representation and Distance Sequences A shape representation method is outlined in this section. rotation and scaling.introduce a new shape representation method that is invariant to translation. and scaling.3. rotation. or even deformed images. occluding. where x. and θ are related using Equations given below A sketch map is shown of Distance and angle of the contour points relative to centroid Figure 4.3. then the contour graph can be represented by a polar equation d = f (θ ) . To permit invariance to translation. and also has high tolerance to complex.θ ) .1 Central Point Determination The first step in shape representation for an object is to locate the central point of the object. where n is the number of points of an object. the geometric center of the object is selected as a reference point. 4.3 20 . d. We use the equation below to compute the centroid of an object. We characterize the contour using a sequence of contour points described in polar from. and each contour point (x. Here. 4.y) has the polar description (d.yc). we take the pole at the centroid (xc. y.

However.…. (b) Graph of polar representation for the contour in (a).With the polar description. where di = f (θ i) θi =i ∗ 2π /n . If we only record the distance of one point (say. the maximum distance is computed and all distances are normalized to it. Figure 4. the contour points of some protrusions may be missed. dn-1) by successively rotating a ray emanating from the pole counter clockwise through an fixed angle Δθ . Thus. d1. or furthermore associating the number of all the intersection points. recording the distances. or for a more detailed description. dn−1) . We can eliminate this problem by recording the distance of the farthest intersection point at each rotating the scanning ray step.4 illustrates the graph of the polar equation d = f (θ ) for a given contour. 21 . all values fall between 0 and 1 regardless of how much the objects are scaled. This method of representing and describing the shape of an object is adequate for convex objects. smallest distance) at each step of rotation. for an object containing concavities.4 An example of polar representation (a) A contour of an object. d1. Recording the distance of intersection point of the current ray lies with the contour . we may represent contour points as a sequence (d0 .5 Features selection of two different concave objects. and at each step of rotation. To provide scale invariance. a ray may intersect the contour with more than one point. Figure 3.…. where di is known to be the distance between the corresponding contour point and the centroid. We can obtain the distance sequence ( d0 . Figure 4. where Δθ = 2π n for a positive integer n.

we use the MCS to represent the shape of objects. we evaluate the ordering-consistency functions ci's. at the sequence D = (d0. and ( 2 .4. dn-1) as described . The representation will not be unique. such that the maximum distance was associated with the angle of zero. 1. and as a result. as defined in Equation below. they are considered having the same shape. Sequence (MCS) for the object. 1. To reduce this problem.1). 3. 2 . the representation of a distance sequence is translation invariant.3 Mountain Climbing Sequence (MCS) Since we used the pole at the centroid of the object. 1. In the example shown in figure. …. 2 . 1. 2 . of the function having the smallest value.1. 1. 1. 1.1). 2 . This new sequence Dm is called the mountain climbing sequence(MCS) for the object.ds+n-1). We proceed to the matching stage to measure the similarity between two objects by simply evaluating the Euclidean distance between each object‘s MCSs of them.ds+1. 2 ). 1. 2 . 1. As discussed in the receding subsection. Shape Matching The final step of content-based image retrieval is the matching stage. Bernier rotated the polar coordinate system. The MCS representations for Figures 3. ( 2 . The Euclidean distance between two sequences is given in Equation below 22 .3. s. d1.4. both objects have three maximal distances and each has three possible representations: ( 2 .1 2 . 2 .5(a) and (b) are identical and both come out as (1. To achieve rotation-invariance. First.1).3. as defined in Equation ci. and determine the index. 2 . where dk = dk mod n for each k. …. we propose another representation method that deals with all distances rather than only the individual maximal distances in the sequence. However there is no any guarantee for this method if there are more than one maximum distance.1. The distances in the sequence D are then shifted forward for s positions to yield a new sequence Dm= (ds.

