MSL Hand Gesture System

Priyanka Tandale

Abstract: Gesture recognition is an important for developing alternative human-computer interaction. It enables human to interface with machine in a more natural way. A hand gesture consists of two types, static and dynamic. A static gesture is a particular hand configuration and pose, represented by a single image. A dynamic gesture is a moving gesture, represented by a sequence of images. Four steps with regard to gesture are; acquisition, modelling, feature extraction and recognition. Gesture acquisition for dynamic hand gestures is carried using web camera. Gesture modelling consists of pre-processing steps. Segmentation is used to detect hand from its background. Gesture recognition from Marathi Sign Language (MSL) alphabets database consisting of total 40 gestures and total dataset of 200 images with different orientation will be carried out using feature extraction and training the gestures using ANN. Recognition includes multilayer perceptions.

Keywords: MSL, HSV, ANN, MLP, Back Propagation