New Jersey Institute of Technology
Department of Computer Science
CS780 - Computer Vision -
Fall'2008
Monday, 2:30 - 5:25 PM, KUPF xxx
Course
Description | Readings | Tentative Contents | Grading
Policy | Miscellaneous
Chengjun Liu, Ph.D.
Phone: 973-596-5280
Email: chengjun.liu@njit.edu
Office: GITC
4306
Hours: MT xxxPM-xxxPM or by appointment
Course Description
- This course introduces computational models of computer vision
and their implementation on computers, and focuses on material that is
fundamental and has a broad scope of application. Topics include
contemporary
developments in all mainstream areas of computer vision e.g., Image
Formation,
Feature Detection/Representation, Classification and Recognition,
Motion
Analysis, Camera Calibration, 3D/Stereo Vision, Shape From X (motion,
shading,
texture, etc.), and typical applications such as Biometrics.
- Prerequisites: CS 610 –
Data Structures and Algorithms
Readings
- E. Trucco and A. Verri, Introductory
Techniques for 3D Computer Vision, Prentice Hall, 1998.
- D. Forsyth and J. Ponce, Computer
Vision - A modern approach, Prentice Hall, 2003.
- D. Marr, Vision: A Computational
Investigation into the Human Representation and Processing of Visual
Information, Freeman, San Francisco, 1982.
- V. N. Vapnik, The Nature of Statistical Learning Theory,
2nd edition, Springer, 2000.
- Selected
papers.
Tentative
Contents
- Introduction
- Computer Vision Fundamentals
- Related Fields: IP, PR, NN, ML, AI
- Image Fundamentals: Formats/Protocols
- Matlab
- Image Formation
- Basic Optics
- Basic Radiometry
- Camera Models
- Camera Parameters
- Geometric Feature Representation
- Noise Reduction (frequency domain,
spatial domain)
- Edge Detection (Canny, Zero-crossing,
LOG, Prewitt, etc.)
- Corner Detection
- Line & Curve Detection (Hough
Transform),
- Ellipse Detection
- Deformable Contours (snakes)
- Statistical Feature Representation
- Principal Component Analysis (PCA)
- Independent Component Analysis (ICA)
- Shape and Texture
- Gabor Wavelets
- Classification and Recognition Methods
- Bayes Classifier and the MAP Rule
- Linear Methods (LDA/FLD)
- Kernel Methods (SVM, kernel PCA, kernel
FLD, etc.)
- Motion Analysis
- Motion Field
- Optical Flow
- Tracking (Kalman filter, Condensation)
- Structure From Motion
- Biometrics
- Face Recognition
- Iris Recognition
- Fingerprint Recognition
- Camera Calibration
- Intrinsic/Extrinsic Camera Parameters
- Explicit Parameter Calibration
- Projection Matrix-based Parameter Calibration
- 3D Vision - Stereo Vision
- Correspondence
- Epipolar Geometry (E and F matrices)
- 3D Reconstruction
- Shape From X
- Shape From Shading
- Shape From Texture
- Evolutionary Computation for Computer
Vision
- Genetic Algorithms (GA)
- Evolutionary Strategy (ES)
- Evolutionary Programming (EP)
- Neural Computation for Computer Vision
- Multilayer Perceptrons and BP Algorithm
- Radial-Basis Function Networks
- Machine Learning for Computer Vision
- Bayesian Learning
- Decision Tree
- Reinforcement Learning
- Statistical Learning Theory (STL)
- Structural Risk Minimization (SRM)
- Support Vector Machines (SVM)
Grading
Policy
Projects (topics are related
to our course Contents)
Presentation (~10 mins.)
Paper (~10 pages)
Class attendance
NJIT Honor Code will be upheld, and any
violations will be brought to the immediate attention of the Dean of
Students.
Students will be consulted with by the
instructor and must agree to any modifications or deviations from the
syllabus throughout the course of the semester.
Miscellaneous