Page 24 - REC :: M.E. CSE Curriculum and Syllabus - R2019

CP19P05 COMPUTER VISION Category L T P C
PE 3 0 0 3

Objectives:
⚫ To Develop of algorithms and techniques to analyze and interpret images
⚫ To understand the fundamental concepts related to multi-dimensional processing
⚫ To perform pattern analysis and visual geometric modeling
⚫ To understand the 3D image analysis
⚫

UNIT-I DIGITAL IMAGE LOW-LEVEL PROCESSING 9
Overview and State-of-the-art, Fundamentals of Image Formation, Transformation: Orthogonal, Euclidean, Affine,
Projective, Fourier Transform, Convolution and Filtering, Image Enhancement, Restoration, Histogram Processing

UNIT-II FEATURE EXTRACTION 9
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 and DWT.

UNIT-III IMAGE SEGMENTATION 9
Region Growing, Edge Based approaches to segmentation, Graph-Cut, Mean-Shift, MRFs, Texture Segmentation;
Object detection.

UNIT-IV MOTION ANALYSIS AND IMAGE STITCHING 9
Background Subtraction and Modeling, Optical Flow, KLT, Spatio-Temporal Analysis, Dynamic Stereo; Motion
parameter estimation, Image Stitching

UNIT-V SHAPE FROM X 9
Light at Surfaces; Phong Model; Reflectance Map; Albedo estimation. Photometric Stereo; Use of Surface
Smoothness Constraint; Shape from Texture, color, motion and edges.

Total Contact Hours : 45

Course Outcomes:
Upon completion of the course, students will be able to:
⚫ See how images are represented numerically
⚫ Implement image processing techniques
⚫ Learn why distinguishing features are important in pattern and object recognition tasks.
⚫ Find the contours and edges of multiple objects in an image.
⚫ Learn about background subtraction for video.

Reference Book (s):
1 Richard Szeliski, “Computer Vision: Algorithms and Applications”, Springer-Verlag London Limited 2011.
2 D. A. Forsyth, J. Ponce,“Computer Vision: A Modern Approach”, Pearson Education, 2003.
Richard Hartley and Andrew Zisserman, “Multiple View Geometry in Computer Vision”, Second Edition,
3
Cambridge University Press, March 2004.
nd
4 K. Fukunaga,“Introduction to Statistical Pattern Recognition”, 2 Edition, Morgan Kaufmann, 1990.
5 R.C. Gonzalez and R.E. Woods, Digital Image Processing, Addison- Wesley, 1992.