Combined textural-Gabor Wavelet descriptors for Sign and Hand Gesture Recognition

Sign language, also known as the silent language, is a vital communication tool for the hearing-impaired society where the communication represents a significant challenge. In this paper, we propose a gesture recognition system implementation for both static and dynamic gesture (Jochen Triesch’s static dataset for American Sign Language ASL, and Sebastien Marce’s dynamic database) in a uniform background. The system is based on Gabor features, Histogram of Oriented Gradients (HOG), Center-Symmetric Local Binary Patterns (CSLBP), Local Directional ZigZag Pattern (LDZP) and Local Energy based Shape Histogram (LESH) where the recognition task is applied using the one against all Support Vector Machine (SVM) classification technique. Individual textural and combined Gabor-textural descriptors are also studied to show the efficiency of the oriented Gabor filters. The combined Gabor-HOG architecture achieved the best recognition rate where 98.33 percent was obtained for ASL.