Take a look at the new version of this page: [ beta version ]. Tell us what you think.

ABSTRACT

In a small computer science department without a graduate program, it is sometimes difficult to attract research students. This is particularly true for research in computer vision, since it is built upon a substantial body of knowledge, including considerable mathematics, that most undergraduates are not familiar with. My approach to encouraging students to take part in this research starts by introducing computation with images in early programming classes. Students become comfortable working with images in a structured framework, where they are not exposed to excessive underlying details. The students that become interested in working with images can take my computer vision class. This course is taught in a way that students can understand the material without having a deep background in mathematics. Students that are successful in this class are ready for (and encouraged to) work on undergraduate research projects and perform internships in computer vision research. While my strategy focuses on computer vision, similar approaches could be used for other research areas.

REFERENCES

• 1: G. Bebis, D. Egbert, and M. Shah. Review of computer vision education. IEEE Transactions on Education, 46(1):2--21, February 2003.
• 2: Harriet J. Fell , Viera K. Proulx, Exploring Martian planetary images: C++ exercises for CS1, Proceedings of the twenty-eighth SIGCSE technical symposium on Computer science education, p.30-34, February 27-March 01, 1997, San Jose, California, United States
• 3: E. Finak and M. Heath. Image-processing projects for an algorithms course. International Journal of Pattern Recognition and Artificial Intelligence, 15(5):859--868, August 2001.
• 4: David A. Forsyth , Jean Ponce, Computer Vision: A Modern Approach, Prentice Hall Professional Technical Reference, 2002
• 5: Goefrey Holmes , Tony C. Smith, Adding some spice to CS1 curricula, Proceedings of the twenty-eighth SIGCSE technical symposium on Computer science education, p.204-208, February 27-March 01, 1997, San Jose, California, United States
• 6: Ricardo Jiménez-Peris , Sami Khuri , Marta Patiño-Martínez, Adding breadth to CS1 and CS2 courses through visual and interactive programming projects, The proceedings of the thirtieth SIGCSE technical symposium on Computer science education, p.252-256, March 24-28, 1999, New Orleans, Louisiana, United States
• 7: B. A. Maxwell. Teaching computer vision to computer scientists: Issues and a comparative textbook review. International Journal of Pattern Recognition and Artificial Intelligence, 12(8):1035--1051, August 1998.
• 8: R. E. Montgomery. Image analysis: A group assignment in programming with breadth. In Proceedings of the ASEE/IEEE Frontiers in Education Conference, volume 2, pages 4d3.12--4d3.14, 1995.
• 9: C. F. Olson, H. Abi-Rached, M. Ye, and J. P. Hendrich. Wide-baseline stereo vision for Mars rovers. In Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems, pages 1302--1307, October 2003.
• 10: S. Sarkar and D. Goldgof. Integrating image computation in undergraduate level data-structure education. International Journal of Pattern Recognition and Artificial Intelligence, 12(8):1071--1080, 1998.
• 11: George Stockman , Linda G. Shapiro, Computer Vision, Prentice Hall PTR, Upper Saddle River, NJ, 2001
• 12: D. E. Stevenson. Image related applications for a core algorithms course. International Journal of Pattern Recognition and Artificial Intelligence, 15(5):845--857, August 2001.
• 13: Emanuele Trucco , Alessandro Verri, Introductory Techniques for 3-D Computer Vision, Prentice Hall PTR, Upper Saddle River, NJ, 1998

INDEX TERMS

Primary Classification:
  K. Computing Milieux
  K.3 COMPUTERS AND EDUCATION
      K.3.0 General

General Terms:
Algorithms, Human Factors

Keywords:
computer vision, pedagogy, research