Home Page Image
Please Note >
Exam reading materials are highlighted with yellow background in the table at right.


Section numbers in the readings columns below refer to the required textbook, D. A. Forsyth and J. Ponce, Computer Vision - A Modern Approach, Pearson, 2nd edition, 2012 (very different from the first edition). Additional material will be handed out in class or posted on the table below as appropriate.

Paper references below are specified through their Digital Object Identifier, when available. These links will get you to the full article if you or your institution have proper access privileges. For Duke students, this typically means that the link will work from a Duke computer, but not from elsewhere.

The syllabus below may change somewhat throughout the semester. Material in cells with a yellow background is required reading

  Module Description Required Readings Optional Readings Software and Data
Introduction purpose, state of the art, history     Slides on computer vision
Image Formation optics, sensing Image Formation, 1.1.1, 1.1.3 Rest of 1.1
Image Processing filtering, derivatives, and edges 4 (skip 4.3 and 4.4), Image Processing (skip sections 2.2, 2.3.1, 2.5) Smoothing and gradient code
Features feature detection 5, SIFT (skip sections 7 and higher) SURF, HOG Gaussian and Laplacian pyramid code, Vedaldi's VLFeat toolbox
Segmentation pixel grouping methods 6.2.2, 9.3.3, 9.3.4, 9.3.5, SLIC Rest of chapter 9 SLIC superpixel code
Classification machine learning methods for feature classification 15.1, 15.2.6, Performance Curves Rest of chapter 15  
Image Classification image summaries and end-to-end image classification 16.1.3, 16.2.2, Sivic and Zisserman, Viola and Jones Rest of chapter 16, Nilsback and Zisserman, Gehler and Nowozin  
Object Detection sliding windows, detection of articulated objects   17, Rowley et al., Felzenszwalb et al. Felzenszwalb et al. code