Using K-NN (K-Nearest Neighbor) Classification Method
I Gede Surya Rahayuda
STMIK AMIKOM Yogyakarta
e-mail: [email protected]
Endek fabric Bali is one form of craft woven fabric of Balinese society. Today almost all Balinese dressed in clothes made of fabrics Endek in daily activities. Endek cloth is used to attend a specific event or to be worn at work, previously only government officials who wore Endek as clothes for work, but today almost all agencies also use it, either government or private agencies. Endek fabric has a variety of motifs or designs used on the cloth picture, a lot of people who do not know that endek have the type based on the design motif. In this research will be carried out an analysis texture on the Image Motif of Endek Bali and then classify them into several classes based on the type pattern motif of Endek Bali. The first step in this research is to collect some Image of Endek with different motif, then after that transform image into a gray level image using Edge Detection, after that do the extraction characteristics using GLCM (Gray Level Co-occurrence Matrix), after getting the feature extraction then performed the data classification feature extraction using K-NN (K-Nearest Neighbor).
Based on the analysis of all the grades K that have been tested, the value K with the most excellent level accuracy is K = 15, if viewed by image component, the most accurate accuracy is on Correlation component, with an accuracy percentage of 43.33%. Overall, the Cemplong motif is a motif that has recognition accuracy levels better than most other motifs, that with a percentage of 57.50%. There are quite a lot of motifs that are less precise Endek recognized at the time of classification. This is because among the Endek motifs may have similar texture. The purpose of this study is to analyze texture and classify image motif of Endek Bali so that later can be developed into an application or program that can help make it easier for people to recognize the type of fabric Endek based design motif. And even better if the program will be implemented on the mobile phone, so can facilitate the process of image acquisition and subsequent directly extracted and classified from the mobile phone and can produce accurate classification results.
Keywords: Analisis Tekstur, Endek, Bali, Edge Detection, Gray Level Co-occurrence Matrix, K-Nearest Neighbor, GLCM, K-NN.
...(download the rest of the essay above)