Sketch Recognition, Fall 2006 (689-610)

MWF 12:40-1:30, 104 Bright

Homework

Instructor

Tracy Hammond
Email: hammond at cs.tamu.edu
Office: HRBB 414C
Phone: 979 862 4284

Class Office Hours

Office hours will change from week to week depending on the type of assignment. (I will try to arrange office hours in the lab for lab assignments.)
Daily 3-3:30
Office hours can also be made by appointment.


Description

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.


Prerequisites

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.


Grading

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).


Topics

(order may change depending on availability of tablets)
1: Introduction
2: Feature based recognition (Rubine)
3: Gathering Data: Students will gather data on which to test the algorithms to be studied later in the semester.
4: Recognizing primitives (breaking down strokes into lines, arcs, and ellipses)
5: Geometric algorithms
6: Vision based algorithms
7: Combining classifiers with Adaboost
8: Combining classifiers using other techniques from machine learning
9: User Interface Issues

Each topic will take 1-2 weeks. Each topic involves the student reading 2-3 papers, and class discussion of the benefits and drawbacks of each method. For each topic, the students will implement a recognition algorithm of that type, which will then be tested on the gathered drawings. At the end of course, students will have a final project where they develop a new recognizer, which either combines methods studied in class, or uses a new method.


Project
Proposal Due Date: September 22nd
Related Work Presentation: October TBD
Project Due Date: November 29th

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. (If the tablet pc's don't come in, we will make alternate solutions.)


Americans with Disabilities Act (ADA) Policy Statement

The following ADA Policy Statement (part of the Policy on Individual Disabling Conditions) was submitted to the University Curriculum Committee by the Department of Student Life. The policy statement was forwarded to the Faculty Senate for information.

The Americans with Disabilities Act (ADA) is a federal anti-discrimination statute that provides comprehensive civil rights protection for persons with disabilities. Among other things, the legislation requires that all students with disabilities be guaranteed a learning environment that provides for reasonable accommodation of their disabilities. If you believe you have a disability requiring an accommodation, please contact the Department of Student Life, Services for Students with Disabilities, in Cain Hall or call 845-1637.


Copyrights

The handouts used in this course are copyrighted. By “Handouts” we mean all materials generated for this class, which include but are not limited to syllabi, lab problems, in-class materials, review sheets, and additional problem sets. Because these materials are copyrighted, you do not have the right to copy such handouts, unless the author expressly grants permission.


Scholastic Dishonesty

As commonly defined, plagiarism consists of passing off as one’s own the ideas, work, writings, etc., that belong to another. In accordance with this definition, you are committing plagiarism if you copy the work of another person and turn it in as your own, even if you have the permission of the person. Plagiarism is one of the worst academic sins, for the plagiarist destroys the trust among colleagues without which research cannot be safely communicated. If you have questions regarding plagiarism, please consult the latest issue of the Texas A&M University Student Rules [http://student-rules.tamu.edu], under the section “Scholastic Dishonesty”.


Academic Integrity Statement

"An Aggie does not lie, cheat, or steal or tolerate those who do."

Upon accepting admission to Texas A&M University, a student immediately assumes a commitment to uphold the Honor Code, to accept responsibility for learning and to follow the philosophy and rules of the Honor System. Students will be required to state their commitment on examinations, research papers, and other academic work. Ignorance of the rules does not exclude any member of the Texas A&M University community from the requirements or the processes of the Honor System. For additional information please visit: http://www.tamu.edu/aggiehonor

University Regulations, Section 42, define scholastic dishonesty to include acquiring answers from any unauthorized source, working with another person when not specifically permitted, observing the work of other students during any exam, providing answers when not specifically authorized to do so, informing any person of the contents of an exam prior to the exam, and failing to credit sources used. Disciplinary actions range from grade penalty to expulsion.

This course has a zero-tolerance policy. Academic misconduct on any assignment will result in failing the entire course! All such cases will be referred to the Aggie Honor Council for additional disciplinary action by the University. Finally, misconduct will also result in an "Unsatisfactory" rating on the annual departmental review of Ph.D. students. Please refer to http://www.tamu.edu/aggiehonor/acadmisconduct.htm for more information about the scope and meaning of academic misconduct.

On all course work, assignments, and examinations at Texas A&M University, the following Honor Pledge shall be preprinted and signed by the student: "On my honor, as an Aggie, I have neither given nor received unauthorized aid on this academic work."