Semantic and Structural Image Segmentation for Prosthetic Vision

Melani Sanchez Garcia, Rubén Martínez Cantín, José J. Guerrero
2019 Jornada de Jóvenes Investigadores del I3A  
We present a new approach to build a schematic representation of indoor environments for phosphene images. The proposed method combines a variety of convolutional neural networks for extracting and conveying relevant information about the scene such as structural informative edges of the environment and silhouettes of segmented objects. Experiments were conducted with normal sighted subjects with a Simulated Prosthetic Vision system.
doi:10.26754/jji-i3a.003511 fatcat:4gpbxo5y7zajrjsxxzjw4wpbda