Pengenalan Motif Batik Berdasarkan Fitur Tekstur Menggunakan Gray Level Co-occurance Matrics dan Random Forest

Fadilah, Rakhmat (2021) Pengenalan Motif Batik Berdasarkan Fitur Tekstur Menggunakan Gray Level Co-occurance Matrics dan Random Forest. Undergraduate thesis, Politeknik Negeri Jember.

	Text (Abstrak) Abstract.pdf - Accepted Version Available under License Creative Commons Attribution Share Alike. Download (356kB)
	Text (Bab 1 Pendahuluan) Bab 1 Pendahuluan.pdf - Accepted Version Available under License Creative Commons Attribution Share Alike. Download (476kB)
	Text (Daftar Pustaka) Daftar Pustaka.pdf - Accepted Version Available under License Creative Commons Attribution Share Alike. Download (285kB)
	Text (Laporan Lengkap) E41170391_Rakhmat Fadilah_Skripsi_v0.pdf Restricted to Registered users only Download (6MB) | Request a copy

Abstract

Indonesian batik has a variety of motifs and models, which differ in each region and become the hallmark of the region. With the variety and number of batik motifs, the majority of people find it difficult to recognize and distinguish the characteristics of batik cloth motifs, because not all people have knowledge of the types and motifs of existing batik. The differences in existing motifs can be recognized through differences in the shape and texture of the core motif. For this reason, an information system was developed and built that has a function to recognize and identify batik images. This application applies computer vision where the computer is given knowledge so that it can carry out the image identification process. The method used for image extraction is Gray Level Cooccurance Matrics (GLCM) with parameters contrast, dissimilarity, homogeneity, energy, ASM, correlation, IDM and entropy with different angles of 00, 450, 900 and 1350. Batik image data used a total of 400 images, which consists of 360 images of training data and 40 images of testing data. The classification method in this study uses Random Forest. By testing the confusion matrix, the results obtained are True Batik Jember 8 with False 2, True Batik Bondowoso 7 with False 3, True Batik Situbondo 7 with False 3 and True Batik Banyuwangi 9 and False 1. The accuracy results obtained are 77.5 %

Actions (login required)

View Item