Temu Kembali Citra Menggunakan Multi Texton Co-Occurrence Descriptor

Minarno, Agus Eko (2014) Temu Kembali Citra Menggunakan Multi Texton Co-Occurrence Descriptor. Masters thesis, Insititut Teknologi Sepuluh Nopember.

Text 5112201024-Master_Thesis.pdf Download (2MB)

Abstract

Sistem temu kembali citra masih menjadi topik penelitian yang belum terselesaikan. Beberapa metode ekstraksi fitur untuk temu kembali citra telah dikerjakan sebelumnya, diantaranya Gray Level Co-Occurrence Matrix (GLCM), Texton Co- Occurrence Histogram (TCM), Multi Texton Histogram (MTH), Micro Stucture Descriptor (MSD), Enhanced Micro Strcuture Descriptor (EMSD) dan Color difference Histogram (CDH). Namun, penelitian tersebut masih memiliki precision rata-rata 40%- 60%, sehingga masih perlu dikembangkan lebih lanjut. Dibandingkan dengan TCM, MSD, EMSD dan CDH, pendekatan menggunakan MTH memiliki kompleksitas komputasi yang lebih sederhana, sehingga untuk melakukan temu kembali citra menjadi lebih cepat. Namun demikian MTH memiliki kekurangan dalam merepresentasikan fitur. Pertama, MTH hanya menggunakan fitur lokal dalam merepresentasikan citra. Kedua, dalam pendeteksian pasangan piksel menggunakan Texton, ada informasi pasangan piksel yang terlewatkan sehingga dapat mengurangi representasi citra. Penelitian ini mengusulkan pendekatan baru untuk melakukan ekstraksi fitur pada sistem temu kembali citra. Kontribusi penelitian ini yaitu menambahkan jenis Texton baru untuk mendeteksi pasangan piksel dan menambahkan fitur GLCM. Metode yang diusulkan pada penelitian ini dinamakan Multi Texton Co-Occurrence Descriptor (MTCD). MTCD melakukan ekstraksi fitur warna, tekstur dan bentuk secara simultan menggunakan Texton, kemudian menghitung representasi citra secara global dengan GLCM. Texton mendeteksi konkurensi pasangan pixel pada setiap komponen RGB dan orientasi tepi citra, sedangkan GLCM merepresentasikan citra dengan sudut pandang global yang dihasilkan dari energy, entropy, contrast dan correlation. Fitur akhir MTCD berupa histogram hasil dari deteksi Texton dan GLCM. Data yang digunakan untuk temu kembali citra menggunakan 300 data Batik dan 10.000 data Corel. Pengukuran kemiripan citra menggunakan Canberra dan pengukuran performa MTCD menggunakan precision dan recall. Data uji dipilih secara acak terdiri dari 50 d ata Batik, 2.500 untuk data Corel 5.000 dan 5.000 untuk data Corel 10.000. Berdasarkan hasil uji coba yang telah dilakukan, penambahan 2 texton baru dan fitur GLCM dapat meningkatkan precision 2,86% pada data Batik, 3,40% pada data Corel 5.000 dan 3,06% pada data Corel 10.000. MTCD lebih unggul daripada MTH untuk temu kembali citra.
=============================================================================================================================
Image retrieval system is one of a challenging topic and is not yet finalized. A number of features extraction methods has been proposed, for example Gray Level Co- Occurrence Matrix (GLCM), Texton Co-Occurrence Histogram (TCM), Multi Texton Histogram (MTH), Micro Stucture Descriptor (MSD), Enhanced Micro Structure Descriptor (EMSD) and Color difference Histogram (CDH). However, the precision rate of those methods are relatively low, between 40% and 60%. Therefore, there is a need of a new approach to improve the results. Looking to those methods, in term of computational complexity, MTH is the simplest. The problem is that there is weakness in representing image features. First, MTH using local features to representate the image. Second, The weakness occurs in the proces of detecting pairs of pixel using texton for color quatization and edge orientation quantization. This study proposes a new approach to perform features extraction in image retrieval systems. Contribution of this study is to add new types of Texton to detect pairs of pixels and adding GLCM features. The method in this study is called Multi Texton Co-Occurrence Descriptor (MTCD). MTCD works by extracting color features, texture features and shape features simultaneously using Texton, then calculates the global image representations with GLCM. Texton detects concurrency of pairs of pixels on each RGB component and the edge orientation of image, while GLCM represents the image as global viewpoint by the value of energy, entropy, contrast and correlation. Features that are detected by MTCD are presented as histogram. The data used in this study is a 300 batik data and a 10,000 Corel data. In order to measure image similarity, Canberra Distance is used. For performance measurement, precision and recall are used. Test data randomly selected consists of 50 Batik data, 2,500 for Corel 5.000 and 5.000 for Corel 10.000. Based on the results of the testing that has been done, the addition of 2 new texton and GLCM features can improve the precision 2.86%, 3 ,40% and 3,06% on Batik, Corel 5.000 and Corel 10.000 respectively. MTCD is superior than MTH for image retrieval.

Item Type:	Thesis (Masters)
Additional Information:	RTIf 006.42 Min t
Uncontrolled Keywords:	Batik, Temu kembali citra, Texton, Gray Level Co-Occurrence Matrix
Subjects:	T Technology > TA Engineering (General). Civil engineering (General) > TA1637 Image processing--Digital techniques
Divisions:	Faculty of Intelligent Electrical and Informatics Technology (ELECTICS) > Informatics Engineering > 55101-(S2) Master Thesis
Depositing User:	Mr. Marsudiyana -
Date Deposited:	06 Nov 2023 07:32
Last Modified:	06 Nov 2023 07:32
URI:	http://repository.its.ac.id/id/eprint/105070

Actions (login required)

View Item