Recognition of Static Gestures Applied to Brazilian Sign Language (Libras)

This paper aims at describing an approach developed for the recognition of gestures on digital images. In this way, two shape descriptors were used: the histogram of oriented gradients (HOG) and Zernike invariant moments (ZIM). A feature vector composed by the information acquired with both descriptors was used to train and test a two stage Neural Network, which is responsible for performing the recognition. In order to evaluate the approach in a practical context, a dataset containing 9600 images representing 40 different gestures (signs) from Brazilian Sign Language (Libras) was composed. This approach showed high recognition rates (hit rates), reaching a final average of 96.77%.