Hand Gesture Recognition of Dumb Person Using one Against All Neural Network

TL;DR

This paper introduces a neural network-based method for recognizing hand gestures of individuals with speech impairments in real-world settings, utilizing color space segmentation and statistical features for classification.

Contribution

It presents a novel approach combining color space segmentation and one-against-all neural networks for gesture recognition of speech-impaired individuals.

Findings

Recognition accuracy surpasses existing methods

Effective segmentation using L.a.b color space

Parallel recognition of multiple gesture classes

Abstract

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.