Deep Learning Car Driver Motion Magnified Saccadic Eye Movements for Advanced Driving Assistance System

Rundo, Francesco; Messina, Angelo; Calabretta, Michele; Dilonardo, Matteo; Coffa, S.; Spampinato, Concetto

doi:10.1109/ijcnn55064.2022.9892353

Cited by 2 publications

(1 citation statement)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In biometrics, methods for segmenting the iris reflections could increase the iris segmentation accuracy [1]. In human-machine interaction, the iris region is frequently segmented to analyze the gaze of the user [2] for different applications, like driving assistance systems [3]. Photo editing applications could also introduce automatic methods to remove reflections from the iris region, with the aim of obtaining visually pleasing portrait pictures by using artificially generated textures [4].…”

Section: Introductionmentioning

confidence: 99%

Iris Reflection Segmentation from Ocular Images Acquired in Uncontrolled and Uncooperative Conditions

Labati,

Piuri,

Rundo

et al. 2023

2023 IEEE International Conference on Computational Intelligence and Virtual Environments for Measurement Systems and Applicati

Self Cite

View full text Add to dashboard Cite

The segmentation of reflections from the iris region is a relevant task for biometric systems, human-machine interaction technologies, and photo editing applications. This task is particularly complex for ocular images acquired from uncooperative users in uncontrolled illumination and environmental conditions. Furthermore, to the best of our knowledge, all of the studies in the literature on methods specifically designed to detect reflections in the iris texture are based on algorithmic approaches. In this paper, we present the first study on deep neural networks for segmenting reflection regions from iris images. Specifically, we propose a modified version of the U-Net architecture based on an encoder (downsampler) characterized by a relatively low computational complexity, and designed with the aim of being applied on edge devices. Experiments have been performed for a dataset of 3,286 ocular images acquired from websites and social media in completely uncontrolled and uncooperative conditions. The obtained results prove that our proposed method can accurately segment the iris reflections for particularly challenging images. A detailed qualitative analysis also confirm the robustness of our method for non-ideal application contexts. Furthermore, experiments show that our method can increase the accuracy of state-of-the-art iris segmentation techniques based on deep neural networks.

show abstract

Section: Introductionmentioning

confidence: 99%