Entrenamiento de una red neuronal para el reconocimiento de imagenes de lengua de senas capturadas con sensores de profundidad

TL;DR

This paper presents a neural network-based system utilizing autoencoders for classifying images of sign language captured with depth sensors, achieving high accuracy to aid communication for the deaf.

Contribution

It introduces a novel neural network approach with autoencoders specifically designed for sign language image recognition using depth sensor data.

Findings

99.5% classification accuracy

Error rate of 0.01684

Effective for aiding deaf communication

Abstract

Due to the growth of the population with hearing problems, devices have been developed that facilitate the inclusion of deaf people in society, using technology as a communication tool, such as vision systems. Then, a solution to this problem is presented using neural networks and autoencoders for the classification of American Sign Language images. As a result, 99.5% accuracy and an error of 0.01684 were obtained for image classification