000095939 001__ 95939 000095939 005__ 20210902121616.0 000095939 0247_ $$2doi$$a10.1371/journal.pone.0227677 000095939 0248_ $$2sideral$$a116541 000095939 037__ $$aART-2020-116541 000095939 041__ $$aeng 000095939 100__ $$0(orcid)0000-0002-5656-1582$$aSanchez-Garcia, M.$$uUniversidad de Zaragoza 000095939 245__ $$aSemantic and structural image segmentation for prosthetic vision 000095939 260__ $$c2020 000095939 5060_ $$aAccess copy available to the general public$$fUnrestricted 000095939 5203_ $$aProsthetic vision is being applied to partially recover the retinal stimulation of visually impaired people. However, the phosphenic images produced by the implants have very limited information bandwidth due to the poor resolution and lack of color or contrast. The ability of object recognition and scene understanding in real environments is severely restricted for prosthetic users. Computer vision can play a key role to overcome the limitations and to optimize the visual information in the prosthetic vision, improving the amount of information that is presented. We present a new approach to build a schematic representation of indoor environments for simulated 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. The results show good accuracy for object recognition and room identification tasks for indoor scenes using the proposed approach, compared to other image processing methods. 000095939 536__ $$9info:eu-repo/grantAgreement/ES/MINECO/BES-2016-078426$$9info:eu-repo/grantAgreement/ES/MINECO-FEDER/DPI2015-65962-R$$9info:eu-repo/grantAgreement/ES/MINECO-FEDER/RTI2018-096903-B-I00 000095939 540__ $$9info:eu-repo/semantics/openAccess$$aby$$uhttp://creativecommons.org/licenses/by/3.0/es/ 000095939 590__ $$a3.24$$b2020 000095939 591__ $$aMULTIDISCIPLINARY SCIENCES$$b26 / 73 = 0.356$$c2020$$dQ2$$eT2 000095939 592__ $$a0.99$$b2020 000095939 593__ $$aMultidisciplinary$$c2020$$dQ1 000095939 655_4 $$ainfo:eu-repo/semantics/article$$vinfo:eu-repo/semantics/publishedVersion 000095939 700__ $$0(orcid)0000-0002-6741-844X$$aMartinez-Cantin, R.$$uUniversidad de Zaragoza 000095939 700__ $$0(orcid)0000-0001-5209-2267$$aGuerrero, J. J.$$uUniversidad de Zaragoza 000095939 7102_ $$15007$$2520$$aUniversidad de Zaragoza$$bDpto. Informát.Ingenie.Sistms.$$cÁrea Ingen.Sistemas y Automát. 000095939 773__ $$g15, 1 (2020), e0227677 [22 pp]$$pPLoS One$$tPloS one$$x1932-6203 000095939 8564_ $$s809486$$uhttps://zaguan.unizar.es/record/95939/files/texto_completo.pdf$$yVersión publicada 000095939 8564_ $$s469085$$uhttps://zaguan.unizar.es/record/95939/files/texto_completo.jpg?subformat=icon$$xicon$$yVersión publicada 000095939 909CO $$ooai:zaguan.unizar.es:95939$$particulos$$pdriver 000095939 951__ $$a2021-09-02-08:44:16 000095939 980__ $$aARTICLE