6 First. finally keep the smallest distance found among point a. There is a limitation for the above calculated distance given as below: Figure 4. and n is the dimension of the feature space.1 Introduction Although hausdorff distance technique is very robust nature application of which resulted in the appearance of time delay.where U and V are the query and dababase images. Any arbitrary two dimensional shape can then be compared to any other using the outline method. 4. ui are their ith features. respectively. find its smallest distance to any point of B. That is for every point a of A.4. vi. So in order to get better result we have to reach a trade-off between time delay accuracy. shortest distance doesn‘t consider the whole shape 23 .4 Hausdorff Distance Technique 4.

More formally. we'll take d(a. Hausdorff distance is the maximum distance of a set to the nearest point in the other set . shortest distance doesn‘t account for the position of the object 4. b) as the Euclidian distance between a and b. Hausdorff distance from set A to set B is a maxi-min function.2. and d(a. What is Hausdorff distance ? Named after Felix Hausdorff (1868-1942). defined as where a and b are points of sets A and B respectively. for simplicity.7 Second.8 24 . b) is any metric between these points .4.Figure 4. If for instance A and B are two sets of points. steps to to understand how hausdorff distance is calculated are shown below : Step 1: Figure 4.

11 Compute distance between a2 and bj‘s.10 Keeping the shortest distance.B) Step 2: Figure 4. Step4: Figure 4.finding h(A. Step3: Figure 4.9 Compute distance between ai and bj‘s. 25 .Given two sets of points A and B .

B). Step 7: Figure 4.13 Finally . 26 . find the largest of the two distances.12 And keep the shortest distance Step6: Figure 4.14 This is h(A.Step5: . Figure 4.

computer-assisted surgery. the best the match. Basically. visual navigation of robots. the lower the distance value.4.3. and where. even in presence of noise or occlusion (when the target is partially hidden). so to work with binary sets of points. The first step is to extract the edges of both images.15 We want to find if the small image is present.4. lines or polygons : 27 . That method gives interesting results. etc. used for instance in image analysis. Say the small image below is our template. in the large image. the Hausdorff metric will serve to check if a template image is present in a test image . and the large one is the test image : Figure 4. Application Examples One of the main application of the Hausdorff distance is image matching.

etc. such as Canny edge detector. Sobel.Figure 4.16 Edge extraction is usually done with one of the many edge detectors known in image processing. Laplacian. minimum Hausdorff distance between two images found a best match . 28 .

However. This difficulty is demonstrated by the number of different texture definitions attempted by vision researchers. A fundamental characteristic of texture: it cannot be analyzed without a frame of reference of tonal primitive being stated or implied. Then as resolution increases. simplifying assumptions are made about the uniformity of intensities in local image regions.‖ 29 . it has no texture.‖ • ―An image texture is described by the number and types of its (tonal) primitives and the spatial organization or layout of its (tonal) primitives. it takes on a fine texture and then a coarse texture. slowly varying. • ―We may regard texture as what constitutes a macroscopic region. (ii) the order consists in the arrangement of elementary parts. For any smooth gray-tone surface. the image of a wooden surface is not uniform but contains variations of intensities which form certain repeated patterns called visual texture. and (iii) the parts are roughly uniform entities having approximately the same dimensions everywhere within the textured region. We recognize texture when we see it but it is very difficult to define.‖ • ―A region in an image has a constant texture if a set of local statistics or other local properties of the picture function are constant. Some have compiled a catalogue of texture definitions in the computer vision literature and we give some examples here. there exists a scale such that when the surface is examined.1 Introduction In many machine vision and image processing algorithms. or approximately periodic.CHAPTER 5 TEXTURE BASED IMAGE RETRIEVAL 5. or they could be the result of reflectance differences such as the color on a surface. Its structure is simply attributed to the repetitive patterns in which elements or primitives are arranged according to a placement rule. images of real objects often do not exhibit regions of uniform intensities. For example.‖ • ―The notion of texture appears to depend upon three ingredients: (i) some local ‗order‘ is repeated over a region which is large in comparison to the order‘s size. The patterns can be the result of physical surface properties such as roughness or oriented strands which often have a tactile quality.

