Nurrahim, Fahmi (2019) KLASTERISASI HASIL TEMU KEMBALI CITRA MENGGUNAKAN METODE MULTI TEXTON CO – OCCORRENCE DESCRIPTOR DAN K – MEANS. Bachelors Degree (S1) thesis, University of Muhammadiyah Malang.

Preview	Text PENDAHULUAN.pdf Download (704kB) | Preview
Preview	Text BAB I.pdf Download (267kB) | Preview
Preview	Text BAB II.pdf Download (935kB) | Preview
Preview	Text BAB III.pdf Download (1MB) | Preview
	Text BAB IV.pdf Restricted to Registered users only Download (1MB)
	Text BAB V.pdf Restricted to Registered users only Download (315kB)
	Text LAMPIRAN.pdf Restricted to Registered users only Download (566kB)
	Image poster.jpg Restricted to Registered users only Download (3MB)

Abstract

Along with the development of image processing, there is an alternative approach to look for images based on information on features found in each image, the approach is image retrieval technique. The characteristics of the image contain information about colors, angles, edges, textures and various other types of information obtained from the image itself. This information is used to determine how precisely the desired image is retrieved. The way to extract features in an image uses texton detection to recognize objects in the image. Multi Texton Co-occurrence Descriptor (MTCD) is a texton detection method by using 6 types of texton detection in the image by extracting three characteristics in the image, namely color, edge, and angle. K-Means is a method of grouping or clustering a data into their respective classes based on the similarity of the distance between one data and another data. This study aims to create an image retrieval program using the addition of the K-Means method on the MTCD results in order to better group the images of each class. Based on the results of tests conducted on 50% of the 10,000 data in the Corel dataset obtained a precision increase of 1.22% in the image retrieval results.

Item Type:	Thesis (Bachelors Degree (S1))
Student ID:	201510370311055
Keywords:	MTCD, clustering, feature extraction, K – Means
Subjects:	Z Bibliography. Library Science. Information Resources > ZA Information resources
Divisions:	Faculty of Engineering > Department of Informatics (55201)
Depositing User:	Sulistyaningsih Sulistyaningsih
Date Deposited:	17 May 2019 07:53
Last Modified:	17 May 2019 07:53
URI :	http://eprints.umm.ac.id/id/eprint/46194

Actions (login required)

View Item