KLASIFIKASI MOTIF BATIK PAPUA MENGGUNAKAN FITUR GRAY LEVEL CO-OCCURRENCE MATRIX DAN LOCAL BINARY PATTERN DENGAN ALGORITMA K-NEAREST NEIGHBORS

Susan Rosmawati, S.Pd, NIM.: 212060510011 (2023) KLASIFIKASI MOTIF BATIK PAPUA MENGGUNAKAN FITUR GRAY LEVEL CO-OCCURRENCE MATRIX DAN LOCAL BINARY PATTERN DENGAN ALGORITMA K-NEAREST NEIGHBORS. Masters thesis, UIN SUNAN KALIJAGA YOGYAKARTA.

Preview	Text (KLASIFIKASI MOTIF BATIK PAPUA MENGGUNAKAN FITUR GRAY LEVEL CO-OCCURRENCE MATRIX DAN LOCAL BINARY PATTERN DENGAN ALGORITMA K-NEAREST NEIGHBORS) 21206051011_BAB-I_IV-atau-V_DAFTAR-PUSTAKA.pdf - Published Version Download (3MB) | Preview
	Text (KLASIFIKASI MOTIF BATIK PAPUA MENGGUNAKAN FITUR GRAY LEVEL CO-OCCURRENCE MATRIX DAN LOCAL BINARY PATTERN DENGAN ALGORITMA K-NEAREST NEIGHBORS) 21206051011_BAB-II_sampai_SEBELUM-BAB-TERAKHIR.pdf - Published Version Restricted to Registered users only Download (4MB) | Request a copy

Abstract

Batik is one of Indonesia's most famous and internationally recognized cultures. Batik has been recognized by UNESCO as a Masterpieces of the Oral and Intangible Heritage of Humanity in 2009. Papuan batik is characterized by motifs inspired by nature and Papuan culture, such as animal motifs, plants, and Papuan traditional symbols. The bright and rich colors also characterize Papuan batik. With the development of technology, batik has become one of the most sought-after textile products in Indonesia and the world. Batik is not only considered as traditional clothing, but also as an innovative and modern fashion product. However, there are still many people who do not know about batik motifs, especially from Papua. A lot of research on batik pattern recognition has been done, but research on Papuan batik pattern recognition has never been done. Therefore, this research focuses on Papuan batik motifs such as Cendrawasih, Asmat, and Honai. There are 51 batik images, 42 training data, and 9 test data. Gray Level Co-occurrence Matrix and Local Binary Pattern are used to extract features in this research. In the pre-processing stage, image acquisition is carried out, followed by resizing the batik image and grayscaling. Using the K-Nearest Neighbor algorithm during the classification process. K-Nearest Neighbor has several advantages, including fast training, simple, and easy to learn. The purpose of this research is to find a good accuracy value of the two texture features used. The best accuracy value is obtained by the GLCM feature with an accuracy value of 100% at K = 7. While LBP obtained an accuracy value of 88.88% at K = 3.

Share this knowledge with your friends :

Actions (login required)

View Item