Syllabus - Image Processing and Computer Vision (CS803 (A))

Computer Science and Engineering

Image Processing and Computer Vision (CS803 (A))

VIII

UNIT 1

Introduction to computer vision and Image processing (CVIP)

Basics of CVIP, History of CVIP, Evolution of CVIP, CV Models, Image Filtering, Image Representations, Image Statistics Recognition Methodology: Conditioning, Labeling, Grouping, Extracting, and Matching, Morphological Image Processing: Introduction, Dilation, Erosion, Opening, Closing, Hit-or-Miss transformation, Morphological algorithm operations on binary images, Morphological algorithm operations on gray-scale images, Thinning, Thickening, Region growing, region shrinking.

UNIT 2

Image Representation and Description

Representation schemes, Boundary descriptors, Region descriptors Binary Machine Vision: Thresholding, Segmentation, Connected component labeling, Hierarchal segmentation, Spatial clustering, Split& merge, Rule-based Segmentation, Motion-based segmentation. Area Extraction: Concepts, Data-structures, Edge, Line-Linking, Hough transform, Line fitting, Curve fitting (Least-square fitting).

UNIT 3

Region Analysis

Region properties, External points, Spatial moments, Mixed spatial gray-level moments, Boundary analysis: Signature properties, Shape numbers. General Frame Works For Matching: Distance relational approach, Ordered structural matching, View class matching, Models database organization

UNIT4

Facet Model Recognition

Labeling lines, Understanding line drawings, Classification of shapes by labeling of edges, Recognition of shapes, Consisting labeling problem, Back-tracking Algorithm Perspective Projective geometry, Inverse perspective Projection, Photogrammetric -from 2D to 3D, Image matching: Intensity matching of ID signals, Matching of 2D image, Hierarchical image matching. Object Models And Matching: 2D representation, Global vs. Local features

UNIT 5

Knowledge Based Vision

Knowledge representation, Control-strategies, Information Integration. Object recognition-Hough transforms and other simple object recognition methods, Shape correspondence and shape matching, Principal component analysis, feature extraction, Neural network and Machine learning for image shape recognition

Course Objective

Students should be able to Understand practice and theory of computer vision. Elaborate computer vision algorithms, methods and concepts. Implement computer vision systems with emphasis on applications and problem solving. Apply skills for automatic analysis of digital images to construct representations of physical objects and scenes. Design and implement real-life problems using Image processing and computer vision.

Practicals

Reference Books

  • Robert Haralick and Linda Shapiro, "Computer and Robot Vision", Vol I, II, Addison-Wesley, 1993

  • David A. Forsyth, Jean Ponce, "Computer Vision: A Modern Approach" Pearson

  • Milan Sonka,VaclavHlavac, Roger Boyle, "Image Processing, Analysis, and Machine Vision" Thomson Learning.