ECS 174: Computer Vision

Summary of Course Content

1. Students will acquire a general background on computer vision. Topics will include: Features and Filters
   1. Linear filters
   2. Edge detection and image gradients
   3. Edges, contours, and binary image analysis
   4. Texture
   5. Color
2. Grouping and Fitting
   1. Gestalt properties
   2. K-means, Mean-shift, Spectral clustering
   3. Hough transform
   4. Deformable contours
   5. RANSAC
   6. Homography
3. Recognition
   1. Local Invariant feature detection and description
   2. Indexing local features
   3. Instance recognition
   4. Generic category recognition
   5. Discriminative classifiers (Nearest Neighbors, Support Vector Machines, Boosting)
   6. Window-based models
   7. Part-based models

Illustrative Reading
Richard Szeliski, Computer Vision: Algorithms and Applications, Springer, 2011.

Potential Course Overlap
There is a very small overlap with ECS 173. ECS 174 will have very limited overlap with the "2D image processing" module of ECS 173 (it has no overlap with the other 2 modules). ECS 174 focuses less on low-level image processing, and more on the high-level understanding of visual content. So the computer vision algorithms and techniques taught in ECS 174 are geared towards achieving this goal, most of which are not covered in ECS 173. There is also a minimal overlap with ECS 171 in the teaching of some unsupervised and supervised learning algorithms. This overlap is minimal and the treatment of the underlying methods is fundamentally different: ECS 171 focuses on general pattern recognition and machine-learning techniques, whereas ECS 174 focuses on processing visual input (i.e., computing image and video features) and applications of machine-learning techniques to visual data. It also teaches many algorithms specific to computer vision problems that are not taught in general machine learning courses such as ECS 171.