Skip to Main Content
 

Global Search Box

 
 
 
 

Files

File List


osu1306867373.pdf (3.37 MB)

ETD Abstract Container

Abstract Header

Real Time Badge Detection and Recognition for Bicycle Racing

Pandya, Jatan K.
http://rave.ohiolink.edu/etdc/view?acc_num=osu1306867373

Abstract Details

2011, Master of Science, Ohio State University, Electrical and Computer Engineering.
In this approach, we present a new method for region extraction, which is based on a specially designed geometric pattern. By establishing simple statistical relationships between the fundamental geometric blocks of the pattern, we can determine its correct coordinates. The object under consideration is a bicyclist badge. The badge extraction is followed by its affine correction, normalization, segmentation and character recognition. For about 80 sample images, we are able to achieve 93.75% detection rate. The false positives are nearly nil, even in the most complex backgrounds. The badge is scale and rotation invariant; and supports a limited rotation of 45 degrees with the current approach.
Yuan Zheng, PhD (Advisor)
Joanne Degroat, PhD (Committee Member)
54 p.
Electrical Engineering

Recommended Citations

Citations

  • Pandya, J. K. (2011). Real Time Badge Detection and Recognition for Bicycle Racing [Master's thesis, Ohio State University]. OhioLINK Electronic Theses and Dissertations Center. http://rave.ohiolink.edu/etdc/view?acc_num=osu1306867373

    APA Style (7th edition)

  • Pandya, Jatan. Real Time Badge Detection and Recognition for Bicycle Racing. 2011. Ohio State University, Master's thesis. OhioLINK Electronic Theses and Dissertations Center, http://rave.ohiolink.edu/etdc/view?acc_num=osu1306867373.

    MLA Style (8th edition)

  • Pandya, Jatan. "Real Time Badge Detection and Recognition for Bicycle Racing." Master's thesis, Ohio State University, 2011. http://rave.ohiolink.edu/etdc/view?acc_num=osu1306867373

    Chicago Manual of Style (17th edition)

osu1306867373
657
© 2011, all rights reserved.
This open access ETD is published by The Ohio State University and OhioLINK.