texture is defined as the amount of randomness which has a lower value in the vicinity of the border between the heart cavity and the inner wall than in the blood filled cavity. in the SAR images of Figures 4. Images from two application domains are shown in Figure 1. For example.2 Applications Texture analysis is an important and useful area of study in machine vision. Image texture.1(b) and (c) texture is defined to be the local scene heterogeneity and this property is used for classification of land use categories such as water. is useful in a variety of applications and has been a subject of intense study by many researchers. and remote sensing. In some of the mature domains (such as remote sensing) texture already has played a major role. We will briefly review the role of texture in automated inspection. The role that texture plays in these examples varies depending upon the application. and others are driven completely by the application in which the definition will be used. Most natural surfaces exhibit texture and a successful vision system must be able to deal with the textured world surrounding it. This section will review the importance of texture perception from two viewpoints — from the viewpoint of human vision or psychophysics and from the viewpoint of practical machine vision applications. This fact can be used to perform segmentation and boundary detection using texture analysis methods. One immediate application of image texture is the recognition of image regions using texture properties. In the ultrasound image of the heart in Figure 4. document processing.This collection of definitions demonstrates that the ―definition‖ of texture is formulated by different people depending upon the particular application and that there is no generally agreed upon definition. Some are perceptually motivated. medical image processing. defined as a function of the spatial variation in pixel intensities (gray values).1(a). agricultural areas. Texture analysis methods have been utilized in a variety of application domains. while in other disciplines (such as surface inspection) new applications of texture are being found. 5. 30 . etc.

Conners utilized texture analysis methods to detect defects in lumber wood automatically. These applications include defect detection in images of textiles and automated inspection of carpet wear and automobile paints. Texture features are computed from the filtered images. (b) The two different regions are immediately discriminable by humans. In the detection of defects in texture images.Figure 5. A Mahalanobis distance classifier is used to classify the defective areas. Inspection There has been a limited number of applications of texture processing to automated inspection problems. They extract a skeletal structure from images. Chen and Jain used a structural approach to defect detection in textured images. (a) Humans cannot perceive the two regions without careful scrutiny. and by detecting anomalies in certain statistical features in these skeletons.1 5.1. defects in the texture are identified. The defect detection is performed by 31 . They have sparse convolution masks in which the bank of filters are adaptively selected depending upon the image to be analyzed. This allows one to detect the boundaries of defects in the texture. most applications have been in the domain of textile inspection. Dewaele used signal processing methods to detect point defects and line defects in texture images. The bottom halves of the images consist of texture tokens that are different from the ones in the top half. Texture pairs with identical second-order statistics.2. Some have defined a simple window differencing operator to the texture features obtained from simple filtering operations.

A pair of automotive paint finish images is shown where the image in (a) has uniform coating of paint. Depending upon the particular classification task. The features they use to perform this classification is based on tonal features such as mean.dividing the image into sub windows and classifying each sub window into one of the defect categories such as knot. Jain used the texture features computed from a bank of Gabor filt ers to automatically classify the quality of painted metallic surfaces. decay. In general. Siew proposed a method for the assessment of carpet wear. They used simple texture features that are computed from second-order gray level dependency statistics and from first-order gray level difference statistics. the extracted features capture morphological properties. such as distinguishing normal tissue from abnormal tissue. skewness. or certain textural properties of the image. variance. and kurtosis of gray levels along with texture features computed from gray level co-occurrence matrices in analyzing pictures of wood.2 Medical Image Analysis Image analysis techniques have played an important role in several medical applications. but the image in (b) has ―mottle‖ or ―blotchy‖ appearance. mineral streak. The combination of using tonal features along with textural features improves the correct classification rates over using either type of feature alone. In the area of quality control of textured images. the applications involve the automatic extraction of features from the image which are then used for a variety of classification tasks. etc.2 Examples of images from various application domains in which texture analysis is important. 5. color properties. They showed that the numerical texture features obtained from these techniques can characterize the carpet wear successfully. Figure 5. 32 .

