BOOK CART –ONLINE BOOK STORE

Presented By :

Sanket Basu Roy Roll:10700213030
Ishan Soni Roll:10700213013

Under The Guidance of:
Prof. TANIYA PURKAIT
Department of IT

ACKNOWLEDGEMENT

 Expressing our profound gratitude and deep regards to
our faculty guide Prof. TANIYA PURKAIT Department of
IT for his exemplary guidance.

 We wish to reciprocate in full measure the kindness
shown by Mr. Arunava Bhattacharyya (HOD,
Information Technology) who inspired us.

 Obliged and grateful to my project mate for her
cooperation during the period of assignment.

Processing is a rapidly evolving field with the growing applications in science & engineering.  What is Image Processing? Image processing is a method to convert an image into digital form and perform some operations on it. . in order to get an enhanced image or to extract some useful information from it. INTRODUCTION  What is Digital Image? A digital image is a two dimensional representation of objects or real life entities .

Improve qualities of images so that human can interpret them better. Such as image analysis. 2. .Objectives of digital image processing 1. restoration and so on. Process pictures and extract some information from them for machine perception. image recognition and so on. Such as enhancement.

What can digital image processing do?  Digitizing an image ( convert an continuous image to a digital one)  Enhancing an image ( Let an image better suit for a specific application)  Restoring an image ( Recover a damaged image)  Compressing an image ( Store it with less bytes )  Segmenting an image ( Partition objects in an image from background )  Recognizing an image ( Tell what the objects are in an image ) .

 The aim of image enhancement is to improve the interpretability or perception of information in images for human viewers. or to provide `better' input for other automated image processing techniques. . IMAGE ENHANCEMENT  The process of improving the quality of a digitally stored image by manipulating the image with software.

in order to stretch out the intensity range. It is a method that improves the contrast in an image. Histograms of an image before and after equalization . HISTOGRAM EQUILIZATION Histogram equalization is a method in image processing of contrast adjustment using the image's histogram.

 Brightness Preserving bi Histogram Equalization(BBHE). .  Equal Area dualistic sub-image histogram equalization (DSIHE). ALGORITHMS FOR HISTOGRAM  Global Histogram Equalization (GHE) algorithm .

Global Histogram Equalization (GHE) algorithm: Derive the intensity mapping from the image Calculate the cumulative frequency distribution Divide the cumulative frequency into equal frequency for each intensity level Calculate the cumulative e frequency for the new frequency value For each intensity in the original image find an intensity in the transformed image that as close as possible. the same amount of cumulative frequency .

Now let input image is decomposed into two sub-images 𝑋𝐿 and 𝑋𝑈 by using the input mean𝑋𝑚 where𝑋𝑚 ∈ {𝑋0 . Brightness Preserving Bi Histogram Equalization(BBHE)  The BBHE firstly decomposes an input image histogram H(X) into two sub-images based on the mean of the input image. σ𝐿−1 𝑖=0 𝑖. 𝑗 ∈ 𝑋} And 𝑋𝑈 = {𝑥(𝑖. 𝑗)|𝑥 𝑖. 𝑗)|𝑥 𝑖. 𝑗 > 𝑋𝑚 ∀ 𝑥 𝑖. 𝑗 ∈ 𝑋} And mean of the input image is calculated by. 𝑋1 … 𝑋𝐿−1 } 𝑋 = 𝑋𝐿 ∪ 𝑋𝑈 Where 𝑋𝐿 = {𝑥(𝑖. 𝑗 ≤ 𝑋𝑚 ∀ 𝑥 𝑖. 𝑝(𝑋𝑖 ) 𝑋𝑚 = 𝐿−1 σ𝑖=0 𝑝(𝑋𝑖 ) .

STEP 3: First minimum level to the mean value and for second mean value to the maximum level. Description of the algorithm BBHE is: STEP1: BBHE divides the input image histogram into two parts based on the mean value. . STEP 2: Then histogram equalization is applied to the both separated parts with the new intensity range.

𝑗)|𝑥(𝑖. 𝑗) ∈ 𝑋} . 𝑗) > 𝑋𝐷 ∀ 𝑥(𝑖. 𝑗) ∈ 𝑋} And 𝑋𝑈 = {𝑥(𝑖.XDis the median value which divides input image into two parts XL and XU then XL and XU is be defined as- 𝑋 = 𝑋𝐿 𝑈 𝑋𝑈 Where 𝑋𝐿 = {𝑥(𝑖. 𝑗) ≤ 𝑋𝐷 ∀ 𝑥(𝑖.Equal Area dualistic sub-image histogram equalization (DSIHE)  The DSIHE is similar to BBHE except that it firstly decomposes an input image histogram 𝐻(𝑋) into two sub- images based on the median of the input image. 𝑗)|𝑥(𝑖.

STEP 2: Then histogram equalization is applied to the both separated parts with the new intensity range. . Description of the algorithm DSIHE is: STEP1: DSIHE divides the input image histogram into two parts based on the median value. STEP 3: First minimum level to the median value and for second median value to the maximum level.

