Instructor: Dr. Nazar Khan Semester: Fall 2015 Campus

Passing this course is necessary for students planning to register for an M.Phil Thesis with Dr. Nazar Khan.

This course is open to graduate students as CS-565. It is also open to undergraduate students as SE-461.

1. 
   CGPA
   
2. 
   FYP topic
   
3. 
   Instructor's permission (only in exceptional circumstances).
   

1. 
   General overview of the field of Image Analysis.
   
2. 
   Learn fundamental techniques and mathematical models in the areas of Image Processing and Computer Vision.
   
3. 
   Understand typical Computer Vision pipelines for solving problems.
   

1. 
   not be afraid of Mathematics,
   
2. 
   be able to develop Computer Vision applications,
   
3. 
   explain fundamental algorithms in the area along-with their mathematical subtleties,
   
4. 
   appreciate that Computer Vision is a deceptively hard problem,
   
5. 
   be equipped to read research papers in the area,
   
6. 
   report results in a scientifically satisfactory manner, and
   
7. 
   be comfortable enough with the terminology and techniques so as to pursue graduate level research in the area.
   

1. 
   Introduction (1 Week)
   
   1. 
      Computer Vision vs. Image Processing vs. Computer Graphics
      
   2. 
      Computer Vision vs. Biological Vision – The Grand Deception!
      
   3. 
      Successful Computer Vision solutions.
      
2. 
   Mathematical Background (1 Week)
   
   1. 
      Cartesian vs. Image axis
      
   2. 
      Taylor's formula
      
   3. 
      Constrained optimisation
      
   4. 
      SVD
      
3. 
   Image Processing (4 Weeks)
   
   1. 
      Image Types and their degradations.
      
   2. 
      Color Perception and Color Spaces
      
   3. 
      Filtering and Convolutions
      
      1. 
         Gaussian Smoothing
         
      2. 
         Derivative Filtering
         
   4. 
      Fourier Transform
      
      1. 
         Basic idea and background math
         
      2. 
         Euler's formula for circular motion
         
      3. 
         Projection onto circular motion basis
         
      4. 
         Frequency domain filtering
         
   5. 
      Image Adjustment
      
4. 
   2D Computer Vision (5 Weeks)
   
   1. 
      Edge Detection
      
   2. 
      Corner Detection
      
   3. 
      Hough Transform
      
   4. 
      Spatial Transformations
      
      1. 
         Types of spatial transformations
         
      2. 
         Recovering best transformation
         
      3. 
         Image warping
         
   5. 
      Optical Flow
      
      1. 
         Local Methods
         
      2. 
         Global Methods
         
5. 
   3D Computer Vision (3 Weeks)
   
   1. 
      Projective Geometry
      
      1. 
         Camera Models
         
      2. 
         Camera Matrix Anatomy
         
      3. 
         Camera Calibration
         
   2. 
      Stereo Reconstruction
      
      1. 
         The case of orthoparallel cameras
         
      2. 
         The case of converging cameras
         
         1. 
            Epipolar constraint and fundamental matrix
            
         2. 
            Estimation of fundamental matrix
            
         3. 
            Disparity estimation
            
6. 
   Machine Learning for Computer Vision (1 Week)
   
   1. 
      Principal Component Analysis
      

1. 
   To determine course grade, graduate students will be evaluated in a more rigorous manner.
   
2. 
   Theoretical assignments have to be submitted before the lecture on the due date.
   
3. 
   There will be no make-up for any missed quiz.
   
4. 
   Make-up for a mid-term or final exam will be allowed only under exceptional circumstances provided that the instructor has been notified beforehand.
   
5. 
   Instructor reserves the right to deny requests for any make-up quiz or exam.
   
6. 
   Worst score on quizzes will be dropped.
   
7. 
   Worst score on assignments will be dropped.