TY - JOUR
T1 - Point-SPV
T2 - end-to-end enhancement of object recognition in simulated prosthetic vision using synthetic viewing points
AU - Nejad, Ashkan
AU - Küçükoǧlu, Burcu
AU - de Ruyter van Steveninck, Jaap
AU - Bedrossian, Sandra
AU - Heutink, Joost
AU - de Haan, Gera A.
AU - Cornelissen, Frans W.
AU - van Gerven, Marcel
PY - 2025/3/24
Y1 - 2025/3/24
N2 - Prosthetic vision systems aim to restore functional sight for visually impaired individuals by replicating visual perception by inducing phosphenes through electrical stimulation in the visual cortex, yet there remain challenges in visual representation strategies such as including gaze information and task-dependent optimization. In this paper, we introduce Point-SPV, an end-to-end deep learning model designed to enhance object recognition in simulated prosthetic vision. Point-SPV takes an initial step toward gaze-based optimization by simulating viewing points, representing potential gaze locations, and training the model on patches surrounding these points. Our approach prioritizes task-oriented representation, aligning visual outputs with object recognition needs. A behavioral gaze-contingent object discrimination experiment demonstrated that Point-SPV outperformed a conventional edge detection method, by facilitating observers to gain a higher recognition accuracy, faster reaction times, and a more efficient visual exploration. Our work highlights how task-specific optimization may enhance representations in prosthetic vision, offering a foundation for future exploration and application.
AB - Prosthetic vision systems aim to restore functional sight for visually impaired individuals by replicating visual perception by inducing phosphenes through electrical stimulation in the visual cortex, yet there remain challenges in visual representation strategies such as including gaze information and task-dependent optimization. In this paper, we introduce Point-SPV, an end-to-end deep learning model designed to enhance object recognition in simulated prosthetic vision. Point-SPV takes an initial step toward gaze-based optimization by simulating viewing points, representing potential gaze locations, and training the model on patches surrounding these points. Our approach prioritizes task-oriented representation, aligning visual outputs with object recognition needs. A behavioral gaze-contingent object discrimination experiment demonstrated that Point-SPV outperformed a conventional edge detection method, by facilitating observers to gain a higher recognition accuracy, faster reaction times, and a more efficient visual exploration. Our work highlights how task-specific optimization may enhance representations in prosthetic vision, offering a foundation for future exploration and application.
KW - simulated prosthetic vision
KW - synthetic viewing points
KW - object recognition
KW - end-to-end training
KW - deep learning
U2 - 10.3389/fnhum.2025.1549698
DO - 10.3389/fnhum.2025.1549698
M3 - Article
SN - 1662-5161
VL - 19
JO - Frontiers in Human Neuroscience
JF - Frontiers in Human Neuroscience
M1 - 1549698
ER -