Sign Language Detection from Hand Gesture Images using Deep Multi-layered Convolution Neural Network

Automatic detection of sign language from hand gesture images is crucial nowadays. Accurate detection and classification of sign language can help people with hearing and speech disorder. In this paper, a deep multi-layered convolution neural network is proposed for this purpose. In the proposed approach, 32 convolution filters with 3 x3 kernel, LeakyReLU activation function and 2 x2 max pooling operation have been performed in the deep multi-layered CNN structure. SoftMax activation function has been used in the output layer. The proposed approach has been evaluated on a database containing both static (54000 images and 36 classes) and dynamic (49613 images and 23 classes) hand gesture images. Experimental results demonstrate the efficacy of the proposed methodology in sign language detection task.