 Presentation: 2022 Artificial Intelligence

IMAGE PROCESSING IN ARTIFICIAL INTELLIGENCE

Group Members:
Muhammad Hussnain Waheed , 19-A-2793
Maryam Zoya , 19-A-2784
Muhammad Ali, 19-A-2788
Ahmad Mir, 19-A-2752

Date: 14-JUNE-2022
Prof. Mlik Shahzar Younus
MUHAMMAH HUSSNAIN
WAHEED
“ 19-Arid-2793 ”
TOPIC:

“- DIGITAL IMAGE PROCESSING“

(Concept, methods, HISTORY , examples)
 IMAGE PROCESSING
WHAT IS AN IMAGE?
 Image is a collection of pixel.
 Pixels is a smallest unit in an image which contain the color value.
 PPI (Pixel per inch)  [Min.300 pixels required per inch].
E.G  “RGB COLOR – MILLIONS OF PIXELS”.
 IMAGE PROCESSING
CONTINUE….
WHAT IS AN IMAGE - PROCESSING?
 Image Processing is a method to perform some operations on an image, in order to get an
enhanced image or to extract some useful information from it.
E.G  “Photo Editing”.
 Here are two methods of image- processing , These Are:-
1. Analog Image Processing.
2. Digital Image Processing.
• Analog image processing is used for processing physical photographs, printouts, and other hard
copies of images.
• Digital image processing is used for manipulating digital images with the help of computer
algorithms.
 DIGITAL IMAGE PROCESSING (DIP)

WHAT IS AN DIGITAL IMAGE?

 Digital Image is a representation of two-dimensional image as a finite set of digital values,
called picture elements or pixels.
 DIGITAL IMAGE PROCESSING (DIP)
CONTINUE….

WHAT IS AN DIGITAL IMAGE?

 Pixel Values typically represent gray levels, colors, heights, opacities etc..
 Remember digitization implies that a digital image is an approximation of a real scene
 IN WHAT FORM IS A DIGITAL IMAGE STORED?

 Common image formats include:

– 1 sample per point (B&W or Grayscale).
– 3 samples per point (Red, Green, and Blue).
– 4 samples per point (Red, Green, Blue, and “Alpha”, a.k.a. Opacity).

◦ For most of this course we will focus on grey-scale images.

WHAT IS DIGITAL IMAGE & VIDEO PROCESSING

 Digital Image (and Video) processing focuses on two major tasks: -

– Improvement of pictorial information for human interpretation
– Processing of image data for storage, transmission and representation for autonomous
machine perception.
 Some argument about where image processing ends and fields such as image analysis and
computer vision start !!
 WHAT IS DIGITAL IMAGE PROCESSING (DIP)
CONTINUE….

 The continuum from image processing to computer vision can be broken up into low-, mid-
and high-level processes.
 IN TERMS OF SIGNAL REPRESENTATIONS

 Digital Image and Video Processing is the manipulate of still and moving images, treated as
multidimensional signals.

 Still Images - f(x,y)

 Moving Images - f(x,y,t)
 Other Signals (CT, MRI) - f(x,y,z,t)
 HISTORY OF DIGITAL IMAGE PROCESSING
◦ Early 1920s: One of the first applications of digital imaging was in the newspaper
industry
– The Bartlane cable picture transmission service
– Images were transferred by submarine cable between London and New York
– Pictures were coded for cable transfer and reconstructed at the receiving end on a
telegraph printer
 HISTORY OF DIGITAL IMAGE PROCESSING
CONTINUE….
◦ Mid to late 1920s: Improvements to the Bartlane system resulted in higher quality images
– New reproduction processes based on photographic techniques
– Increased number of tones in reproduced images
DIGITAL IMAGE ACQUISITION:
“SAMPLING”
DIGITAL IMAGE ACQUISITION:
“QUANTISATION”
Ahmad Mir
“ 19-Arid-2752 ”
KEY PHASES OF DIGITAL
IMAGE PROCESSING
 IMAGE ACQUISTION
 Is the
process of capturing an image with a sensor (such as a camera) and
converting it into a manageable entity.
 IMAGE ENHANCEMENT
 Improves the quality of an image in order to extract hidden information from
it for further processing.
 IMAGE RESTORATION
• Deals with degradation of extreme nature such as distortions created by sensor system,
poor lighting condition etc.

• This process helps to restore the blur or damage images in the quality one.

• Image restoration is more mathematical and formal.

 MORPHOLOGICAL PROCESSING
• Describes the shapes and structures of the objects in an image
• Can be used when creating datasets for training AI models
 WAVELETS & MULTI-RESOLUTION PROCESSING
• Short duration waves.

• Used to analyze frequency and time.