Texture is represented as an index at each pixel. In their classification experiments. being the local fractal dimension within an window estimated according to the fractal Brownian motion model proposed by Chen. The fractal dimension is expected to be higher on an average in blood than in tissue due to the noise and backscatter characteristics of 33 . In such applications. texture analysis methods are ideally suited for these images. Some diseases. These features are computed based on an isotropic contrast measure.1). Harms used image texture in combination with color features to diagnose leukemic malignancy in samples of stained blood cells. the texture features significantly improved the correct classification rate of blood cell types compared to using only color features. The ultrasound images in this study are time sequence images of the left ventricle of the heart.1 shows one frame in such a sequence. and a Fourier domain energy sampling. Lundervold used fractal texture features in combination with other features (such as response to edge detector operators) to analyze ultrasound images of the heart (see Figure 5. Sutton and Hall discuss the classification of pulmonary disease using texture features. such as interstitial fibrosis. the best classification results were obtained using the directional contrast measure. a directional contrast measure. and used the fractal texture features to do edge enhancement in chest X-rays. affect the lungs in such a manner that the resulting changes in the X-ray images are texture changes as opposed to clearly delineated lesions. the gray level. the mean texton radius and texton size for each color and various texton shape features. They extracted texture micro-edges and ―textons‖ between these micro-edges. Landeweerd and Gelsema extracted various first-order statistics (such as mean gray level in a region) as well as second-order statistics (such as gray level cooccurrence matrices) to differentiate different types of white blood cells. including the response to a Kirsch edge operator. In combination with color. They made significant use of the knowledge about the physics of the ultrasound imaging process and tissue characteristics to design the texture model. They extracted a number of texture features from the textons including the total number of pixels in the textons which have a specific color. Figure 5. The textons were regions with almost uniform color. Insana used textural features in ultrasound images to estimate tissue scattering parameters. For example.The textural properties computed are closely related to the application domain to be used. Sutton and Hall propose the use of three types of texture features to distinguish normal lungs from diseased lungs. Chen used fractal texture features to classify ultrasound images of livers. The texture feature is used in addition to a number of other traditional features. and the result of temporal operations.

Wang and Srihari used projection profiles of the pixel values to identify large ―text‖ blocks by detecting valleys in these profiles. A segmentation of the document image is obtained using three classes of textures: one class for the text regions. For example. Document Processing One of the useful applications of machine vision and image analysis has been in the area of document image analysis and character recognition. Wahl used constrained run lengths and connected component analysis to detect blocks of text. and utilized Hough transform techniques to detect collinear elements. For example. the fractal dimension is low at non-random blood/tissue interfaces representing edge information. Document processing has applications ranging from postal address recognition to analysis and interpretation of maps. and a third class for the transition areas between the two types of regions. 34 . a second class for the uniform regions that form the background or images where intensities vary slowly. They use various classification methods to compute the segmentation including contextual classification and relaxation algorithms. is the bar code block.3. Most image analysis methods proposed to date for document processing are based upon the characteristics of printed documents and try to take advantage of these properties. In addition. Taxt view the identification of print in document images as a two-category classification problem. Many methods work on images based on precise algorithms which one might consider as having morphological characteristics. generally newspaper print is organized in rectangular blocks and this fact is used. The processing of the ultrasound images of the heart using textural features. A similar method is used for locating text blocks in newspapers. the first step is the ability to separate the regions in the image which contain useful information from the background. Fletcher and Kasturi used the fact that most text blocks lie in a straight line. An example of this can be seen in Figure. which is different from its surrounding texture. where the categories are print and background. One can also use texture segmentation methods for preprocessing document images to identify regions of interest..the blood which is more disordered than that of solid tissue. In many postal document processing applications (such as the recognition of destination address and zip code information on envelopes). The texture segmentation algorithm described in was used to segment a newspaper image.2. In the resulting segmentation. 5. one of the regions identified as having a uniform texture.

