This course gives an overview of fundamental methods in computer vision from a computational perspective. Methods studied include: camera systems and their modeling; computation of 3-D geometry from binocular stereo, motion, and photometric stereo; and object recognition. Edge detection and color perception are covered as well. Elements of machine vision and biological vision are also included.This course gives an overview of fundamental methods in computer vision from a computational perspective. Methods studied include: camera systems and their modeling; computation of 3-D geometry from binocular stereo, motion, and photometric stereo; and object recognition. Edge detection and color perception are covered as well. Elements of machine vision and biological vision are also included.

1. Image Processing
• Image Filtering
• Image Smoothing
• Image Enhancement
• Edge Detection
• Line Detection
2. Feature, Matching and Tracking
• Feature Detection
• Feature Descriptors
• Feature Matching
• Feature Tracking and Optical Flow
3. Multiple View Geometry and 3D Reconstruction
• 2D Transformations
• Two-View Geometry
• Affine Strucuture from Motion
4. Segmentation
• K-means and EM
• Spectral clustering and graph cuts
• Color Segmentation
• Texture Segmentation
5. Recognition
• Nearest neighbors, support vector machines, bag of words
• Eigenfaces
• Image classification
• Object detection

The class does not have a required book. The reading material includes the slides posted in this website as well as your class notes.

For complementary reading, you may read the following online book.

1. R. Szeliski, Computer Vision, Springer 2011

Most of the slides used in class are based on slides from Prof. Hager's 2012 version of the course. Slides on corner detection are based on Prof. Steve Seitz's course. The copyright of the slides belongs to the respective authors.

Date	Slides	Assignments	Solutions
09/03/2013	Overview
09/05/2013	Image Filtering
09/10/2013	Image Filtering
09/12/2013	Edge and Line Detection	Homework 1	Homework 1 Solution
09/17/2013	Feature Point Detection
09/19/2013	Feature Descriptors
09/24/2013	Feature Tracking	Homework 2	Homework 2 Solution
09/26/2013	2D Transformations
10/01/2013	2D Transformations
10/03/2013	2-View Geometry
10/08/2013	2-View Geometry
10/10/2013	2-View Geometry
10/15/2013	Fall Break
10/17/2013	Homography	Homework 3	Homework 3 Solution
10/22/2013	Segmentation: K-means	Sample Exam
10/24/2013	Segmentation: EM
10/29/2013	Segmentation: EM	Homework 4	Homework 4 Solution
10/31/2013	Exam 1	Exam 1	Exam 1 Solution
11/05/2013	Segmentation: Random Walker
11/07/2013	Segmentation: Spectral Clustering
11/12/2013	Segmentation: Spectral Clustering
11/14/2013	Recognition: Introduction and Bag of Words Models	Homework 5
11/19/2013	Recognition: Part-Based Models
11/21/2013	Recognition: Discriminative Models
11/26/2013	Recognition: Joint Semantic and Recognition
11/28/2013	Thanksgiving Break
12/03/2013	Review 2
12/05/2013	Exam 2

1. Homeworks (40%): There will homeworks every other week (approximately). Homework problems will include both analytical exercises as well as programming assignments in MATLAB.
2. Exams (40%): There will be two in-class exams, one on October 29 and the other on December 3rd.
3. Project (20%): There will be a final project to be done in teams of two students. Each team will write a 6-page report and give a 10 minute presentation (including 3 minutes for questions) on the scheduled exam day (mid December).

• Late policy:
• Homeworks and projects are due on the specified dates.
• No late homeworks or projects will be accepted.
• Honor policy:

  The strength of the university depends on academic and personal integrity. In this course, you must be honest and truthful. Ethical violations include cheating on exams, plagiarism, reuse of assignments, improper use of the Internet and electronic devices, unauthorized collaboration, alteration of graded assignments, forgery and falsification, lying, facilitating academic dishonesty, and unfair competition.

• Homeworks and exams are strictly individual
• Projects can be done in teams of two students

• Dictionary of Computer Vision and Image Processing
• HIPR-2 Image Processing Learning Resources
• The Computer Vision Homepage
• CV Online - Compendium of Computer Vision
• Previous year's course webpage
• MATLAB tutorial handout during TA session - from a course offering at UCSD