Sclera Segmentation and Joint Recognition Benchmarking Competition: SSRBC 2023

Abhijit Das, Saurabh Atreya, Aritra Mukherjee, Matej Vitek, Haiqing Li,Caiyong Wang, Guangzhe Zhao, Fadi Boutros, Patrick Siebke, Jan Niklas Kolf,Naser Damer, Sun Ye, Lu Hexin, Fan Aobo, You Sheng,Sabari Nathan, R. Suganya, R. S. Rampriya, Geetanjali Sharma, P. Priyanka, Aditya Nigam,Peter Peer, Umapada Pal,Vitomir Struc

2023 IEEE INTERNATIONAL JOINT CONFERENCE ON BIOMETRICS, IJCB(2023)

引用 0|浏览0
暂无评分
摘要
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.
更多
查看译文
关键词
Benchmark Competition,Biometric,Segmentation Model,Recognition Performance,Segmentation Results,Model Performance,Convolutional Neural Network,Convolutional Layers,Performance Metrics,Feature Maps,Intersection Over Union,Prediction Probability,Segmentation Task,Recognition Model,Gaze Direction,Recognition Results,Eye Color,Acquisition Conditions,Recognition Stage,Equal Error Rate,Intersection Over Union Score,Decoder Block,Ocular Imaging,Thresholding Procedure,Stochastic Gradient Descent,Light Conditions,Convolutional Block,Precision-recall Curve
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要