Announcements

• Project Proposal Revision Feedback :: Come see me this week to discuss.
• Literature Review Presentation begin on Thursday :: You are required to print and read both papers. However, you only need to submit an abridged paper summary (summary + 1-2 important conceptual points or questions) for one of the posted papers.

Introduction

This course focuses on computer perception: using computers to analyze images, sounds, and videos. We will specifically focus on object recognition and multimedia retrieval, but will also look at segmentation, localization, clustering, tracking and other perception tasks.

The first third of this class will be a lecture style format that introduces some fundamental topics and tools. The remaining two thirds will be a seminar style format in which students will present academic papers and conduct research.

Class information

Professor: Douglas Turnbull
Office: Science Center 255
Phone: (610) 597-6071
Office hours: TBA or by appointment

Room: Science Center Conference Room
Time: Tuesday, Thursday 11:20pm–12:35pm
Text: None, but lots of suggested references and weekly readings...

Schedule

Grading

This course is structured like a graduate seminar course where each student will be graded based on both their contribution to the seminar and their research project.

Course Work 40% Problem Set 1 4% Problem Set 2 6% Assigned Paper Presentation 10% Weekly Notes 20%

Project 60% Proposal 5% Proposal Update 5% Literature Review Presentation 10% Manuscript 10% Manuscript Reviews 5% Conference Presentation 10% Final Paper 15%

Bonus - Submit paper to workshop or conference
Double Bonus - Submit paper to peer-reviewed conference

Weekly Notes

For every academic paper that we read for class, you should prepare a 1-page summary. The format should be as follows:

• Summary: 3-4 sentences that describe what the paper is about. What is the problem? How do the authors attempt solve the problem? What do they conclude from the results?
• Strentgh: a list of 3 strengths of the paper. Is the solution novel and interesting? Are the results compelling? Is the evaluation clear and illustrative? Is the paper successful?
• Weaknesses: a list of three weaknesses. Are there any hole in the logic of the paper? Are the result dubious? Do the authors make any questionable assumption?
• Questions: a list of three (or more) things that you found confusing. We will be covering some pretty dense papers this semester. It usually takes a couple of readings before a paper become comprehensible. Evem still, do not be intimidated if you only understand a small portion of each paper. With time and experience, you will get better at understanding the material.

Academic Integrity

Academic honesty is required in all work you submit to be graded. With the exception of your lab partner on lab assignments, you may not submit work done with (or by) someone else, or examine or use work done by others to complete your own work. You may discuss assignment specifications and requirements with others in the class to be sure you understand the problem. In addition, you are allowed to work with others to help learn the course material. However, with the exception of your lab partner, you may not work with others on your assignments in any capacity.

All code you submit must be your own with the following permissible exceptions: code distributed in class, code found in the course text book, and code worked on with an assigned partner. In these cases, you should always include detailed comments that indicates which parts of the assignment you received help on, and what your sources were.

``It is the opinion of the faculty that for an intentional first offense, failure in the course is normally appropriate. Suspension for a semester or deprivation of the degree in that year may also be appropriate when warranted by the seriousness of the offense.'' - Swarthmore College Bulletin (2007-2008, Section 7.1.2)

Please see me if there are any questions about what is permissible.

External Links

Links that are related to the course may be posted here. If you have suggestions for links, let me know.

Machine Learning and Pattern Recognition

• Pattern Classification (2nd ed.) - Duda, Hart, and Stork
• Pattern Recognition and Machine Learning - Christopher Bishop
• Artificial Intelligence: A Modern Approach - Russell and Norvig
• Mathworld - online math reference
• Wikipedia - general reference

Image and Audio Processing

• Image Processing - Farid
• Scientist & Engineer's Guide to Digital Signal Processing - Smith

Matlab - General Info

• Matlab: Documentation, Getting Started, etc.
• Matlab Primer
• Tutorial Code Snippets
• Matlab Frequently Asked Questions

Matlab - Computer Perception

• Piotr Image & Video Toolbox for Matlab - optimized for video and image processing
• Auditory Toolbox for Matlab - audio processing toolbox
• Music/Audio Matlab Toolbox
• Matlab Toolboxes - signal processing, image processing, statistics

Other Software (Weka, Matlab, etc.)

• Weka - Java-based Machine Learning Software
• Marysas - Music Signal Processing in Java
• Echonest Music API - content and context based music information