A fully automatic method for recognizing hand configurations of Brazilian sign language

• Autor(a) principal: Costa Filho,Cicero Ferreira Fernandes
• Data de Publicação: 2017
• Outros Autores: Souza,Robson Silva de, Santos,Jonilson Roque dos, Santos,Bárbara Lobato dos, Costa,Marly Guimarães Fernandes
• Tipo de documento: Artigo
• Idioma: eng
• Título da fonte: Research on Biomedical Engineering (Online)
• Texto Completo: http://old.scielo.br/scielo.php?script=sci_arttext&pid=S2446-47402017000100078
• topic: Deaf community; Sign language; Gesture recognition; Novelty classifier; kNN classifier; Libras

Abstract Introduction Sign language is a collection of gestures, postures, movements, and facial expressions used by deaf people. The Brazilian sign language is Libras. The use of Libras has been increased among the deaf communities, but is still not disseminated outside this community. Sign language recognition is a field of research, which intends to help the deaf community communication with non-hearing-impaired people. In this context, this paper describes a new method for recognizing hand configurations of Libras - using depth maps obtained with a Kinect® sensor. Methods The proposed method comprises three phases: hand segmentation, feature extraction, and classification. The segmentation phase is independent from the background and depends only on pixel value. The feature extraction process is independent from rotation and translation. The features are extracted employing two techniques: (2D)2LDA and (2D)2PCA. The classification employs two classifiers: a novelty classifier and a KNN classifier. A robust database is constructed for classifier evaluation, with 12,200 images of Libras and 200 gestures of each hand configuration. Results The best accuracy obtained was 96.31%. Conclusion The best gesture recognition accuracy obtained is much higher than the studies previously published. It must be emphasized that this recognition rate is obtained for different conditions of hand rotation and proximity of the depth camera, and with a depth camera resolution of only 640×480 pixels. This performance must be also credited to the feature extraction technique, and to the size standardization and normalization processes used previously to feature extraction step.