for the detection of changes in bone microstructure. this feature is more useful for synthesis than analysis tasks. Methods based on second-order statistics (i.g. 35 The approach based on . Human texture discrimination in terms of texture statistical properties is investigated Julesz. The most popular second-order statistical features for texture analysis are derived from the so-called co-occurrence matrix. but different third-order moments require deliberate cognitive effort. The advantage of the structural approach is that it provides a good symbolic description of the image. statistics up to the second order may be most important. This may be an indication that also for automatic processing. model-based and transform methods. Texture Analysis Approaches to texture analysis are usually categorised into     structural. statistical approaches do not attempt to understand explicitly the hierarchical structure of the texture. the textures in grey-level images are discriminated spontaneously only if they differ in second order moments. Accordingly. It may prove to be useful for bone image analysis. they represent the texture indirectly by the non-deterministic properties that govern the distributions and relationships between the grey levels of an image. e. however.and macrostructure and no clear distinction between them. Equal second order moments. To describe the texture.3. In contrast to structural methods. They were demonstrated to feature a potential for effective texture discrimination in biomedical-images. Structural approaches represent texture by well defined primitives (micro texture) and a hierarchy of spatial arrangements (macro texture) of those primitives.5. The choice of a primitive (from a set of primitives) and the probability of the chosen primitive to be placed at a particular location can be a function of location or the primitives near the location. statistical.e. statistics given by pairs of pixels) have been shown to achieve higher discrimination rates than the power spectrum (transform-based) and structural methods. The abstract descriptions can be ill defined for natural textures because of the variability of both micro. A powerful tool for structural texture analysis is provided by mathematical morphology . one must define the primitives and the placement rules. Instead.

Identifying the perceived qualities of texture in an image is an important first step towards building mathematical models for texture. In spite of this. Modelling this physical variation is very difficult.multidimensional co-occurrence matrices was recently shown to outperform wavelet packets (a transform-based technique) when applied to texture classification. there are a number of intuitive properties of texture which are generally assumed to be true. attempt to interpret an image texture by use of.3. A large number of texture features have been proposed. general definition of texture exists in the computer vision literature. such as Fourier. 5. The use of statistical features is therefore one of the early methods proposed in the machine vision literature. 36 . But. respectively. Statistical Methods One of the defining qualities of texture is the spatial distribution of gray values. however. Compared with the Gabor transform.3. so texture is usually characterized by the two-dimensional variations in the intensities present in the image. The relationship between the various statistical texture measures and the input image is summarized in Fig. Gabor filters provide means for better spatial localisation. The parameters of the model are estimated and then used for image analysis. This explains the fact that no precise. the wavelet transforms feature several advantages. Picard has also related the gray level co-occurrence matrices to the Markov random field models.1. Gabor represent an image in a space whose co-ordinate system has an interpretation that is closely related to the characteristics of a texture (such as frequency or size). the computational complexity arising in the estimation of stochastic model parameters is the primary problem. In practice. Methods based on the Fourier transform perform poorly in practice. we will use to denote an N X N image with G gray levels. however.4. The intensity variations in an image which characterize texture are generally due to some underlying physical variation in the scene (such as pebbles on a beach or waves in water). It can be used also for texture analysis and. Transform methods of texture analysis. due to its lack of spatial localisation.3 . their usefulness is limited in practice because there is usually no single filter resolution at which one can localise a spatial structure in natural textures.discrimination. generative image model and stochastic model. The fractal model has been shown to be useful for modelling some natural textures. In the following. Model based texture analysis using fractal and stochastic models. these features are not independent as pointed out by Tomita. it lacks orientation selectivity and is not suitable for describing local image structures.

The entry (i.Figure 5.j) of Pd is the number of occurrences of the pair of gray levels i and j which are distance d apart.dy) is defined as follows. I(t. Formally given as.3 Co-occurrence Matrices Spatial gray level co-occurrence estimates image properties related to second-order statistics. s). As an example.| is the cardinality of a set. v):I(r. The G X G gray level cooccurrence matrix Pd for a displacement vector d= (dx. j) =|{((r.v)=j}| ` and |. Haralick suggested the use of gray level co-occurrence matrices (GLCM) which have become one of the most well-known and widely used texture features. Pd( I. s)=I.(t. consider the following image containing 3 different gray values: 1100 1100 0022 0022 37 .

