Course Name: Machine Vision
Main Text book: Machine Vision
Authors: Ramesh Jain, Rangachar Kasturi and Brain G.Schunck
McGraw Hill International Editions, 1995
Supporting Text Books:
Digital Image Processing (2nd Edition)
Authors: Rafael C.Gonzalez, Richard E.Woods
Publisher: Prentice Hall, 2002
Machine Vision
Authors: Wesley E.Snyder and Hairong Qi
Course syllabus:
1.1 Machine Vision
1.2 Relationship to other fields
1.3 Image Geometry
1.4 Image Definition
1.5 Levels of Computation
2.1 Thresholding
2.2 Geometric Properties
2.3 Run-Length Encoding
2.4 Binary Algorithms
2.5 Morphological Operations on Binary Images
2.5.1 Erosion
2.5.2 Dilation
2.5.3 Opening and Closing
2.7 Morphological Operations on Gray Scale Images
3.1 Regions and Edge
3.2 Regions Representation
3.3
3.4 Region Growing
3.5 Water-Shed Region Detection Algorithm
4.1 Linear Systems
4.2 Linear Filters
4.3 Gaussian Smoothing
4.3.1 Designing Gaussian Filters
5.1 Edge Detection Filters
5.2 Laplacian of Gaussian
5.3 Image Approximation
5.4 Gaussian Edge Detection
5.4.1 Canny Edge Detector
5.5 Sub-pixel Location Estimation
5.6 Edge Detection Performance
5.6.1 Methods for Evaluating Performance
5.6.2 Figure of Merit
6.1 Digital Curves
6.1.1 Chain Codes
6.1.2 Slope Representation
6.2 Curve Fitting
6.3 Polyline Representation
6.4 Circular Arcs
6.5 Conic Sections
6.6 Curve Approximation
6.6.1 Total Regression
6.6.2 Estimating Corners
6.6.3 Robust Regression
6.6.4 Hough Transform
7.1 Introduction
7.2 Statistical Methods of texture Analysis
7.3 Structural Analysis of Ordered Texture
7.4 Model Based Methods for Texture Analysis
8.1 Stereo Imaging
8.2 Stereo Matching
8.2.1 Edge Matching
8.2.2 Region Correlation
8.3 Range Imaging
8.3.1 Structured Lighting
8.3.2 Imaging Radar
8.4 Active Vision
9.1 Coordinate System
9.2 Rigid Body Transformation
9.3 Absolute Orientation
9.4 Relative Orientation
9.5 Camera Calibration
10.1 Change Detection
10.2 Segmentation Using Motion
10.3 Image Flow
10.4 Segmentation using a Moving Camera
10.5 Tracking
10.5.1 Deviation Function for Path Coherence
10.5.2 Path Coherence Function
10.5.3 Path Coherence in Presence of Occlusion
10.5.4 Application in Control Traffic
10.5.5 Kalman Filter
11.1 Complexity of Object Recognition
11.2 Object Representation
11.3 Feature Detection
11.4 Recognition Strategies
11.5 Verification
Course Evaluation is done as follows:
1. Mid Term Exam
2. Final Exam
3. Seminar (Oral presentation of
a research paper by students)
4. Course work (Implementation of
some basic algorithms using MATHLAB)
5. Course Project (Programming a research topic that may be related to the seminar)