Course outline _-------------------------

Contact on email or in the classroom. Please No calls.

Sessionals are based on Assignments. Major assignment : implementation of research paper and submission in a journal or conference.

CSEC-722 Computer Vision

This course provides an introduction to computer vision, including fundamentals of image formation, camera imaging geometry, feature detection and matching, stereo, motion estimation and tracking, image classification, scene understanding, and deep learning with neural networks. This course discusses basic methods for applications that include finding known models in images, depth recovery from stereo, camera calibration, image stabilization, automated alignment, tracking, boundary detection, and recognition.

Contents

1. Computer Vision an Introduction.

2. Image formation.

3. Image Processing.

4. Feature Detection and Matching.

5. Feature-based Alignment.

6. Image Stitching.

7. Dense Motion Estimation.

8. Structure from Motion.

9. Recognition.

10. Computational Photography.

11. Stereo Correspondence.

12. 3D Reconstruction.

13. Image-based Rendering.

14. Statistical Texture Description, Methods Based on Spatial Frequencies, Co-occurrence Matrices, Edge Frequency, Primitive Length (Run Length).

15. Laws’ Texture Energy Measures, Fractal Texture Description, Multiscale Texture Description – Wavelet Domain Approaches, other Statistical Methods of Texture Description, Syntactic Texture Description Methods, Shape Chain Grammars, Graph Grammars, Primitive Grouping in Hierarchical Textures, Hybrid Texture Description methods, Texture Recognition Method Applications

Pre-Requisite: Linear Algebra

Recommended Book 1. Computer Vision Algorithms and Applications by Richard Szeliski, Springer, ISBN-13: 978-1848829343

Suggested Books 1. Image Processing, Analysis, and Machine Vision by Milan Sonka, CL Engineering, 3rd Edition, ISBN-13: 9780495082521 2. Computer Vision: Models, Learning, and Inference by Dr Simon J. D. Prince, Cambridge university press