Abstract: Racing bib number localization in marathon natural images is challenging because in those images, there are many texts appearing in the scene that will produce many false positive texts. This research presents a method to detect racing bib numbers on complex backgrounds based on edge detection technique. The algorithm initially extracts candidate texts by applied vertical edge detection and morphological operations. Then, face detection technique is applied for the verification step. The experiments were tested on over 400 marathon images. It was reported satisfactory by the performance that was improved from the original work.
DOI: *As the DOI is a unique identifier, it is already available in the pdf version. **The DOI link will be activated in the first midst of January 2026.
WSEAS Transactions on Systems and Control, ISSN / E-ISSN: 1991-8763 / 2224-2856, Volume 13, 2018, Art. #27