Hand Gesture Recognition of Static Letters American Sign Language (ASL) Using Deep Learning
An American Sign Language (ASL) is a complex language. It is depending on the special gesture stander of marks. These marks are represented by hands with assistance by facial expression and body posture. ASL is the main communication language of deaf and people who have hard hearing from North America and other parts of the world. In this paper, Gesture recognition is proposed of static ASL using Deep Learning. The contribution consists of two solutions to the problem. The first one is resized with Bicubic static ASL binary images. Besides that, good recognition results in of detection the boundary hand using the Robert edge detection method. The second solution is to classify the 24 alphabets static characters of ASL using Convolution Neural Network (CNN) and Deep Learning. The classification accuracy equals to 99.3 % and the error of loss function is 0.0002. According to 36 minutes with 15 seconds of elapsed time result and 100 iterations. The training is fast and gives the very good results, in comparison with other related works of CNN, SVM, and ANN for training.
How to Cite
The author assigns to Engineering and Technology Journal with full title guarantee, all copyrights, rights in the nature of copyright, and all other intellectual property rights in the article throughout the world (present and future, and including all renewals, extensions, revivals, restorations and accrued rights of action). The Author represents that he/she is the author and proprietor of this Article and that this Article has not heretofore been published in any form. The Author warrants that he/she has obtained written permission and paid all fees for use of any literary or illustration material for which rights are held by others. The author agrees to hold the editor(s)/publisher harmless against any suit, demand, claim or recovery, finally sustained, by reason of any violation of proprietary right or copyright, or any unlawful matter contained in the submitted article.