CBM371 Computer Vision Syllabus:
CBM371 Computer Vision Syllabus – Anna University Regulation 2021
COURSE OBJECTIVES:
To review image processing techniques for computer vision.
To understand various features and recognition techniques
To learn about histogram and binary vision
Apply three-dimensional image analysis techniques
Study real world applications of computer vision algorithms
UNIT I INTRODUCTION
Computer Vision ,What is Computer Vision – Low-level, Mid-level, High-level ; Fundamentals of Image Formation, Transformation: Orthogonal, Euclidean, Affine, Projective.
UNIT II FEATURE EXTRACTION
Feature Extraction -Edges – Canny, LOG, DOG; Line detectors (Hough Transform), Corners – Harris and Hessian Affine, Orientation Histogram, SIFT, SURF, HOG, GLOH, Scale-Space Analysis- Image Pyramids and Gaussian derivative filters, Gabor Filters.
UNIT III COLOR IMAGES, BINARY VISION
Simple pinhole camera model – Sampling – Quantisation – Colour images – Noise – Smoothing – 1D and 3D histograms- Back-projection – k-means Clustering – Thresholding – Threshold Detection Methods – Variations on Thresholding – Mathematical Morphology – Connectivity.
UNIT IV 3D VISION
Methods for 3D vision – projection schemes – shape from shading – photometric stereo – shape from texture – shape from focus – active range finding – surface representations – point-based representation – volumetric representations – 3D object recognition – 3D reconstruction
UNIT V MOTION
Introduction to motion – triangulation – bundle adjustment – translational alignment – parametric motion–spline-based motion- optical flow – layered motion.
30 PERIODS
PRACTICALS:
1. Document Image Analysis
2. Biometrics based Recognition
3. Object Recognition
4. Object Tracking
5. Medical Image Analysis
6. Content-Based Image Retrieval
7. Video Data Processing
30 PERIODS
COURSE OUTCOMES:
On successful completion of this course, the student will be able to
CO1: explain low level processing of image and transformation techniques applied to images.
CO2: develop the feature extraction and object recognition methods
CO3: apply Histogram transform for detection of geometric shapes like line, ellipse and objects.
CO4: illustrate 3D vision process and motion estimation techniques.
CO5: apply vision techniques to real time applications.
TOTAL:60 PERIODS
TEXT BOOKS
1. Richard Szeliski, “Computer Vision: Algorithms and Applications”, Springer Verlag London Limited,2011
2. Simon J. D. Prince, Computer Vision: Models, Learning, and Inference, Cambridge University Press, 2012
3. D. A. Forsyth, J. Ponce, “Computer Vision: A Modern Approach”, Pearson Education, 2003
REFERENCES
1. Mark Nixon and Alberto S. Aquado, Feature Extraction & Image Processing for Computer Vision, Third Edition, Academic Press, 2012.
2. E. R. Davies, “Computer & Machine Vision”, Fourth Edition, Academic Press, 2012.
3. Concise Computer Vision: An Introduction into Theory and Algorithms, by Reinhard Klette, 2014.