Anindita Septirini
Mulawarman University

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

Analysis of Color Features Performance Using Support Vector Machine with Multi Kernel for Batik Classification Edy Winarno; Wiwien Hadikurniawati; Anindita Septirini; Hamdani Hamdani
International Journal of Advances in Intelligent Informatics Vol 8, No 2 (2022): July 2022
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Batik is a sort of cultural heritage fabric that originated in many areas of Indonesia. Each area, particularly Semarang in Central Java, has its own batik design. Unfortunately, due to a lack of knowledge, not all residents are able to recognize the types of Semarang batik.  Therefore, this study proposed an automated approach for classifying Semarang batik. Semarang batik was classified into five categories according to this method:  Asem Arang, Blekok Warak, Gamblang Semarangan, Kembang Sepatu, and Semarangan. Since color was able to distinguish batik patterns, it is necessary to analyze color features based on the color space in order to generate discriminative features.  Color features were produced based on the RGB, HSV, YIQ, and YCbCr color spaces. Four different kernels were used to feed these features into the Support Vector Machine (SVM) classifier. The experiment was conducted using a local dataset of 1000 batik images classified into five classes (each class contains 200 images).  In order to evaluate the method, cross-validation was performed using a k-fold value of 10. The results showed that the proposed method could reach an accuracy of 1 in all SVM Kernels when employing the YIQ color space, which was consistent across all tests.