What question did this study set out to answer?

The aim is to predict and classify traditional batik motifs to preserve Indonesian cultural heritage.

January 1, 2018Open Access

Classification of coastal and Inland Batik using GLCM and Canberra Distance

Key Points

The aim is to predict and classify traditional batik motifs to preserve Indonesian cultural heritage.
Utilized Content-Based Image Retrieval (CBIR) for motif prediction.
Employed Gray Level Co-Occurrence Matrices (GLCM) for feature extraction.
Applied Canberra Distance for classification of motifs.
Achieved significant accuracy in classifying Coastal and Inland Batik motifs using GLCM and Canberra Distance.

Abstract

As an effort to preserve one of the Indonesian cultural products, this study discusses the predictions of traditional motifs. The case study is the Coastal Batik and Inland Batik. The diversity of traditional batik motifs in Indonesia began to erode due to the influx of foreign culture hence the authenticity of the traditional motifs of a particular area is not synonymous with the region of origin. As a consequent, due to many traditional Indonesian motifs, it is difficult to recognize the original motive of a particular area. It became the goal in conducting this study. Traditional motifs (Coastal Batik and Inland Batik) were data to be predicted using the method of Content-Based Image Retrieval (CBIR). With the implementation of feature extraction of Gray Level Co-Occurrence Matrices (GLCM) with a classification method using CBIR to calculate Canberra Distance, the level of accuracy of the classification results was obtained.

Bookmark

View Full Paper