• When you want to represent the images in various degrees or resolution wavelets and
multiresolution process works as the foundation.
 IMAGE COMPRESSION & DE-COMPRESSION
• Compression is responsible for reducing the size and resolution, while
decompression is used for restoring an image to its original size and
resolution
 SEGMENTATION
• A method in which a digital image is broken down into various segments
which helps in reducing the complexity of the image to make further
processing or analysis of the image simpler.
 OJECT RECOGNITION
• Suppose, the image is telling it is tree that means it has the leaf or the shape
as like the tree. In digital image processing system it will save the description
among the image.
MARYAM ZOYA
“ 19-Arid-2784 ”
TOPIC

Machine learning frameworks and image

processing platforms.
 CONTINUE….
 If you want to move beyond using simple AI algorithms, you can build custom deep
learning models for image processing. To make development a bit faster and easier, you
can use special platforms and frameworks. Below, we take a look at some of the most
popular ones:
◦ Tensor Flow
◦ Porch
◦ MATLAB Image Processing Toolbox
◦ Microsoft Computer Vision
◦ Google Cloud Vision
◦ Google Collaborator (Colab)
 1. Tensor Flow: -
 Google’s Tensor Flow is a popular open-source framework with support for machine
learning and deep learning. Using Tensor Flow, you can create and train custom deep
learning models. The framework also includes a set of libraries, including ones that can be
used in image processing projects and computer vision applications.
2. PyTorch: -
 PyTorch is an open-source deep learning framework initially created by the
Facebook AI Research lab (FAIR). This Torch-based framework has Python, C++,
and Java interfaces.

◦ Among other things, you can use PyTorch for building computer vision and natural
language processing applications.
 3. MATLAB Image Processing Toolbox : -
 MATLAB is an abbreviation for matrix laboratory. It’s the name of both a popular
platform for solving scientific and mathematical problems and a programming language.
This platform provides an Image Processing Toolbox (IPT) that includes multiple
algorithms and workflow applications for AI-based picture analysis, processing, and
visualizing as well as for developing algorithms.

◦ MATLAB IPT allows you to automate common image processing workflows. This toolbox
can be used for noise reduction, image enhancement, image segmentation, 3D image
processing, and other tasks. Many of the IPT functions support C/C++ code generation, so
they can be used for deploying embedded vision systems and desktop prototyping.

◦ MATLAB IPT isn’t an open-source platform, but it has a free trial.

 4. Microsoft Computer Vision: -

 Computer Vision is a cloud-based service provided by Microsoft that gives you access to
advanced algorithms for image processing and data extraction. It allows you to:
◦ analyze visual features and characteristics of an image

◦ moderate image content

◦ extract text from images
 5. Google Cloud Vision:

 Cloud Vision is part of the Google Cloud platform and offers a set of image processing
features. It provides an API for integrating such features as image labeling and
classification, object localization, and object recognition.

◦ Cloud Vision allows you to use pre-trained machine learning models and create and train
custom models for creating image processing projects using machine learning.
 6. Google Collaborator (Colab):
Google Collaborator, otherwise known as Colab, is a free cloud service that can be used not only for improving your
coding skills but also for developing deep learning applications from scratch.

◦ Colab makes it easier to use popular libraries such as OpenCV, Keras, and Tensor Flow when developing an AI-based
application. The service is based on Jupiter Notebooks, allowing AI developers to share their knowledge and expertise
in a comfortable way. Plus, in contrast to similar services, Colab provides free GPU resources.

◦ In addition to different libraries, frameworks, and platforms, you may also need a large database of images to train and
test your model.

◦ There are several open databases containing millions of tagged images that you can use for training your custom
machine learning applications and algorithms. ImageNet and Pascal VOC are among the most popular free databases
for image processing.
Muhammad ali
“ 19-Arid-2788 ”
TOPIC

Using neural networks for

image processing.
 NEURAL NETWORKS
• Neural networks reflect the behaviour of the human brain, allowing
computer programs to recognize patterns and solve common problems in
the fields of AI, machine learning, and deep learning.
 NEURAL NETWORKS & HUMAN
BRAIN
• Neural networks, also known as artificial neural networks (ANNs) or
simulated neural networks (SNNs), are a subset of machine learning and
are at the heart of deep learning algorithms. Their name and structure are
inspired by the human brain, mimicking the way that biological neurons
signal to one another.
 WORKING OF NEURAL NETWORKS

◦ Artificial neural networks (ANNs) are comprised of a node layers

◦ It contains an input layer, one or more hidden layers, and an output layer.
◦ Each node, or artificial neuron, connects to another and has an associated weight
and threshold.
◦ If the output of any individual node is above the specified threshold value, that
node is activated, sending data to the next layer of the network. Otherwise, no data
is passed along to the next layer of the network.
CONTINUE….
 NEURAL NETWORKS VS DEEP LEARNING

◦ Deep Learning and neural networks tend to be used interchangeably in

conversation, which can be confusing.
◦ As a result, it’s worth noting that the “deep” in deep learning is just referring to
the depth of layers in a neural network.
◦ A neural network that consists of more than three layers—which would be
inclusive of the inputs and the output—can be considered a deep learning
algorithm.
◦ A neural network that only has two or three layers is just a basic neural network.
THE END
 References
◦
http://www.sci.utah.edu/~gerig/CS6640-F2012/Materials/ImageProcessing1-Introduction
-Bryan-Mac-Namee.pdf
◦ https://www.apriorit.com/dev-blog/599-ai-for-image-processing
◦ https://www.geeksforgeeks.org/components-of-image-processing-system/