Indian Sign Language Recogntion using Kinect Sensor

The Depth Cameras have been exploited in computer vision for several years, but the high price and the poor quality of such devices have limited their applicability. With the invention of the low-cost Microsoft Kinect sensor, high-resolution depth and visual (RGB) sensing has become available for widespread use as an off-the-shelf technology. The complementary nature of the depth and visual (RGB) information in the Kinect sensor opens up new opportunities to solve fundamental problems in computer vision, including object and activity recognition, people tracking, 3-D mapping, HGR, Sign language recognition and so on. Meanwhile, the accuracy of object tracking/identification can be improved by considering the depth, motion and appearance information of an object. Furthermore, depth cameras allow us to take computer vision out of the lab and into real environments (e.g. peoples’ homes). Hand gestures are a strong medium of communication for hearing impaired society. Hand Gesture Recognition is helpful for establishing interaction between human and computer. Hand Gesture Recognition for ISL with Kinect sensor is proposed. A continuous Indian Sign Language (ISL) gesture recognition system where both the hands are used for performing any gesture. Recognizing a sign language gestures from continuous gestures is a very challenging research issue. Hand gesture classification can be achieved by K-means algorithm, SVM algorithm, Deep neural networks, PCA algorithm, FEMD (Fingers Earth Movers Distance) etc. FEMD provides robust part-based gesture classification. The proposed work is an attempt towards minimizing the processing time, noise and thus increasing the accuracy of the system. Keywords: Image segmentation, HGR, ISL, FEMD, PCA, K- means, RGB-D sensor.