




This course provides an introduction to image processing and computer vision. We start from the basics of image formation (cameras, light, color), then cover the fundamental concepts in 2D signal processing (2D convolutions, Fourier transforms, etc) and lowlevel vision (edges, texture), and finally move on to higher level problems such as motion analysis, image segmentation, image classification and retrieval. 

Lectures:  TuTh, 12:30p1:50p, Peter 103 

Discussion: 
W 11a  11:50a, PETER 104 

Instructor:  Nuno Vasconcelos, n u n o @ e c e . u c s d . e d u, EBU15602  
Office hours:  Friday, 9:30a10:30a  
Teaching Assistant:  Pedro Morgado, p m a r a v i l (at) u c s d . e d u, EBU14608 

Office hours:  Wednesday, 17:00a18:30p  
Text:  Computer Vision: a modern approach  
D. Forsyth and J. Ponce, Prentice Hall, 2003  
Secondary text:  Two Dimensional Signal and Image Processing Jae Lim, Prentice Hall, 1990 

Syllabus:  [ps, pdf]  
Homework:  Problem set 1 [ps, pdf, data] Issued: April 7 Due: April 14  
Problem set 2 [ps, pdf, data] Issued: April 14 Due: April 21  
Problem set 3 [ps, pdf,
data] Issued: April 21 Due: April 28 

Problem set 4 [ps, pdf, data] Issued: April 28 Due: May 12  
Problem set 5 [ps, pdf, data] Issued: May 12 Due: May 24  
Problem set 6 [ps, pdf] Issued: May 24 Due: June 2  
Note:  There are various editions of the book. The numbers of
problems from the book may not be those of your version. In general, you can tell which problem we are talking about, by hints, notes, etc. If you don't, make sure to ask. 

Note: 
Only the computer problem of each assignment will be graded.
You should not turn in the other problems. HW should be submitted to the TA. 


Midterm:  May 5: covers Lectures 210 
Final:  June 6: covers all materials  
Readings:  Lecture 1: introduction  
Lecture 2: cameras (sections 11.2.2, 1.3, F&P) [slides, videos]  
Lecture 3: radiometry (chapter 4, F&P) [slides]  
Lecture 4: radiometry, light sources (sections 5.15.2.2, 5.3.1, F&P) [slides,video]  
Lecture 5: color (sections 6.16.3.3, F&P)[slides]  
Lecture 6: 2D DSP (chapter 1, Lim; chapter 7, F&P)[slides]  
Lecture 7: 2D DSP, Fourier transforms (chapter 1, Lim; chapter 7, F&P)[slides]  
Lecture 8: filtering, smoothing and noise (chapter 8, F&P) [slides]  
Lecture 9: edges (chapter 8, F&P) [slides]  
Lecture 10: edges, interpolation, templates (chapter 8, F&P) [slides]  
Lecture 11: midterm review [problems]  
Lecture 12: midterm  
Lecture 13: 2D DFT (chapter 3, Lim; chapter 7, F&P) [slides, video]  
Lecture 14: 2DDFT (chapter 3, Lim) [slides]  
Lecture 15: DCT (chapter 3, Lim) [slides]  
Lecture 16: scale, pyramids, and texture (chapter 9, F&P) [slides]  
Lecture 17: least squares [slides] (section 15.2, F&P; section 3.3 Strang)  
Lecture 18: motion, least squares [slides] (paper by Lucas and Kanade)  
Lecture 19: MPEG [slides]  
Lecture 20: JPEG [slides]  
Extra material:  Linear Algebra and DSP [slides]  