Lightweight Image Pre-processing Model for Improving Segmentation of Infrared Human Eye Images

P. 271–277.

Aleksei Samarin, Aleksei Toropov, Kotenko E., Nazarenko A., Elena Mikhailova, Valentin Malykh, Alexander Savelev, Motyko A.

This study focuses on improving iris and pupil segmentation in infrared images, a crucial task for gaze-tracking systems. We propose a lightweight image preprocessing approach, which ensures controlled data transformation, effectively eliminating parasitic reflections, noise, and contrast inconsistencies without introducing unwanted artifacts. Our approach employs analytically defined transformations, incorporating local and global filtering techniques to enhance the quality of input images while preserving physiologically relevant features. We compared deep learning-based segmentation models with and without preprocessing, demonstrating that the proposed approach significantly improves performance. Experimental results show notable gains in the mIoU metric, confirming increased robustness to illumination and image quality variations.

Keywords: reflection, testing, robustness, filtering, image segmentation, pupils, Lighting, image preprocessing, noise, iris

In book

Proceedings of the 37th Conference of Open Innovations Association FRUCT, Helsinki, Finland, 14-16 May 2025, Issue 1 (Full Papers)

Vol. 37. , Helsinki: FRUCT Oy, 2025.