Sign language recognition based on concept learning

This paper presents a concept-based learning framework for sign language recognition. The recognition is based on the concept learning framework which transforms learning about high-level concepts into learning for low-level concepts, the structure of which is simpler and can be learned with fewer samples. The sign language samples were first segmented by a modified Time Varying Parameter (TVP) algorithm which segments the motion time series according to pause points, and the segments are used to build a primitive library with a self-organizing feature map (SOFM) network. Then the SL samples represented by the primitive library were recognized using template matching and model generation methods. Experimental results show that under the framework of concept learning, we achieve 3% to 4% accuracy improvement for the recognition of 95 classes Australian Sign Language (AUSL) using Dynamic Time Warping (DTW) and Hidden Markov Model (HMM) classifiers.