L T P C
2303CS041 COMPUTER VISION FOR ENGINEERS
3 0 0 3
PREREQUISITES:
Computer Programming Languages, Linear Algebra, Vector Calculus, Data structures
COURSE OBJECTIVES:
1. To understand the fundamental concepts related to Image formation, transformation and
processing.
2. To understand the concepts of image segmentation and enhancements.
3. To become familiar with motion estimation and image recognition.
4. To develop skills on 3D reconstruction.
5. To gain hands-on experience on image recognition with computer vision applications.
COURSE OUTCOMES:
Upon successful completion of this course, students will be able to:
CO1: Understand the basic principles of image processing and its significance in real world.
CO2: Implement various approaches for image enhancements, segmentation and restoration.
CO3: Analyze images and videos for problems such as tracking and structure from motion.
CO4: Apply 3D image reconstruction techniques.
CO5: Apply computer vision techniques to real-world problems.
COs Vs POs & PSOs MAPPING:
COs PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11 PSO1 PSO2
CO1 3 2 2 2 - - - - - 2 3 1 2
CO2 2 2 2 3 - - - - - 2 2 1 2
CO3 2 2 2 3 3 - - - 2 1 3 2 2
CO4 2 2 2 3 3 - - - 2 2 3 2 2
CO5 1 1 3 3 2 - - - 1 2 2 2 3
COURSE CONTENTS:
MODULE I IMAGE FORMATION AND TRANSFORMS 9 Hours
Image Formation: Image Processing Fundamentals - Image Models - Image Acquisition - Sampling and
Quantization - Relationship between pixels - Digital Image Processing Systems.
Image Transforms: Fourier Transform - Extension to 2D - Properties of Fourier transformations -
Convolution and Linear Filtering.
MODULE II IMAGE ENHANCEMENTS AND FEATURE BASED ALIGNMENT 9 Hours
Image Enhancements: Histogram Equalization - Image Smoothing - Image Sharpening - Edge Detection -
Segmentation: Active Contours - Split and Merge - Mean Shift - Mode Finding - Normalized Cuts.
Feature Based Alignment: 2D and 3D Feature Based Alignment - Pose Estimation.
MODULE III MOTION ANALYSIS 9 Hours
Structure from Motion: Triangulation - Two-Frame Structure from Motion - Factorization - Bundle
Adjustment - Constrained Structure and Motion.
Dense Motion Estimation: Translational Alignment - Parametric Motion - Spline-Based Motion - Optical
Flow - Layered Motion.
MODULE IV 3D RECONSTRUCTION 9 Hours
3D Reconstruction: Stereo Vision -Shape from Shading - Shape from Texture - Shape from Focus-
Projection Schemes - Active Range Finding - Surface Representations: Point-Based Representations -
Volumetric Representations - Mesh-Based Representations - Model-Based Reconstruction: CAD-Based
Reconstruction - Template-Based Reconstruction.
MODULE V RECOGNITION 9 Hours
Recognition: Object Detection - Face Recognition - Instance Recognition - Category Recognition -
Context and Scene Understanding - Computer Vision Applications.
TOTAL: 45 HOURS
TEXT BOOKS:
1. Richard Szeliski, “Computer Vision: Algorithms and Applications”, Springer- Texts in Computer
Science, Second Edition, 2022.
2. R. C. Gonzalez and R. E. Woods “Digital Image Processing”, Fourth Edition, Pearson Education,
2018.
REFERENCES:
1. D. A. Forsyth, J. Ponce, “Computer Vision: A Modern Approach”, Second Edition, Pearson
Education, 2019.
2. E. R. Davies: Computer and Machine Vision - Theory, Algorithms and Practicalities, Elsevier
(Academic Press), Fourth edition, 2018.
3. Simon J. D. Prince, Computer Vision: Models, Learning, and Inference, Cambridge University Press,
2019.
4. Richard Hartley and Andrew Zisserman, Multiple View Geometry in Computer Vision, Second
Edition, Cambridge University Press, March 2017..
5. https://onlinecourses.nptel.ac.in/noc19_cs58/preview
