L T P C

Image Processing and Computer Vision

3 0 0 3

Course Objective
This course gives an introduction to the concepts and applications of image processing and
computer vision. This course teaches the fundamental techniques for image processing tasks such
as image restoration, segmentation and compression. Computer Vision is a field that spans
multiple disciplines and draws links to several traditional fields such as image processing, optics,
probability, and statistics. After introducing image processing techniques, vision tasks such as
shape reconstruction, object and scene recognition etc. are taught.
Course Content:
Module 1: Fundamentals – Human Vision System; Computer Vision System; Camera Geometry
Fundamentals
Digital Image Fundamentals: A simple image formation model, image sampling and quantization,
basic relationships between pixels
Module 2: Image enhancement in the spatial domain: Basic gray-level transformation, histogram
processing, enhancement using arithmetic and logic operators, basic spatial filtering, smoothing
and sharpening spatial filters, combining the spatial enhancement methods, nonlinear
transformations for enhancement
Module 3: Image restoration – using spatial filters, Wiener filter; Introduction to colour spaces
and colour image processing; Morphological image processing – erosion and dilation, opening
and closing, hit-or-miss transform, thinning and shape decomposition;
Module 4: Image segmentation – edge detection, thresholding, region-based segmentation;
Image compression – fundamentals, lossless coding, predictive coding, transform coding.
Module 5: Patterns and patterns classes, recognition based on decision–theoretic methods,
matching, optimum statistical classifiers, neural networks, structural methods – matching shape
numbers, string matching object recognition, scene recognition, face detection and human motion
categorization.

Text Books:
1. Gonzales R. C. and Woods R. E., Digital Image Processing, Prentice-Hall, 4 ed, 2018
2. Computer Vision: Algorithms and Applications, by Richard Szeliski, Springer, 2010. 3.
Learning OpenCV, by Gary Bradski & Adrian Kaehler, O'Reilly Media, 2008.
References:
1. Multiple View Geometry in Computer Vision, 2nd Edition, by R. Hartley, and A.
Zisserman, Cambridge University Press, 2004.
 2. Computer Vision: A Modern Approach, by D.A. Forsyth and J. Ponce, Prentice Hall,
2002.
3. Pattern Classification (2nd Edition), by R.O. Duda, P.E. Hart, and D.G. Stork, Wiley-
Interscience, 2000.
4. Pratt W. K., Digital Image Processing, 4 ed, Wiley, 2007
5. Bovik, A. C., The essential guide to image processing, Academic Press, 2009
6. Forsyth D. A. and Ponce J., Computer Vision - A Modern Approach, 2 ed, 2012.
7. M Sonka, V Hlavac, and R Boyle: Image Processing, Analysis, and Machine Vision,
Thomson, Toronto, 4 ed, 2015.
Course Outcomes:
At the end of the course, a student will be able to:
1. Understand the fundamentals of image processing such as sampling and quantization
2. Process image datasets in tools such as OpenCV and perform key image processing tasks
such as transformations, restoration, segment and compression
3. Learn the algorithms and techniques used in image processing
4. Understand the fundamentals of computer vision such as Cameras and projection models
5. Process image and video datasets in tools such as OpenCV and perform key computer
vision tasks such as clustering; shape reconstruction from stereo, object recognition,
scene recognition, face detection and human motion categorization.
6. Implement the algorithms and techniques used in computer vision.
 L T P C
BCA 351 Image Processing and Computer Vision LAB
0 0 2 1

Course Learning Objectives:

This course gives an introduction to the concepts and applications of image processing and
computer vision. This course implements fundamental techniques operations for image
processing tasks such as image restoration, segmentation. Process image and video datasets in
tools such as OpenCV and perform key computer vision tasks such as clustering; shape
reconstruction from stereo, object recognition, scene recognition, face detection and human
motion categorization.

List of Experiments:

1. Perform basic Image Handling and processing operations on the image.

 Reading an image in python
 Convert Images to another format
 Convert an Image to Grayscale
 Play a video file
2. The objective of this lab is to introduce Geometric Transformation and apply it to
images.
 Perform scaling, rotation and shifting operations on an image using
OpenCV().
 Perform image reflection on an image using OpenCV().
 Perform Image shearing on an image using OpenCV().
 Apply the affine transformation on an image using OpenCV().
3. Compute Homography Matrix
 Compute the Homography matrix for a 4 data points without SVD and
transformed the point using the computed homography matrix.
 Compute the Homography matrix for a 4 data points using DLT and
transformed the point using the computed homography matrix.
4. Perspective Transformation
 Remove the Projective Distortion in the image using Homography
 For perspective transformation, you need a 3x3 transformation matrix.
Straight lines will remain straight even after the transformation. To find this
transformation matrix, you need 4 points on the input image and
corresponding points on the output image. Among these 4 points, 3 of
them should not be collinear. Then the transformation matrix can be
found by the function cv2.getPerspectiveTransform(). Then apply
cv2.warpPerspective() with this 3x3 transformation matrix.
5. Compute Fundamental Matrix
 Compute the Fundamental Matrix using the Least Square Minimization
 Compute the Fundamental Matrix using the 8-point algorithm.
 Plotting epipole lines using the Fundamental Matrix computed in (1).
 Finding the projection matrix of the second camera using the
Fundamental Matrix (assuming that the first camera is calibrated).
6. Edge Detection, Line Detection and Corner Detection
 Compute the edge detection using Sobel, Prewitt and canny operator.
 Implement the Harris Corner detector algorithm to determine the corner in the
image.
 Implement the Harris Corner Detector algorithm without the inbuilt
OpenCV() function.
 Detect the line using Hough Transform

7. SIFT feature descriptors

 Write a program to compute the SIFT feature descriptors of the image.
 Write a program to generate a panorama image using SIFT feature descriptor.
8. SURF and HOG feature descriptors
 Write a program to compute the SURF feature descriptors of the image.
 Write a program to compute the HOG feature descriptors of the image.

Course Learning Outcomes:

At the end of this course, students will be able to

1. Be able to understand basic concepts image processing, image storage and

types of transformations that can be applied to images.
2. Use computer vision techniques behind a wide variety of real-world
applications.
3. Perform image transformation, Edge detection, object detection