Pengenalan Pola Motif Kain Songket Lombok Menggunakan Ekstraksi Fitur LBP, GLCM dan Metode K-Nearest Neighbor

Abstract

Lombok's original songket cloth is an example of regional culture that attracts tourists to Lombok. The way the fibers and middle flowers are arranged which are characteristic of each motif can be used to differentiate one motif from another. Therefore, this research was conducted to introduce the names of Lombok songket cloth motifs to the general public by utilizing machine learning technology to recognize patterns of Lombok songket cloth motifs by extracting Gray Level Co-occurrence Matrix (GLCM), Local Binary Pattern (LBP) and K-Nearest Neighbor (KNN). The total data used is 60 data with 6 Lombok songket motifs which are divided into training data and test data. The best accuracy obtained when combining GLCM and LBP features is 83.33%. Obtained using the GLCM dissimilarity, correlation, homogeneity and contrast features, all GLCM tangles (0⁰, 45⁰, 90⁰, 135⁰) at k=1.