Algorithm Of Gesture Recognition Based On Image Analysis

The technology of computer vision, machine learning and other areas applies deaf speech recognition problems.Now the main way of communication between the hearing disorders is text and sign language. Most of the hearing disabilities use sign language gestures to communicate, however the hearing normal people don’t know the basically sign language. This phenomenon leads to the barriers of communication between the hearing disorder and the hearing normal. In order to solve the issue of information exchange between hearing impaired people and normal people, research the sign language automatic recognition technology.Sign language recognition system takes use of information technology, communication technology, computer technology to solve communication problems for deaf, and it is an integrated system for those key technology about sign language recognition. Summarized In this paper, as follows:Through analysis based on the current research results, using image processing to extract the target area, and take appropriate characterization and machine learning methods for further precise judgment, ultimately to finish sign language recognition.First, obtain the complete hand-type region of the image, using the image preprocess algorithm such as YUV color segmentation, image differencing, connected domain detection. Then process images through contour detection, have the feature extraction and compression by LBP transform and principal component analysis. Finally, use support vector machine as a training machine learning algorithms to build classifier and finish the classification and identification.Finally, verify by experiment and data analysis results from a comprehensive software testing to show the proposed algorithm’s effectiveness and practicality. To research a total of630gesture images, the experimental results show that the algorithm can improve the recognition rate and speed effectively. And its recognition rate reaches94.22%, speed reaches0.29s/piece, meet the requirement of real-time communication for sign language.The proposed method can be applied to improve the real-time detection, and also has a good anti-jamming capability and capacity to respond to complex background.