City University of Hong Kong, Department of Computer Science

CS 5187 -- Vision and Image

Class Project Guidelines

General Objectives:

The project is intended to provide the students with an opportunity to take the initiative and develop independent research capability and creativity.  In the project, students are expected to identify problems of their own interest, tackle the problems from their own perspective, gain hand-on experience, and hopefully, have the fun of making their own discoveries.   The project will obviously require a good deal of time and energy, imagination and hard work.

Project Format:

The class project will be done individually (that is, teaming with other students is not allowed), requiring about 15 hours over the entire semester.  A project includes the following phases: choosing a project topic, conducting the project, and writing a final project report.

A project usually consists of reading papers on a chosen topic, comparing performances of different approaches, and perhaps proposing your own algorithms/improvements, implementing one or two of them.     

• The length of a report must be between 3 pages and 10 pages.
• Reports must follow the official IEEE publication format. Use the Word or Latex templates provided by IEEE.

  Specifically, you can find

  • Word template
    Click here.

• Reports must include the following parts:
  • Project title and your name
  • Abstract - A paragraph that summarizes the problem and the results.
  • Introduction - Sets the context, describes the problem, and describes your solution.
  • Description - One or more sections that describes the problem and your approach to the solution in detail.
  • Evaluation - A section that quantitatively evaluates your ideas.
  • Related work - Describes representative works related to your work, and summarizes the pros and cons of each work.
  • Summary and Conclusions - Summarize what you did and what interesting things you learned from the project.
  • Reference list
• In addition, you need to prepare a Powerpoint file, which must include the following parts (there is no page limit for the Powerpoint file):
  • The problem under study
  • Existing approaches
  • (Optional) Proposed new approach if there is any
  • Performance evaluation of existing approaches and (if any) the proposed new approach
  • Conclusion

• You need to submit the following items to Canvas under the directory of "Project Report".
  • A written report for your project in pdf or WORD format. You should not put your project report file in a zip/rar file; otherwise, you will not receive TurnItin similarity score. You need to upload your project report file separately from other files so that you can receive a TurnItin similarity score.
  • A file of your presentation slides in ppt or pptx with your speech recorded in the ppt/pptx.
• Please do not submit your project report to Turnitin web site (turnitin.com) for similarity score of your project report.

  When you upload your project report to Canvas, Canvas will automatically obtain a similarity score for your project report from Turnitin. You will see the similarity score on Canvas within 24 hours after you upload your project report. If you upload the same report to two different courses on Canvas, the similarity score of your report will be 100%.  Using the same project report for two different courses is not acceptable.

  You are allowed to upload your files to Canvas with an unlimited number of times before the submission deadline.

Hints for Coming Up with a Topic

Please feel free to propose any idea you want for your project.

There are two basic approaches you can use for your project.

• Develop a new idea or a new twist on an existing idea, and then do enough evaluation to serve as a proof of concept.
• Do an extensive evaluation of an existing idea that gives you some insight into the advantages or disadvantages of that idea.

Here are some suggested project topics.

Criteria Used for Grading Your Project Report

1. Quality. The value of a paper is a function of the innate character or degree of excellence of the work described. Was the work performed, or the study made with a high degree of thoroughness? Was high engineering skill demonstrated? Is an experiment described which has a high degree of elegance? Or, on the other hand, is the work described pretty much of a run-of-the-mill nature? 
2. Presentation. The value of the paper is a function of the ease with which the reader can determine what the author is trying to present. Regardless of the other criteria, a paper is not good unless the material is presented clearly and effectively. Is the paper well written? Is the meaning of the author clear? Are the tables, charts and figures clear? Is their meaning readily apparent? Is the information presented in the paper complete? At the same time, is the paper concise?
3. (Bonus) Originality. The value of a paper is a function of the degree to which it presents new or novel technical material. Does the paper present results previously unknown? Does it push forward the frontiers of knowledge? Does it present new methods for solving old problems or new viewpoints on old problems? Or, on the other hand, is it a re-hash of information already known?
4. (Bonus) Contribution. The value of a paper is a function of the degree to which it represents an overall contribution to the advancement of the art. This is different from originality. A paper may be highly original, but may be concerned with a very minor, or even insignificant, matter or problem. On the other hand, a paper may make a great contribution by collecting and analyzing known data and facts and pointing out their significance. Or, a fine exposition of a known, but obscure or complex, phenomenon or theory or system or operating technique may be a very real contribution to the art. Obviously, a paper may well score highly on both originality and contribution. Perhaps a significant question is, will the engineer who reads the paper be able to practice his profession more effectively because of having read it?