Chinese Sign Language Alpha-Numeric Character Classification using Neural Network
Abstract: The Chinese Sign Language (CSL) alpha-numeric character classification/recognition without using any aid (embedded sensor, color glove) is really difficult task. This paper describes a novel method to classify static sign by obtaining feature set based on DCT (Discrete Cosine Transform) and Regional properties of hand image. We have collected dataset (alpha numeric character) from 60 people including students of age 20-22 years and few elders aged between 25-38 who have performed 30 signs resulting in total dataset of 1800 signs. Feature set of size 186074 is later trained and tested using different classifiers like Multilayer Perceptron (MLP), Generalized Feed Forward Neural Network (GFFNN), Support Vector Machine (SVM). Out of this 90 % dataset is used for training and 10 % dataset is used for testing/Cross validation. We have got maximum classification accuracy as 89.84 % on CV dataset using GFF Neural Network.
Keywords: CSL, GFFNN, MLP, SVM, DCT
How to Cite?: R. B. Mapari, G. U. Kharat, "Chinese Sign Language Alpha-Numeric Character Classification using Neural Network", Volume 5 Issue 5, May 2016, International Journal of Science and Research (IJSR), Pages: 1158-1164, https://www.ijsr.net/getabstract.php?paperid=NOV163655, DOI: https://dx.doi.org/10.21275/NOV163655