Privacy-enhancing Sclera Segmentation Benchmarking Competition: SSBC 2025

TL;DR

The SSBC 2025 benchmark evaluates the effectiveness of privacy-preserving sclera segmentation models trained on synthetic data, demonstrating competitive performance and highlighting the potential of synthetic data in biometric applications.

Contribution

This paper introduces a benchmarking competition for sclera segmentation using synthetic data, showcasing diverse models and analyzing synthetic versus real data training strategies.

Findings

Synthetic data-trained models can achieve high segmentation accuracy.

Methodological choices impact performance more than real data inclusion.

Synthetic data offers a privacy-preserving alternative for biometric model training.

Abstract

This paper presents a summary of the 2025 Sclera Segmentation Benchmarking Competition (SSBC), which focused on the development of privacy-preserving sclera-segmentation models trained using synthetically generated ocular images. The goal of the competition was to evaluate how well models trained on synthetic data perform in comparison to those trained on real-world datasets. The competition featured two tracks: $(i)$ one relying solely on synthetic data for model development, and $(ii)$ one combining/mixing synthetic with (a limited amount of) real-world data. A total of nine research groups submitted diverse segmentation models, employing a variety of architectural designs, including transformer-based solutions, lightweight models, and segmentation networks guided by generative frameworks. Experiments were conducted across three evaluation datasets containing both synthetic and real-world images, collected under diverse conditions. Results show that models trained entirely on synthetic data can achieve competitive performance, particularly when dedicated training strategies are employed, as evidenced by the top performing models that achieved $F_1$ scores of over $0.8$ in the synthetic data track. Moreover, performance gains in the mixed track were often driven more by methodological choices rather than by the inclusion of real data, highlighting the promise of synthetic data for privacy-aware biometric development. The code and data for the competition is available at: https://github.com/dariant/SSBC_2025.