a large number of features can be computed from the co-occurrence matrix. if most of the entries in the co-occurrence matrix are concentrated along the diagonals. Notice that the co-occurrence matrix so defined is not symmetric. Table 1 lists some of these features.The gray level co-occurrence matrix for this image for a displacement vector d= (1. then the texture is coarse with respect to the displacement vector d.0) is given as follows: 402 Pd= 220 002 Here the entry (0.0) of Pd is 4 because there are four pixel pairs (0. This means that some sort of feature selection method must be used to select the most relevant features. Haralick has proposed a number of useful texture features that can be computed from the co-occurrence matrix. The co-occurrence matrix features suffer from a number of difficulties. The co-occurrence matrix reveals certain properties about the spatial distribution of the gray levels in the texture image. For a given . For example. Examples of Pd for other displacement vectors is given below.0) that are offset by amount. But a symmetric cooccurrence matrix can be computed by the formula P = Pd+P-d . The co-occurrence matrix-based texture features have also been primarily used in texture classification tasks and not in segmentation tasks Autocorrelation Features 38 . There is no well established method of selecting the displacement vector and computing co-occurrence matrices for different values of is not feasible.

4 illustrates the effect of the directionality of a texture on the distribution of energy in the power spectrum. The quantity |F(u.. then the autocorrelation function will drop off slowly. The example in Figure 4. Formally. For regular textures. the autocorrelation function of an image is defined as follows: The image boundaries must be handled with special care but we omit the details here. otherwise. This function is related to the size of the texture primitive (i.1 39 . If the texture is coarse.v) . it will drop off very rapidly. The autocorrelation function is also related to the power spectrum of the Fourier transform (see Figure).e. The autocorrelation function of an image can be used to assess the amount of regularity as well as the fineness/coarseness of the texture present in the image.An important property of many textures is the repetitive nature of the placement of texture elements in the image.y) and its Fourier Transform F(u. the autocorrelation function will exhibit peaks and valleys.v)|2 is defined as the power spectrum where|. Consider the image function in the spatial domain I(x. Early Table 5.| is the modulus of a complex number. the fineness of the texture).

5.5 Texture features computed from the power spectrum of the image approaches using such spectral features would divide the frequency domain into rings (for frequency content) and wedges (for orientation content) as shown in Figure 4. The 40 .Figure 5.4 Figure 5.

you can derive several statistics from them . The following table lists the statistics.frequency domain is thus divided into regions and the total energy in each of these regions is computed as texture features.6 Figure 5. 5. Offsets used are shown in the next figure 5.2 Features and offsets used After you create the GLCMs. These statistics provide information about the texture of an image.6 41 .3.

. image or spreadsheet files) that have been opened or created with a single application. Commands are issued in the GUI by using a mouse. it is much easier for a new user to move a file from one directory to another by dragging its icon with the mouse than by having to remember and type seemingly arcane commands to accomplish the same task. Adding to this intuitiveness of operation is the fact that GUIs generally provide users with immediate. a trash can (to indicate a place to dispose of unwanted files and directories) and buttons on web browsers (for navigating to previous pages. or on top of. a way for humans to interact with computers) that uses windows.. menu item or window of interest in order to select that object. and thus easier to learn and use. Each window can display a different application.e. when a user deletes an icon representing a file. the icon immediately disappears. or each can display different files (e. trackball or touchpad to first move a pointer on the screen to. For example. An icon is a small picture or symbol in a GUI that represents a program . in which the user types a delete command (inclusive of the name of the file to be deleted) but receives no automatic feedback indicating that the file has actually been removed. GUIs allow users to take full advantage of the powerful multitasking (the ability for multiple programs and/or multiple instances of single programs to run simultaneously) capabilities of modern operating systems by allowing such multiple programs and/or instances to be displayed simultaneously. Icons are used both on the desktop and within application programs. confirming that the file has been deleted (or at least sent to the trash can).g. a text file or an image) seemingly independently of the rest of the display screen.1 Introduction A graphical user interface (GUI) is a human-computer interface (i. Examples include small rectangles (to represent files). The result is a large increase in the flexibility of computer use and a consequent rise in user productivity. icons and windows can be moved by dragging (moving the mouse with the held down) and objects or programs can be opened by clicking on their icons. icons. For example. a program. etc. a file.g. A major feature is the ability for multiple windows to be open simultaneously. text. for reloading the current page. In addition. icons and menus and which can be manipulated by a mouse and often to a limited extent by a keyboard as well. A window is a rectangular portion of the monitor screen that can display its contents (e. Advantages of GUIs A major advantage of GUIs is that they make computer operation more intuitive.CHAPTER 6 GRAPHICAL USER INTERFACE 6.). for example. 42 . visual feedback about the effect of each action.. This contrasts with the situation for a CLI. a directory or a device (such as a hard disk or floppy). Then. file folders (to represent directories). the icon.

