Color-based Segmentation of Batik Using the L*a*b Color Space

Abstract

Indonesian Batik has a variety of styles. Coloring techniques affect the color quality of batik. Color is very important to show staining breakthroughs. The colors R (Red) G (Green) and B (Blue) have a close color correlation level so that it is difficult to segment. Segmentation is the process of partitioning digital images into several segments. The segmentation process is carried out on 15 batik sample data. The first step, each sample is converted from RGB - XYZ - Lab color. The average ratio of Red, Green and Blue on the RGB color and XYZ color 1:10. Segmentation using L*a*b color, displays the composition of the sample data colors into six clusters: background, yellow, magenta, purple, red and green using the clustering method. This proposed work L*a*b color space is selected which is a homogeneous space for visual perception.