Improvement Tracking Dynamic Programming using Replication Function for Continuous Sign Language Recognition

TL;DR

This paper introduces a Replication Function to enhance dynamic programming for continuous sign language recognition, improving tracking accuracy by transforming image intensities to better distinguish skin regions.

Contribution

It proposes a novel use of a Replication Function to improve tracking in dynamic programming for sign language recognition, especially in overlapping hand and face regions.

Findings

Tracking Error Rate reduced to 11%

Average Tracked Distance reduced to 7%

Enhanced visibility of skin regions in images

Abstract

In this paper we used a Replication Function (R. F.)for improvement tracking with dynamic programming. The R. F. transforms values of gray level [0 255] to [0 1]. The resulting images of R. F. are more striking and visible in skin regions. The R. F. improves Dynamic Programming (D. P.) in overlapping hand and face. Results show that Tracking Error Rate 11% and Average Tracked Distance 7% reduced