Image in RGB color space Flowchart of the Image Enhancement Process Case for RGB Color Space : R Channel G Channel B Channel Histogram Histogram Histogram Equalization Equalization Equalization Merge three channels to obtain image in RGB color space Enhanced image in RGB .

Experiment Results GHE Algorithm(Gray Scale): Original Image After Histogram Equalization .

BBHE (Gray): DSIHE(Gray) : Original Images After Histogram Equalization .

Experimental Results GHE Algorithm(RGB Image): Original Image After Histogram Equalization .

BBHE (RGB Image): DSIHE(RGB Image) : Original Images After Histogram Equalization .

29 62.96 Average 25.59 82.67 lena 50.76 68.88 114.Table 1 : Average AMBE Performance for 6 Test Images(Gray Scale): Images GHE BBHE DSIHE barbara2 34.37 79.17 48.88 goldhill 34.53 peppers2 16.76 77.22 98.62 34.2 boat 1.10 baboon2 14.11 88.84 67.14 47.56 120 100 GHE 80 BBHE 60 40 DSIHE 20 0 .17 98.35 58.

41 boat 15.Table 2 : Average PSNR Performance for 6 Test Images(Gray Scale): Image GHE BBHE DSIHE barbara2 13.80 13.32 11.41 9.73 7.54 11.62 baboon2 14.61 6.89 9.66 10.55 12.05 8.13 7.42 peppers2 17.17 9.65 8.09 lena 11.46 20 15 GHE 10 BBHE DSIHE 5 0 barbara2 lena boat baboon2 goldhill peppers2 .20 Average 14.02 goldhill 13.10 11.

25 lena 52.12 18.52 31.06 nature 13.15 test 7.77 48.72 pepeers1 14.30 28.99 25.15 Average 17.14 60 50 GHE 40 BBHE 30 DSIHE 20 10 0 barbara1 lena baboon1 peppers1 test nature .48 26.36 27.97 25.51 baboon1 9.42 48.42 25.76 7.16 22.76 17.Table 1 : Average AMBE Performance for 6 Test Images(For RGB Image): Images RGBGHE RGBBBHE RGBDSIHE barbara1 6.81 22.

16 Average 16.45 nature 17.69 lena 12.62 25 20 GHE 15 BBHE 10 DSIHE 5 0 barbara1 lena baboon1 peppers1 test nature .32 12.08 baboon1 19.97 18.34 15.21 17.27 test 12.18 15.09 pepeers1 16.69 20.96 17.56 18.Table 4 : Average PSNR Performance for 6 Test Images(for RGB Image): Image RGBGHE RGBBBHE RGBDSIHE barbara1 20.53 17.21 13.08 16.65 13.65 16.55 12.

the better the image quality is. Based on the observations of Table-1 and Table-3. Conclusion Assessment of Brightness Preservation : The results shown in the Table-1 and Table-3 presents the performance of brightness preservation of various methods discussed for Gray scale as well as RGB. PSNR is a metrics for image quality assessment. The BBHE also produces better results as compared to DSIHE method. The greater the PSNR. BBHE is second best method for brightness preservation and DSIHE is third best method for brightness preservation. . we see that GHE is best in brightness preservation. Based on the observation of Table-2 and Table-4 we see that the GHE has the greater PSNR values of each image and an average PSNR for all images is also has greater value as compared to other histogram equalization methods. Assessment of contrast enhancement: The results shown in the Table-2 and Table-4 presents the PSNR (Peak Signal to Noise Ratio) values for various methods applied to some standard images.

October 2013 5. 1. Nanjing University of Science and Technology. Gwanggil Jeon. S.wikipedia. The International Arab Journal of Information Technology. Advanced Science and Technology Letters.4.org/wiki/Image_processing 8. 2.5. Brightness Preserving Image Contrast Enhancement using Spatially Weighted Histogram Equalization. Yogendra P. Gonzalez and R. 11. Xiubao Sui. Incheon National University. A COMPARATIVE STUDY OF HISTOGRAM EQUALIZATION BASED IMAGE ENHANCEMENT TECHNIQUES FOR BRIGHTNESS PRESERVATION AND CONTRAST ENHANCEMENT.tutorialspoint. Qian Chen. Maravi and Sanjeev Sharma.7 (2014). Department of Optoelectronic Technology.28 (EEC 2013). pp. 2002. Department of Embedded Systems Engineering. 2nd edition. and Jianle Ren. Prentice Hall. School of Information Technology. Incheon National University. No. No.https://en. Chao Zuo. Color Image Enhancement by Histogram Equalization in Heterogeneous Color Space. Histogram Equalization-Based Color Image Processing in Different Color Model. C. Digital Image Processing.9. International Journal of Multimedia and Ubiquitous EngineeringVol. RGPV.54-57 3.org/wiki/Histogram_equalization 7. China. India. pp. R. Department of Embedded Systems Engineering. E. Vol. Omprakash Patel. Bhopal. Gwanggil Jeon and Young-Sup Lee. No. Vol. https://en.http://www.309-318 4. REFERENCES: 1. Signal & Image Processing : An International Journal (SIPIJ) Vol. Woods.htm . January 2014 6. Madhya Pradesh.com/dip/Histogram_Equalization.wikipedia.

 .THANK YOU….