Tamanho da fonte:
ANALYSIS AND EVALUATION OF DIGITAL IMAGE ENHANCEMENT TECHNIQUES APPLIED TO FACIAL RECOGNITION WITH NEURAL NETWORKS.
Última alteração: 2022-06-22
Resumo
Machine Learning algorithms are used for automating detection such as Artificial Neural Networks.S\u00e3o utilizados softwares que filtram a imagem usando t\u00e9cnicas de Processamento de Imagem afim de definir padr\u00f5es e simplificar a busca, agilizando dessa forma, o processamento.Transforming the resulting image into a binary vector. This vector is used as input in a Neural Network to extract face patterns and perform facial detection.The proposal is promising with hits above 80% with the Gaussian filter and reaching 90% with the Histogram Equalization filter that allow the proposed methodology is used regardless of the filter applied to the image.This work proposes methodology for facial recognition. After performing the image treatment and using filters such as Gaussian and Histogram Equalization, algorithms are applied for transforming the resulting image into a binary vector.They are increasingly used in biometric authentication applications where facial image is used to identify people previously registered. In some cases, facial image can also locate suspects in a crowd or can even assist in the search for missing persons."
Texto completo:
PDF