Sclera Segmentation and Joint Recognition Benchmarking Competition: SSRBC 2023

Authors

Abhijit Das, Birla Institute of Technology and Science, Pilani
Saurabh Atreya, Birla Institute of Technology and Science, Pilani
Aritra Mukherjee, Birla Institute of Technology and Science, Pilani
Matej Vitek, Univerza v Ljubljani
Haiqing Li, Beijing University of Civil Engineering and Architecture
Caiyong Wang, Beijing University of Civil Engineering and Architecture
Guangzhe Zhao, Beijing University of Civil Engineering and Architecture
Fadi Boutros, Fraunhofer Institute for Computer Graphics Research IGD
Patrick Siebke, Fraunhofer Institute for Computer Graphics Research IGD
Jan Niklas Kolf, Fraunhofer Institute for Computer Graphics Research IGD
Naser Damer, Fraunhofer Institute for Computer Graphics Research IGD
Sun Ye, Jilin University
Lu Hexin, Jilin University
Fan Aobo, Jilin University
You Sheng, Jilin University
Sabari Nathan, Cougar Inc.
R. Suganya, Vellore Institute of Technology
R. S. Rampriya, Indian Institute of Technology Mandi
Geetanjali Sharma, Indian Institute of Technology Mandi
P. Priyanka, Indian Institute of Technology Mandi
Aditya Nigam, Indian Institute of Technology Mandi
Peter Peer, Univerza v Ljubljani
Umapada Pal, Indian Statistical Institute, Kolkata
Vitomir Struc, Univerza v Ljubljani

Document Type

Conference Article

Publication Title

2023 IEEE International Joint Conference on Biometrics, IJCB 2023

Abstract

This paper presents the summary of the Sclera Segmentation and Joint Recognition Benchmarking Competition (SSRBC 2023) held in conjunction with IEEE International Joint Conference on Biometrics (IJCB 2023). Different from the previous editions of the competition, SSRBC 2023 not only explored the performance of the latest and most advanced sclera segmentation models, but also studied the impact of segmentation quality on recognition performance. Five groups took part in SSRBC 2023 and submitted a total of six segmentation models and one recognition technique for scoring. The submitted solutions included a wide variety of conceptually diverse deep-learning models and were rigorously tested on three publicly available datasets, i.e., MASD, SBVPI and MOBIUS. Most of the segmentation models achieved encouraging segmentation and recognition performance. Most importantly, we observed that better segmentation results always translate into better verification performance.

DOI

10.1109/IJCB57857.2023.10448601

Publication Date

1-1-2023

Recommended Citation

Das, Abhijit; Atreya, Saurabh; Mukherjee, Aritra; Vitek, Matej; Li, Haiqing; Wang, Caiyong; Zhao, Guangzhe; Boutros, Fadi; Siebke, Patrick; Kolf, Jan Niklas; Damer, Naser; Ye, Sun; Hexin, Lu; Aobo, Fan; Sheng, You; Nathan, Sabari; Suganya, R.; Rampriya, R. S.; Sharma, Geetanjali; Priyanka, P.; Nigam, Aditya; Peer, Peter; Pal, Umapada; and Struc, Vitomir, "Sclera Segmentation and Joint Recognition Benchmarking Competition: SSRBC 2023" (2023). Conference Articles. 521.
https://digitalcommons.isical.ac.in/conf-articles/521