Digital Image Processing to Detect Sumba Woven Fabric Contour Using Gray Level Co-occurrence Matrix and Self Organizing Map

Abstract

Sumba woven cloth is one of the cultural heritages of the island of Sumba. Based on its manufacture, the classification process for Sumba woven fabrics is based on the identification of colors or motifs. However, the classification process is not an easy process. In addition to the classification process, the wider community also does not get much information about Sumba woven fabrics clearly, therefore digital image processing technology is needed to build a system that can overcome the problems faced. The image of the Sumba woven fabric sample is converted to grayscale and resized, then segmented using Sobel detection. Then extracted using Gray level co-occurrence matrix (GLCM). After extraction, it will be classified using a Self Organizing Map (SOM). Based on the results of this study, it was concluded that the accuracy of the validation test was 80%, and the program was successful.