Sign Language Recognition System Simulated for Video Captured with Smart Phone Front Camera

Abstract

This works objective is to bring sign language closer to real time implementation on mobile platforms. A video database of Indian sign language is created with a mobile front camera in selfie mode. This video is processed on a personal computer by constraining the computing power to that of a smart phone with 2GB ram. Pre-filtering, segmentation and feature extraction on video frames creates a sign language feature space. Minimum distance classification of the sign feature space converts signs to text or speech. ASUS smart phone with 5M pixel front camera captures continuous sign videos containing around 240 frames at a frame rate of 30fps. Sobel edge operator’s power is enhanced with morphology and adaptive thresholding giving a near perfect segmentation of hand and head portions. Word matching score (WMS) estimates performance of the proposed method with an average WMS of around 90.58%.