HAND GESTURE RECOGNITION SYSTEM USING HYBRID TECHNOLOGY FOR HARD OF HEARING COMMUNITY

Abstract

Sign language is language which is uses a manual communication or a body language to convey meaning. It is the combination of hand shapes, orientation and movement of hands, arms or body, and facial expressions. Our System is capable of recognizing sign-language  symbols which is used as a means of communication with hard of hearing people. This system is to help those peoples to communicate with normal people without and sophisticated devices like power, data gloves and colored finger cap and etc. Instead we have used a camera as a device to acquire the Indian Sign Language (ISL) from the hard of hearing people. In this process the steps of translation are image acquisition,pre processing, and segmentation of hand shape images, feature extraction and classification of hand shape. In this paper new hybrid image segmentation is proposed to detect the hand sign images based on canny edge detection method and fuzzy c means clustering with thresholding technique. . Here canny edge detection is applied to extract the finger tips of hand sign image accurately. Fuzzy c means clustering method is applied for final tuning of segmented image with better image quality of index. The new method is validated with the parameters in terms of energy level, Entropy level, and Evaluation time (ET). After getting the vectors of feature extraction state the classification is done by comparing existing training set. After getting the symbols from database, the sign symbol is translated as text information (any language ex: English or Tamil)