Premium
Recognition of Objects in Simulated Irregular Phosphene Maps for an Epiretinal Prosthesis
Author(s) -
Lu Yanyu,
Wang Jing,
Wu Hao,
Li Liming,
Cao Xun,
Chai Xinyu
Publication year - 2014
Publication title -
artificial organs
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.684
H-Index - 76
eISSN - 1525-1594
pISSN - 0160-564X
DOI - 10.1111/aor.12174
Subject(s) - phosphene , artificial intelligence , computer vision , dropout (neural networks) , cognitive neuroscience of visual object recognition , computer science , distortion (music) , pixel , pattern recognition (psychology) , object (grammar) , psychology , machine learning , amplifier , computer network , bandwidth (computing) , neuroscience , stimulation , transcranial magnetic stimulation
Visual prostheses offer a possibility of restoring vision to the blind. It is necessary to determine minimum requirements for daily visual tasks. To investigate the recognition of common objects in daily life based on the simulated irregular phosphene maps, the effect of four parameters (resolution, distortion, dropout percentage, and gray scale) on object recognition was investigated. The results showed that object recognition accuracy significantly increased with an increase of resolution. Distortion and dropout percentage had significant impact on the object recognition; with the increase of distortion level and dropout percentage, the recognition decreased considerably. The accuracy decreased significantly only at gray level 2, whereas the other three gray levels showed no obvious difference. The two image processing methods (merging pixels to lower the resolution and edge extraction before lowering resolution) showed significant difference on the object recognition when there was a high degree of distortion level or dot dropout.