This paper proposes a new approach in object recognition to assist visually impaired people. This approach achieved accuracy rates higher than the approaches proposed by the authors of the selected datasets. We applied Data Augmentation with other techniques and adjustments to different Pre-trained CNNs (Convolutional Neural Networks). The ResNet-50 based approach achieved the best results in the most recent datasets. This work focused on products that are usually found on grocery store shelves, supermarkets, refrigerators or pantries.
Este trabalho propõem uma abordagem para auxiliar pessoas com deficiência visual no reconhecimento de pessoas independente da idade. O objetivo é desenvolver um sistema que utilize uma abordagem de reconhecimento facial, com foco na invariância na idade, que retorne bons resultados comparados aos resultados obtidos na revisão da literatura. A abordagem estudada utiliza Redes Neurais Convolucionais profundas CCNs, pré-treinadas pelo conjunto de dados VGGFace2, para extrair descritores de características de imagens de faces e classificar com o algoritmo de classificação Linear SVM. Como pode ser visto no decorrer do trabalho, a abordagem retornou 89,9% de acurácia, utilizando o conjunto de dados FG-NET, com 1002 imagens. E utilizando o conjunto de dados CACD, que contém 163.446 imagens divididas em quatro subconjuntos diferentes, três conjuntos para treino e um para teste, a abordagem retornou 85,2%, 82,4% e 88,2% de acurácia para cada modelo treinado com um conjunto de treinamento diferente.
Facial expression recognition systems can help a visually impaired person to identify the emotions of the person with whom she interacts, assisting in her non-verbal communication. Among the various researches carried out in recent years on recognition of facial expressions, the best results obtained come from methods that use deep learning, mainly with the use of convolutional neural networks. This work presents a literature review on the problem of recognition of facial expressions, through the use of convolutional neural networks and proposes two approaches in which the first one uses pre-trained CNN models together with the Linear SVM classifier that, applied to the bases CK+ and JAFFE data, obtained maximum accuracy of 89.6% and 95.7%, respectively. And in the second approach, a CNN model built from scratch is used with the CK+ and FER2013 databases, which obtained accuracy rates of 85% and 65.8%, respectively.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.