For your final project in CSC 370, you will implement a vision-processing algorithm from the scientific literature, test it, and prepare a class presentation on the results. Students may work on related projects with prior permission from the instructor. The project topic should be chosen carefully in consultation with the professor, since many papers are too complex to implement in the time allotted. The difficulty of the attempted project will be taken into account during grading.
Timeline
To help you to budget your time and maintain continuous progress towards project completion, a number of milestones have been built into the timeline. Students are expected to complete each piece according to the schedule below.
| Date | Item |
|---|---|
| 14 October | Choice of topic (a one paragraph statement indicating the nature of the implementation project, with citation of original paper) |
| 28 October | Precise specification (one to two pages; indicate inputs and outputs to algorithm, general structure of code, and tests planned with sample inputs) |
| November | Progress meetings (individual meetings with professor to discuss progress on projects -- significant work on implementation should be completed by this time) |
| December | Oral presentations (presentation of work to the class -- implementation and testing should be complete, although written report may not be finished yet) |
| 14 December | Written report (code in electronic form plus written hardcopy report/reflections on tests run and project as whole) |
Further Details
Please bear in mind that this project is not just about programming, although that forms a significant part of it. Without proper testing and analysis of the algorithms chosen, the implementation is worthless. Thus the written report, while referring to the code at times, should focus on the analysis of the results.
Final projects should be implemented in a manner compatible with the Matlab programming environment. This may mean implementing them in actual Matlab code. However, for those who prefer C/C++ or Java, some projects may be implemented in those languages using Matlab's external language interfaces. (More details are available for those interested.) Also, some projects might use pre-existing code; the goal would be to interface the code with Matlab and perform extensive testing. Existing code that is incorporated into your project must be appropriately cited in the report.
Topics
Final project topics may cover any aspect of computer vision, and should be chosen with consideration for the ease of implementation. Below are some possible topics for your consideration:
- Camera Calibration
- Face Detection
- Shape Comparison
- Texture Comparison
- Handwriting Identification
- Stereo Matching
- Object Classification
- Level Sets/Active Contours
- Segmentation
- Tracking
Instead of starting with a specific area in mind, you may pick an interesting recent paper to work with. The links below lead to lists of papers from recent computer vision conferences. The papers selected for oral presentation are often particularly strong work and should be considered first. If you need help selecting a paper in a particular area, please speak with the professor. (Note that some papers will not make suitable projects because implementing them would be too difficult.)