Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
Scribd
Upload
40 views

Image Processing & Computer Vision

The document provides an overview of an image processing and computer vision course, including course objectives, topics covered, instructional methods, assessment, textbooks, and definitions of key concepts like image processing and computer vision.

Uploaded by

Raj Singh
Copyright
© © All Rights Reserved
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
40 views

Image Processing & Computer Vision

The document provides an overview of an image processing and computer vision course, including course objectives, topics covered, instructional methods, assessment, textbooks, and definitions of key concepts like image processing and computer vision.

Uploaded by

Raj Singh
Copyright
© © All Rights Reserved
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 21

Image Processing & Computer

Vision
By: Engr Umair Abro
Google
Course Overview
Closely related fields within computer science and engineering,
but they have distinct focuses and goals.
• Course Description:
This course provides an introduction to fundamental concepts,
techniques, and algorithms in the fields of image processing and
computer vision. Students will learn the theoretical foundations as
well as practical applications of image processing and computer
vision techniques through lectures, hands-on exercises, and
projects.
• Prerequisites:
Basic knowledge of linear algebra, Programming experience (e.g.,
Python)
Course Learning Outcomes
• Course Objectives:
1. Understand the basic principles and algorithms of
image processing and computer vision.
2. Gain practical experience in implementing and
applying image processing and computer vision
techniques.
3. Develop critical thinking and problem-solving skills in
analyzing visual data.
4. Explore advanced topics and emerging trends in
image processing and computer vision.
Topics Covered
• Introduction to Image Processing and Computer Vision
• Overview of image representation
• Basic image processing operations
• Image acquisition and digitization
• Image Enhancement
• Histogram equalization
• Spatial domain methods (e.g., filtering, sharpening)
• Frequency domain methods (e.g., Fourier transform)
• Image Restoration
• Image degradation models
• Image denoising techniques
• Image deblurring and restoration
• Image Segmentation
• Thresholding techniques
• Edge detection
• Region-based segmentation
• Feature Extraction and Description
• Point features (e.g., corners, keypoints)
• Feature descriptors (e.g., SIFT, SURF)
• Feature matching algorithms
• Object Detection and Recognition
• Introduction to object detection
• Template matching
• Haar cascades and Viola-Jones algorithm
• Introduction to deep learning-based object detection
• Motion Analysis and Tracking
• Optical flow
• Object tracking techniques
• Multiple object tracking
• 3D Computer Vision
• Stereo vision
• Depth estimation
• Structure from motion
Instructional Methods
• Lectures: Presentation of theoretical concepts
and algorithms.
• Projects: Individual or group projects involving
the application of image processing and
computer vision techniques to real-world
problems.
Assessment
• Assignments: Regular assignments to reinforce
understanding of concepts.
• Projects: Implementation and presentation of
a final project applying image processing and
computer vision techniques to a specific
problem.
• Exams: Midterm and final exams covering
theoretical concepts and practical
applications.
Textbook
• Core Text:
– "Computer Vision: Algorithms and Applications"
by Richard Szeliski
• Additional Readings:
– "Digital Image Processing" by Rafael C. Gonzalez
and Richard E. Woods
– "Learning OpenCV 4 Computer Vision with Python
3" by Joseph Howse, Prateek Joshi, and Udacity
Image Processing
• Definition: Manipulation of images using mathematical
operations and algorithms to enhance, analyze, or extract
information from the images.
• Focus: Transformation of images at the pixel level. Image
processing techniques aim to improve the visual appearance
of images, remove noise, enhance features, and perform tasks
like image compression or restoration.
• Applications: Various fields such as medical imaging (e.g., MRI
or CT scans), satellite imaging, photography, digital art, and
more.
Project Demonstration
1. Finger Detection and Counting
2. Object Detection and Counting
3. Snake Game Using Hand Gesture
4. Vehicle detection In any video
5. Face Filters Like Instagram/Snapchat
6. Mouse Controlling Using Webcam
7. Facial Emotions Recognition
8. Face Recognition
9. Drawing Canvas Using Webcam
What is an Image?

