15-385/685 Computer Vision


[ Home | Syllabus | Links ]


Date  Lecture Topic  Reading  Assignments 
T 1/15 1. Introduction (Overview)  
R 1/16 2.Imaging Basics   GWE Chapters 1,2
Image Representation  
T 1/22 3. Local Wavelet basis (multiscale)   GWE Chapter 7
R 1/24 4. Global Fourier basis(Frequency)   GWE Chapter 4 HW 1 out
T 1/29 5. Adaptive basis (PCA and ICA)   GWE Chapter 11.5
R 1/31 6. Adaptive basis(discriminants)  Duida and Hart
Image Processing  
T 2/5 7. Linear: Smoothing and enhancement  GWE chapter 3
R 2/7 8. Linear: Blind source separation  ICA Paper HW 1 due . HW 2 out
T 2/12 9. Feature extraction 1: edges and contrast  GWE 3.4 -3.5,10.1
R 2/14 10. Feature extraction 2: Corners and SIFTS  Lowes Paper
T 2/19 11.Feature Extraction 3:regions  GWE 9,10
Object Recognition  
R 2/21 12. Object Modeling   GWE 12   HW 2 due. HW 3 out
T 2/26 13. Bayesian Classification   GWE 12  
R 2/28 14. Feature Selection and Boosting   Viola and Jones  
T 3/4 15. Scene and Object Discrimination   Papers  
R 3/6 16. Mid Term Exam     HW 3 due, HW 4 out  
M 3/10 Midterm Grade due  
T 3/11 Spring Break
R 3/13 Spring Break  
Perceptual Analysis
T 3/18 17.Lightness and color paper Adelson HW 4 out
R 3/20 18.Contour completion and extraction GWE 10.1 10.2 Project Proposal Due (5 points)
T 3/25 19.Surface and texture    
R 3/27  20.Segmentation and figure-ground GWE 10.3-10.5
T 4/1
21.Optical flow and motion
Horn,Weiss and Adelson HW 4 due, HW 5 out
R 4/3 22.Reflectance and Photometric Stereo Horn
T 4/8 23.Shape from Shading Horn  
R 4/10 24.Binocular Stereo Horn HW 5 due
Dynamic Vision
T 4/15 25.Attention and context Torrelba Project Midterm (5 Points)
R 4/17 No Class Spring Carnival  
T 4/22 26.Tracking(particle filtering) Isard and Blake
R 4/24 27.Hierarchial feedback Computation Lee, Zhu,Mumford FCE
T 4/29 28.Review and Catching up . FCE
R 5/1 29.Midterm 2 . .
M 5/5
Project Due
M 5/12 Final Examination(Conference)

Course Description

An introduction to the theory and practice of computer vision, i.e. the analysis of the patterns in visual images with the view to understanding the objects and processes in the world that generate them. Major topics include optics, image representation, feature extraction, image processing, object recognition, feature selection, probabilistic inference, perceptual analysis and organization, dynamic and hierarchical processing. The emphasis is on the learning of mathematical concepts and techniques and the translation of them to Matlab programs to solve real vision problem. The discussion will be guided by comparision with human and animal vision, from psychological and biological perspectives.

Course Information:

Class location and time: Wean 5403. Tuesday, Thursday 3:00 p.m - 4:20 p.m.
Recitation: (optional) Matlab tutorials: place and time TBA.
Website: course info: http://www.cs.cmu.edu/afs/andrew/scs/cs/15-385/www
Course directory: homework submission: /afs/andrew.cmu.edu/scs/cs/15-385/
Blackboard: Lecture notes/Handouts/Solutions/Homework Submission http://blackboard.andrew.cmu.edu/
Recommended textbook: Ganzalez, Woods and Eddins (2004) Digital Image Processing with Matlab
Other reference textbooks (on reserve): Forsyth, D. & Ponce, J. Computer Vision: a modern approach, Prentic Hall, 2002 (F)
Palmer, S.E. Vision Science: Photons to Phenomenology. MIT Press. Cambridge, MA. 1999 (P)
Horn, B. Robot Vision, McGraw Hill, 1986 (H)
Duda, R., Hart, P.E., & Stork, D.G. Pattern Classification , 2001. (D)
Gonzalez, R. and Woods, R. Digital Image Processing, Addison-Wesley,1993.


Assignments % of Grade Tentative Topic
HW 1 10 Wavelet and Fourier transform
HW 2 10 Blind source separation
HW 3 10 Image processing techniques
HW 4 10 Scene recognition
HW 5 10 Perceptual organization
Term Project 25 Proposal/Paper/Presentation
Examinations 10/15 Test 1/Test 2

15-385 vs 15-685:

15-385 is designed primarily for undergraduate students. Graduate students and undergraduates (with permission) can take 15-685 for (12 units) graduate credit. 15-385 but not 15-685 students can collaborate on some assignments and the term project. The term project for the graduate students is also expected to be more substantial.


Reports should be type-written if possible, in pdf file, submitted to Blackboard. Matlab code and program output to be submitted to course directory on andrew. Templates (for doc and latex) will be provided. Students can collaborate with one partner on assignment 1-2.


For term project, a type-written report (hard and soft in pdf or ps format) is necessary. Collaboration with one classmate is allowed for 15-385 students. The project write-up should be no less than 6 and no more than 10 pages in CVPR format, with additional pages allowed for commented Matlab codes as appendix. Final Exam day will be a conference of project presentations, with selected projects for oral presentation, and others as posters.

Late Policy:

No credit for late homework or project. One-time pardon for late homework within one week.