EMAIL: PASSWORD:
Front Office
UPT. PERPUSTAKAAN
Institut Teknologi Sepuluh Nopember Surabaya


Kampus ITS Sukolilo - Surabaya 60111

Phone : 031-5921733 , 5923623
Fax : 031-5937774
E-mail : libits@its.ac.id
Website : http://library.its.ac.id

Support (Customer Service) :
timit_perpus@its.ac.id




Welcome..guys!

Have a problem with your access?
Please, contact our technical support below:
LIVE SUPPORT


Moh. Fandika Aqsa


Davi Wahyuni


Tondo Indra Nyata


Anis Wulandari


Ansi Aflacha




ITS » Undergraduate Theses » Teknik Informatika
Posted by aprill@is.its.ac.id at 26/12/2012 09:05:47  •  872 Views


IMPLEMENTASI PENGENALAN CITRA TEKSTUR TAK SERAGAM DAN BERWARNA MENGGUNAKAN MOMEN TCHEBICHEF

AN IMPLEMENTATION OF NON-UNIFORM AND COLORED TEXTURE RECOGNITION USING TCHEBICHEF MOMENTS

Author :
AMORETTA, ADRIENA  ( 5108100018 )




ABSTRAK

Tekstur adalah tampilan permukaan corak dari suatu benda yang dapat dinilai dengan cara dilihat atau diraba. Yang pada prakteknya tekstur sering dikategorikan sebagai corak dari suatu permukaan benda misalnya permukaan karpet baju kulit kayu dan lain sebagainya. Pada suatu citra tekstur merupakan komponen dasar pembentuk citra. Sehingga tekstur kerap kali digunakan sebagai pembeda antara satu citra dengan citra lainnya. Kebanyakan tekstur mempunyai pola yang seragam. Tetapi ada pula yang tak seragam seperti contoh batik tulis. Penggunaan metode matriks kookurensi yang telah ada sebagai pengenalan tekstur memiliki kekurangan jika dihadapkan dengan tekstur yang tak seragam dan berwarna. Karena metode tersebut hanya dapat digunakan untuk tekstur keabuan dan seragam. Akan sangat tidak efisien apabila masukan data adalah citra berwarna yang kemudian pada proses selanjutnya harus dijadikan citra keabuan melalui proses keabuan. Kemudian muncul metode multispektral yang dapat mengenali tekstur berwarna. Tetapi metode tersebut hanya dapat digunakan ketika tekstur tersebut merupakan tekstur seragam. Sehingga tidak dapat digunakan pada tekstur tak seragam seperti batik. Pada tugas akhir ini digunakan polinomial ortogonal Tchebichef sebagai cara untuk mempertahankan informasi bentuk dari tekstur yang tak seragam yang dihasilkan oleh metode matriks kookurensi multispektral RGB. Dekomposisi dari enam matriks kookurensi multispektral RGB menghasilkan satu set koefisien momen yang digunakan untuk mengukur perbedaan antar tekstur. Sehingga setiap satu jenis tekstur memiliki satu set momen yang nilainya hampir sama atau dengan kata lain mempunyai selisih paling sedikit dibandingkan dengan jenis tekstur lain. Metode yang diusulkan menghasilkan tingkat pengenalan paling optimal ketika digunakan metode klasifikasi kNN dengan nilai momen order sebesar 30.


ABSTRACT

On an image texture is a basic component of the image forming. So texture is often used as a differentiator between an image with another image. Carpet surface clothing bark and so on are example of the textureof objects. Most patterns have a uniform texture. To identify an uniform texture is very easy. Because the texture is bound to have the same pattern and color. The problem occurs when faced with a similar texture but not uniform like batik. The use of co-occurrence matrix methods as texture recognition has shortcomings when faced with the color and texture is non-uniform. Since the method can only be used for grayscale and uniform texture it would be very inefficient the data input is a color image which is then on the next process should be through the grayscale image processing. Then comes the multispectral method that can recognize color texture. But the method can only be used when the texture is a uniform texture. So it cant be used on non-uniform texture such as batik. At this final project Tchebichef orthogonal polynomials are used as a way to retain form information of an uniform texture which is produced by the RGB multispectral co-occurrence matrix. Decomposition of six RGB multispectral co-occurrence matrices generates a set of moment coefficient which is used to measure the difference between textures. So each texture has a set of moment whose value is almost the same or in other words less different compared to other types of texture. This proposed method produces the most optimum degree of accuracy when used with kNN classification method with number of moment order is 30.



Keywordsmatriks kookurensi; multispektral tchebichef; tekstur
 
Subject:  pengolahan gambar - teknik digital
Contributor
  1. Yudhi Purwananto, S.Kom, M.Kom
  2. Rully Soelaiman, S.Kom, M.Kom
Date Create: 18/07/2012
Type: Text
Format: pdf
Language: Indonesian
Identifier: ITS-Undergraduate-51001120001667
Collection ID: 51001120001667
Call Number: RSIf 006.42 Amo i


Source
Undergraduate Thesis, Informatics Engineering, RSIf 006.42 Amo i, 2012

Coverage
ITS Community

Rights
Copyright @2012 by ITS Library. This publication is protected by copyright and per obtained from the ITS Library prior to any prohibited reproduction, storage in a re transmission in any form or by any means, electronic, mechanical, photocopying, reco For information regarding permission(s), write to ITS Library




[ Download - Open Access ]

  1.  ITS-Undergraduate-22895-5108100018-Abstract_id.pdf - 189 KB
  2.  ITS-Undergraduate-22895-5108100018-Abstract_en.pdf - 189 KB
  3.  ITS-Undergraduate-22895-5108100018-Conclusion.pdf - 187 KB




 Similar Document...




! ATTENTION !

To facilitate the activation process, please fill out the member application form correctly and completely

Registration activation of our members will process up to max 24 hours (confirm by email). Please wait patiently

POLLING

Bagaimana pendapat Anda tentang layanan repository kami ?

Bagus Sekali
Baik
Biasa
Jelek
Mengecewakan





You are connected from 3.214.224.224
using CCBot/2.0 (https://commoncrawl.org/faq/)



Copyright © ITS Library 2006 - 2020 - All rights reserved.
Dublin Core Metadata Initiative and OpenArchives Compatible
Developed by Hassan