Gesture Based English Character Recognition for Human Machine Interaction in Interactive Set Top Box Using Multi-factor Analysis

In this paper authors have presented a novel approach for human machine interaction (HMI) that can be used to give alphabets as input to Internet browser in an interactive Set top box with this added facility. The device is designed with a MEMS sensor which can be worn on fingertip to send alphabetical input to an interactive set top box. Users write the English alphabet in capital letter by just using the sensor attached to their hand. Then this data is undergone some filtering and finally it is sent to the recognition module. The features used for recognition consists of chain code based and un-directional un-weighted graph based features. Each of them recognizes the input character with some confidence factor lying in the closed interval (0,1). Final decision about the recognized character is made by using multifactorial approach. We get a recognition accuracy of more than 90%. We have tested the system with the inputs given by 22 users (16 male and 6 female) each of the user is asked to write the each letter 5 times.