Detection of Indonesian Sign Language Alphabet Features Using the Chain Code Method Deteksi
Main Article Content
Abstract
SIBI which stands for Sistem Isyarat Bahasa Indonesia refers to an Indonesian signal language system for deaf and mute people. This research concerns with detecting the feature extraction of SIBI letters. For this reason, the researcher conducted several phases such as pre-processing, edge detection, image extraction, and letter similarity [1]. In the segmentation process, manhattan distance method was carried out and then continued by converting RGB image to grayscale image and binary image. The next process namely mathematical morphology aimed at reducing the noise of image, whereas the method of chain code with eight directions of connectivity was employed as the extraction method of shape feature to determine the image probability. After that, the formation of eight connectivity of chain code in which edge was preciously detected by Robert operator generated probability value. Meanwhile, the euclidean distance method served as the equation of resulted probability value. By using 171 dataset consisting of 119 data reference and 52 data testing, the accuracy gained averagely 91%.
Downloads
Article Details
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with Positif : Jurnal Sistem dan Teknologi Informasi agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work.
This work is licensed under a Creative Commons Attribution 4.0 International License.
References
Badan Pengembangan dan Pembinaan Bahasa, (2008). Kamus Besar Bahasa Indonesia.
Indra Dolly, S. Madenda, E. Wibowo (2017). Feature Extraction of Bisindo Alphabets Using Chain Code Contour. https://doi.org/10.21817/ijet/2017/v9i3/170904138
K. Anam and A. K.-S. 2014, “IMPLEMENTASI PENGENALAN BAHASA ISYARAT TANGAN SECARA REAL TIME MENGGUNAKAN METODE TWO DIMENSIONAL LINEAR DISCRIMINANT,” repository.unitomo.ac.id, Accessed: Nov. 06, 2022. [Online]. Available: http://repository.unitomo.ac.id/206/1/Senastik2014end-Trunojoyo.pdf#page=248.
“abdul kadir pengolahan citra digital - Google Scholar.” https://scholar.google.com/scholar?hl=en&as_sdt=0%2C5&q=abdul+kadir+pengolahan+citra+digital&btnG= (accessed Nov. 06, 2022)
S. Madhvanath, G. Kim and V. Govindaraju. (1999). Chain Code Contour Processing for Handwritten Word Recognition, IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 21, No. 9. https://doi.org/10.1109/34.790433