International Journal on Advanced Science, Engineering and Information Technology, Vol. 7 (2017) No. 5, DOI:10.18517/ijaseit.7.5.2746

Recognition of Bisindo Alphabets Based on Contour Chain Code and Similarity of Euclidean Distance

Dolly Indra, Sarifuddin Madenda, Eri Prasetyo Wibowo

Abstract

Sign language in Indonesia there are two forms in its application in the community i.e., Indonesia sign language or known as Bisindo, and Indonesian sign language or known as SIBI. In this study, we conduct  research about recognition of Bisindo alphabets using contour chain code for method of feature extraction and similarity of euclidean distance for method of recognition. Features form used is probability of chain code generated from contour following and the formation of chain code. The proposed method in this study consisted of five section, i.e., input test image, segmentation, edge detection, feature extraction and matching process of alphabet. In the testing process of proposed method, we used 52 images of hand gestures used as test images. The images are in form of static images and 26 images of hand gestures used as reference images which represents 26 alphabets bisindo from A to Z, where the images stored as database. The test images of different shapes and sizes with image references. For recognition we do the matching between the probability of the test image chain code with the probability of the reference image chain code using euclidean distance. The measurement result of euclidean distance in this study was generated average accuracy rate of similarity above 94%. This indicates that the method proposed in this study was effective and produce the level of similarity of bisindo alphabets was accurate

Keywords:

bisindo; segmentation; morphology; edge detection; contour following; chain code; euclidean distance

Viewed: 51 times (since Sept 4, 2017)

cite this paper