Tracy Hammond
Email: hammond at cs.tamu.edu
Office: HRBB 414C
Phone: 979 862 4284
Analysis, implementation, and comparison of sketch recognition algorithms, including feature-based, vision-based, geometry-based, and timing-based recognition algorithms; examination of methods to combine results from various algorithms to improve recognition using AI techniques, such as graphical models.
Students need to be proficient at object oriented programming in either Java or C++. Students should have taken some higher level computer science courses. Possible courses include artificial intelligence, user interfaces, or software engineering.
Each topic will take 1-2 weeks. Each topic will include reading of related papers; students will write a summary and discussion of and/or comment on each paper on their blog. Programmatic assignments will accompany each topic. Students will develop a final project as part of the course. Students will have to write up results in journal formal and provide videos for certain homeworks and final project.
Homeworks: 60%
Project: 30%
Class Participation: 10%
Mini quizzes may be randomly given as part of homework and class participation
(testing that reading was done and ready to be discussed in class).
Students will be expected to do a term project. The possible topics vary widely. Possible topics include:
1) Building a sketch system for a new application using existing techniques
2) Creating a new sketch algorithm by merging techniques, or developing a new technique
Students will write a description of their project expressing why the techniques used were appropriate and why.
Students should also test their projects by having five other people testing their algorithm.