Accessible communication is essential for the inclusion of deaf people in scientific and cultural society. The language barrier that deaf people face when trying to access written Spanish can limit their self-efficacy and their ability to participate fully in society. However, Optical Character Recognition (OCR) technology and Artificial Intelligence offer an innovative solution: the application of a Spanish signifier translator to Colombian Sign Language (CSL). This tool allows deaf people to understand their environment in Spanish in an autonomous way, which promotes inclusion and active participation in the scientific and cultural society. The application of OCR technology in the detection, reading, and conversion of Colombian Sign Language is essential to provide better living conditions for people with hearing disabilities and to bring together two cultures that have traditionally been distanced by the language barrier. This article describes the stages of development of the mobile application, the technology used, and the role of the sign language translator in promoting accessible communication and the participation of deaf people in a scientific and cultural society.

This work is part of the PG2402ECBTI2022 project approved by the Universidad Nacional Abierta y a Distancia. Its objective is to develop a spatial perception system with artificial intelligence (AI) techniques to improve the orientation and mobility of visually impaired people in Ibagué. The proposed system consists of several modules, and this text focuses on the results of the image processing module oriented to the segmentation of pedestrian lanes through the use of semantic neural networks. The network proposed for this task is based on a Deeplab architecture and was trained on a dataset composed of 5443 images. The results show that the architecture obtained an accuracy level of 0.95 and that its capacity to generalize new samples is in accordance with the task required for the system in general.