the provision of memory for storing objects and the ability to draw precision lines and corners on the screen. The Apple Macintosh. Bush proposed an information administration tool. 43 . that would allow data to be stored on microfilm and made easily accessible. such as being able to rotate and freely change the size and transparency of icons. the co-founder of Apple Computer. It was so successful. Much additional progress occurred at Xerox Palo Alto Research Center (PARC). It has also become the standard in human-computer interaction. Microsoft announced development of its first operating system that incorporated a GUI in November 1983. Windows 2. 6. Also being studied is the increased use of natural languages to interact with computers as a supplement or complement to GUIs. and it is now used on (or at least available for) virtually all types of computers. developed a program for his Ph.0 with its addition of icons and overlapping windows. including developing overlapping windows. In 1963 Ivan Sutherland.But the GUI has become much more than a mere convenience. linkable with hyperlinks and programmable. it has led to the development of new types of applications and entire new industries. In his now classic 1945 magazine article As We May Think. Another area of research is increasing user control over GUI objects. An example is desktop publishing. which Xerox Corporation established in 1970 in Palo Alto. was released in November 1985. that the GUI was subsequently adopted by most other developers of operating systems and application software.D. and it has influenced the work of a generation of computer users. the Memex . manipulable icons. released in December 1987. The Future One of the most interesting areas of exploration is GUIs that provide the user with the illusion of navigating through a three-dimensional space.0.0. Apple considerably extended PARC's work. which has revolutionized (and partly wiped out) the traditional printing and typesetting industry. California for the purpose of creating "the architecture of information" and "humanizing computers. His concept included the capability to zoom in and out on the display. which was incorporated into PARC's Alto computer." This included developing the first usable GUI. dropdown menus and a trash can.2 History The origin of the GUI can be traced back to Vannevar Bush. a scientist and futurist who worked at the Massachusetts Institute of Technology (MIT) during World War II. represented a major improvement over the primitive Windows 1. Steve Jobs. but it was not until 1995 with the launching of Windows 95 that Microsoft was able to offer a relatively high quality GUI. a graduate student at MIT. and he thus decided to incorporate a GUI into his company's computers. and the initial version. which allowed the direct manipulation of graphic objects on a CRT screen using a light pen. was the first commercially successful use of a GUI. Moreover. dissertation called Sketchpad. a fixed menu bar. in fact. Windows 1. was heavily inspired by the innovations at nearby PARC. launched in 1984.

Step-2 The program requires the percentages in the edit boxes created especially for this purposes. 44 . This can be input through the edit text windows provided in GUI. For this pupose it has several keys and buttons which are to be discussed next. Step-2 The program then requires the range of averages and standard deviations that are tolerable for the user. Step-4 User has another option of whether to display the images or store them in a particular folder location. Step-3 The user can then press the button search for starting the database search.The user has to give the complete URL of the query image. Step-3 The user can then press the button search for starting the database search.The user has to provide the percentage of different color intansities in the required image as query. ALGORITHM 2-GUI Step 1.3 Image Search GUI The GUI of this project deals with the formation of a user friendly window that allows him to effectively search the database and extract the required images out of it. Step-4 User has another option of whether to display the images or store them in a particular folder location.6. ALGORITHM 1-GUI Step 1.eg-Provide red intensity in ‗R‘ box.