• Image is a collection of pixels


• Pixel is a smallest unit in an image which contain color value.
• PPI (Pixel Per Inch.) [300 Pixels required per inch.
Video?

• So, Pixels to Images And Images to video


Computer Vision

• Definition: Enabling computers to interpret and understand


visual information from the real world.
• Focus: Unlike image processing, computer vision goes beyond
basic image manipulation and aims to replicate human vision
by extracting high-level information from images or video. This
involves tasks like object detection, recognition, tracking, scene
understanding, and 3D reconstruction.
• Applications: Computer vision has applications in a wide range
of domains, including autonomous vehicles, surveillance
systems, augmented reality, robotics, medical diagnostics, and
industrial quality control.
Key Differences
• Goal: Image processing focuses on enhancing or modifying
images, while computer vision aims to extract meaningful
information from images and understand the content.
• Level of Processing: Image processing operates at the
pixel level, manipulating individual pixels or small groups
of pixels. Computer vision operates at a higher level of
abstraction, dealing with objects, shapes, and scenes.
• Tasks: Image processing tasks include noise reduction,
sharpening, edge detection, and image segmentation.
Computer vision tasks include object detection,
recognition, tracking, and scene understanding.
Key Differences (Summary)
• Applications: While there is overlap in applications,
image processing is more commonly used in tasks
like medical imaging or photography enhancement,
while computer vision is applied in tasks requiring
visual understanding, such as autonomous driving
or facial recognition.
• Image processing is about modifying images for
specific purposes, while computer vision is about
enabling computers to understand and interpret
visual information like humans do.
Open CV
• OpenCV is an image processing library created
by Intel and supported by Willow Garage and
now maintained by Itseez.
• Opencv is available on MAC, Windows, Linux.
• Works in C, C++, and Python
• Supports cross-platform integration and it is
flexible.
• It is Open Source and free, easy to use and
install.
Open CV (Continued)
• In OpenCV we use array to store an image
• And Numpy Library is use to handle array
• And Image always store in 2D Array
Image Types
Basic image processing operations
Basic image processing operations involve manipulating digital images to enhance,
analyze, or extract information. Here are some common operations:
1. Image Filtering/Convolution: Applying a filter/kernel to an image to achieve
effects like blurring, sharpening, edge detection, etc. Common filters include
Gaussian, Sobel, and Laplacian filters.
2. Image Transformation: Operations like resizing, rotating, cropping, and flipping
an image.
3. Color Manipulation: Adjusting the color space, changing brightness, contrast,
saturation, and applying color transforms like grayscale conversion.
4. Thresholding: Converting a grayscale image into a binary image by setting a
threshold value. Pixels above the threshold are set to one value (often white),
while pixels below are set to another value (often black).
5. Morphological Operations: Operations like erosion, dilation, opening, and
closing, useful for noise removal, object detection, and image segmentation.
6. Histogram Equalization: Adjusting the contrast of an image by redistributing
pixel intensities.
Basic image processing operations
(Continued)

7. Feature Detection and Extraction: Detecting key points or regions in an image (e.g.,
corners, edges) and extracting features for further analysis or matching.
8. Image Blending: Combining two images by blending their pixel values using
techniques like alpha blending.
9. Geometric Transformation: Distorting an image through operations like affine
transformations, perspective transformations, or warping.
10. Image Segmentation: Dividing an image into meaningful segments or regions
based on pixel properties, such as color, intensity, or texture.
11. Noise Reduction: Removing or reducing noise from an image using techniques like
Gaussian smoothing, median filtering, or bilateral filtering.
12. Image Registration: Aligning multiple images to a common coordinate system,
useful in medical imaging, remote sensing, and computer vision.

You might also like