Batik Motif Classification Using Color-Texture-Based Feature Extraction and Backpropagation Neural Network
Nanik Suciati, Winny Adlina Pratomo, Diana Purwitasari · 2014
Batik is an Indonesian's traditional cloth which has been recognized as one of the world cultural heritage. Currently, there are hundreds of different batik motif which can be classified into 7 groups, i.e. Parang, Ceplok, Lereng, Megamendung, Semen, Lunglungan, and Buketan. This research develops a software to automatically identify motifs of batik image using color-texture-based feature extraction and backpropagation neural network. Color and texture features of batik image is extracted using combination of Color Co-occurence Matrix, Different Between Pixels of Scan Pattern, and Color Histogram for K-Means methods. The extracted features vectors are furthermore classified into motifs using Backpropagation Neural Network. The experiment shows that the software can recognize batik motifs quite well, with rate of Tanimoto Distance 0,37.