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 » Fisika
Posted by fandikaaqsa@its.ac.id at 26/02/2016 14:04:33  •  1203 Views


ANALISA PENGARUH PROSES SEGMENTASI CITRA TERHADAP KLASIFIKASI CITRA RONTGEN PARU-PARU DENGAN JST BACKPROPAGATION

ANALYSIS OF IMAGE SEGMENTATION EFFECT FOR LUNG X-RAY IMAGE CLASSIFICATION BY ANN BACKPROPAGATION

Author :
KHOIRO, MUHIMMATUL ( 1110100049 )




ABSTRAK

Analisis pengaruh proses segmentasi citra terhadap klasifikasi citra rontgen paru-paru dengan JST backpropagation telah dilakukan. Data yang digunakan dalam penelitian ini adalah berupa data citra foto rontgen paru-paru yang telah didiagnosa oleh dokter sebanyak 150 data dengan rincian 90 data untuk pelatihan dan 60 data untuk pengujian. Pada penelitian ini citra foto rontgen akan disegmentasi terlebih dahulu sebelum diklasifikasikan ke dalam tipe paru-paru normal paru-paru yang terkena kanker dan paru-paru yang terkena efusi. Pemrosesan awal dilakukan dengan pengolahan citra pra-processing image dilakukan untuk meningkatkan kualitas visual citra sehingga dapat mempermudah proses klasifikasi citra. Dalam proses ini citra masukkan diberi perlakuan proses pengolahan citra seperti komplemen citra median filter untuk mengurangi noise pada citra dan adaptif histogram equalisation untuk memperlihatkan detail citra. Citra kemudian disegmentasi dengan menggunakan mask daerah paru-paru yang dibuat dengan proses deteksi tepi canny. Citra hasil segmentasi kemudian diekstraksi nilai-nilai fitur histogram yang ada dalam citra tersebut. Nilai fitur histogram yang digunakan dalam penelitian ini ialah mean standard deviasi skewness kurtosis dan entropy. Tahapan akhir dilakukan proses pengklasifikasian citra dengan menggunakan jaringan syaraf tiruan backpropagation yang terdiri dari proses pelatihan dan proses pengujian.Pada proses pelatihan didapatkan nilai akurasi sebesar 100 sedangkan proses pengujian sebesar 6833. Jika dibandingkan dengan hasil penelitian sebelumnya dengan bahan dan metode yang sama tanpa proses segmentasi pada penelitian ini terjadi peningkatan performasi jaringan. Dengan adanya proses segmentasi citra jaringan lebih mudah mengenali pola masukkan dari citra.


ABSTRACT

Analysis of image segmentation effect for lung x-ray image classification by ANN Backpropagation have been done. The research use 150 data of lung X-ray image consist of 90 training data and 60 testing data. On this research X-ray image would be processed by segmentation image before its classificate into type of normal lung lung cancer and pneumonia. Pre-processing image has purpose for increase quality of visual image so classification process will be easier. On this process input image is treated by image processing as complement of image median filter for reducing noise on image and adaptif histogram equalisation for displaying details of image. The next process is segmentation by lung fieald mask which have been prepared by edge detection canny. Then histogram features of image are extracted. The histogram features which are used in this reasearch are mean standart deviation skewness kurtosis and entropy. The final process is classification of image using Backpropagation Artificial Neural Network included training and testing process. The research obtained that learning rate is 100 and testing rate is 6833. As if previous research which used the same object and method wihout segmentation of image performance of network is upgraded by this research. With the segmentation process on image network can be easier to identify pattern of image input.



KeywordsSegmentasi citra, Jaringan syaraf tiruan backpropagation, Citra foto rongent paru-paru
 
Subject:  Pencitraan diagnostik; Fisika
Contributor
  1. M. Arief Bustomi, S.Si, M.Si
Date Create: 26/02/2016
Type: Text
Format: PDF
Language: Indonesian
Identifier: ITS-Undergraduate-11101150008402
Collection ID: 11101150008402
Call Number: RSFi 621.367 Kho a


Source
Paper and Presentations of Physics, RSFi 621.367 Kho a, 2014

Coverage
ITS Community

Rights
Copyright @2016 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-40412-1110100049-Conclusion.pdf - 430 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 54.198.165.74
using CCBot/2.0 (http://commoncrawl.org/faq/)



Copyright © ITS Library 2006 - 2017 - All rights reserved.
Dublin Core Metadata Initiative and OpenArchives Compatible
Developed by Hassan