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 » Master Theses » Teknik Informatika - S2
Posted by anisw@its.ac.id at 04/05/2016 11:05:30  •  1539 Views


PEMBOBOTAN ARAH DAN BESARAN GRADIEN PADA ANT COLONY OPTIMIZATION UNTUK DETEKSI TEPI CITRA

WEIGHTING OF DIRECTION AND GRADIENT MAGNITUDE ON ANT COLONY OPTIMIZATION FOR IMAGE EDGE DETECTION

Author :
KIRANA, KARTIKA CANDRA ( 5113201012 )




ABSTRAK

Deteksi tepi merupakan tahap penting pada pengolahan citra digital.Dalam beberapa bidang hasil deteksi tepi dituntut lebih akurat. Untuk itu dibutuhkan suatu pengembangan algoritma untuk deteksi tepi. Salah satu pengembangan algoritma untuk deteksi tepi adalah Ant Colony Optimization ACO. ACO merupakan salah satu metode heuristik yang meniru perilaku semut. Komunikasi semut pada algoritma ini bersifat lokal. Sementara itu informasi heuristik pada kelompok lokal kurang optimal dalam membedakan piksel tepi dan piksel bukan tepi sehinggadibutuhkan tambahan informasi pada kelompok lokal berdasarkan karakterisitik tepi. Oleh karena itu pada penelitian ini diusulkan pengembangan aturan baru pergerakan semut berdasarkan bobot arah dan besaran gradien pada algoritma ACO yang digunakan untuk deteksi tepi citra. Pada penelitian ini deteksi tepi diawali dengan pembentukan koloni dan sarang semut. Selanjutnya semut akan melakukan pencarian tepi berdasarkan metodeyang diusulkan dimana pergerakan semut tidak hanya berdasarkan feromon dan informasi heuristik tetapi juga berdasarkan stimulus arah dan besaran gradien. Lalu semut akan berhenti dan mendapatkan solusi tepi setelah selisih jumlah tepi antar iterasi telah mencapai ambang batas yang telah ditentukan dimana penentuan tepi dilakukan menggunakan Otsu thresholding. Uji coba dilakukan terhadap tujuh citra pribadi dan 26 citra dataset CID. Figure of Meritdigunakan untuk mengevaluasi akurasi tepi. Rata-rata figure of merit dari metode yang diajukan mencapai 0.800 80 dengan bobot informasi heuristik feromon dan gradien yang bernilai satu serta bobot arah kandidat piksel pada kelompok lokal sebesar 0.9.


ABSTRACT

Edge detection is an important step in digital image processing. In some areas the accuracy of the edge detection isdemanded. Therefore a development of algorithm for edge detection such as Ant Colony Optimization ACO is needed. ACO is a heuristic method that imitatesforaging behavior of ants. Communication of ant is local. However in local communication heuristic information can not classify edge pixel and non-edge pixel clearly so ants need additional edge information. To solve this problem we proposed a new transition rule using weight of gradient magnitude and direction at ACO algorithm for edge detection. In this study the first stage of proposed method is construct colony and nest of ant. Then ants will search edge which rules of ant movement are not only based on the pheromone and heuristic information but also based on weight of gradient magnitude and direction. In the final stage ants will stop after different of edge number reach threshold which the edge number is determined using Otsu. Proposed method is evaluated using personal image and CIDs image dataset. Figure of merit is used to evaluate edge accuration. Experiment showed that the proposed method reached average of figure of merit up to 0.800 80 with weight of pheromone heuristic information and gradient are one and direction weight of local non-edge candidate is 0.9.



KeywordsAnt Colony Optimization; Gradient Magnitude; Gradient Direction; Aturan Pergerakan Semut
 
Subject:  NONE
Contributor
  1. Dr. H. Agus Zainal Arifin, S.Kom., M.Kom.
  2. Wijayanti Nurul Khotimah, S.Kom, M.Sc.
Date Create: 22/01/2015
Type: Text
Format: pdf
Language: Indonesian
Identifier: ITS-Master-51103160001633
Collection ID: 51103160001633
Call Number: RTIf 006.42 Kir p


Source
Master Theses of Informatics Engineering, RTIf 006.42 Kir p, 2014

Coverage
ITS Community

Rights
Copyright @2015 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-Master-41426-5113201012-Abstract_id.pdf - 275 KB
  2.  ITS-Master-41426-5113201012-Abstract_en.pdf - 176 KB
  3.  ITS-Master-41426-5113201012-Conclusion.pdf - 177 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 35.175.191.150
using CCBot/2.0 (https://commoncrawl.org/faq/)



Copyright © ITS Library 2006 - 2019 - All rights reserved.
Dublin Core Metadata Initiative and OpenArchives Compatible
Developed by Hassan