Recognition of sport players' numbers using fast color segmentation

Verleysen, Cédric;De Vleeschouwer, Christophe
(2012) IS&T / SPIE | Electronic Imaging 2012 — Location: Burlingame, California, USA (22.January.2012)

Files

SPIE2012-Recognition_of_sport_players_numbers_using_fast_color_segmentation.pdf
  • Open Access
  • Adobe PDF
  • 686.83 KB
Download
SPIE2012-Recognition_of_sport_players_numbers_using_fast_color_segmentation.pdf
  • Open Access
  • Adobe PDF
  • 686.83 KB
Download
SPIE2012-Recognition_of_sport_players_numbers_using_fast_color_segmentation.pdf
  • Open Access
  • Adobe PDF
  • 686.83 KB
Download

Details

Authors
Abstract
This paper builds on a prior work for player detection, and proposes an efficient and effective method to distinguish among players based on the numbers printed on their jerseys. To extract the numbers, the dominant colors of the jersey are learnt during an initial training phase and used to speed up the segmentation of the candidate digit regions. An additional set of criteria considering the relative position and size (compared to the player bounding box) and the density (compared to the digit rectangular support) of the digit are used to filter out the regions that obviously do not correspond to a digit. Once the plausible digit regions have been extracted, their recognition is based on feature-based classification. A number of original features are proposed to increase the robustness against digit appearance changes, resulting from the font thickness variability and from the deformations of the jersey during the game. Finally, the efficiency and the effectiveness of the proposed method are demonstrated on a real-life basketball dataset. More than 50% of the jersey samples that can be visually recognized are detected as numbers with 93% of correct classification.
Affiliations

Citations

  • APA
  • Chicago
  • FWB

Verleysen, C., & De Vleeschouwer, C. (2012). Recognition of sport players’ numbers using fast color segmentation. Proceedings of IS&T / SPIE | Electronic Imaging 2012, Burlingame, California, USA. Published. IS&T / SPIE | Electronic Imaging 2012, Burlingame, California, USA. https://doi.org/10.1117/12.908723