Hand Gesture Recognition of Dumb Person Using one Against All Neural Network
This work addresses a domain-specific problem for assistive technology, but it appears incremental as it builds on existing methods with minor modifications.
The paper tackles hand gesture recognition for individuals who are unable to speak by developing a technique that preprocesses images, segments hand regions using L.a.b color space, extracts statistical features, and trains an Artificial Neural Network with a one-against-all approach, achieving results described as much better than existing techniques.
We propose a new technique for recognition of dumb person hand gesture in real world environment. In this technique, the hand image containing the gesture is preprocessed and then hand region is segmented by convergent the RGB color image to L.a.b color space. Only few statistical features are used to classify the segmented image to different classes. Artificial Neural Network is trained in sequential manner using one against all. When the system gets trained, it becomes capable of recognition of each class in parallel manner. The result of proposed technique is much better than existing techniques.