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 » 51200-Teknik Informatika S2
Posted by tondoindra@gmail.com at 10/06/2015 17:49:53  •  1038 Views


IDENTIFIKASI PENYAKIT NODA PADA CITRA DAUN TEBU MENGGUNAKAN SEGMENTATION-BASED FRACTAL COOCCURRENCE TEXTURE ANALYSIS SFCTA DAN LAB COLOR MOMENTS

IDENTIFICATION OF SUGARCANE LEAF SPOT DISEASES SEVERITY USING SEGMENTATION-BASED FRACTAL CO-OCCURRENCE TEXTURE ANALYSIS SFCTA AND Lab COLOR MOMENTS

Author :
RATNASARI, EVY KAMILAH ( 5112201058 )




ABSTRAK

Penyakit noda pada tanaman tebu yang disebabkan oleh jamur ada beberapa jenis dan masing-masing memiliki ciri yang unik. Identifikasi penyakit noda tersebut secara manual memiliki beberapa kelemahan yang dapat berpengaruh pada akurasi. Teknik pemrosesan citra telah diaplikasikan pada penelitian sebelumnya tetapi belum ada penelitian yang mengidentifikasi lebih dari satu jenis lesi penyakit noda pada suatu citra daun tebu. Tesis ini mengusulkan gabungan konsep dimensi fraktal dan Gray Level Co-ccurrence Matrix GLCM dari citra tersegmentasi yang dinamakan Segmentation-based Fractal Co-occurrence Texture Analysis SFCTA sebagai ekstraksi fitur tekstur dan Lab color moments sebagai fitur warna untuk klasifikasi. Model tersebut terdiri dari proses a Penentuan area daging daun tebu b Pemotongan daging daun c Ekstraksi fitur d Penentuan jenis penyakit menggunakan metode klasifikasi kNN dan e Perhitungan persentase masing-masing jenis penyakit. Perekaman daun tebu dilakukan pada bagian tengah helai daun dengan panjang 20 cm. Jenis penyakit tebu yang diidentifikasi berupa noda kuning noda karat dan noda cincin. Evaluasi dilakukan dengan membandingkan hasil identifikasi model yang diajukan terhadap pengamatan oleh ahli. Model identifikasi yang dihasilkan dari tesis ini mampu mengenali jenis penyakit noda berdasarkan ekstraksi fitur yang diajukan dengan akurasi sebesar 96 sehingga identifikasi keparahan penyakit noda pada citra daun tebu menghasilkan RMSE rata-rata 7.49 dengan tingkat kesalahan identifikasi rata-rata sebesar 6.66.


ABSTRACT

Spot diseases in sugarcane leaf is caused by fungus have unique symptom of color and surface. Diseases severity identification of sugarcane conducted by experts with interpreting percentage leaf spot diseases has some drawbacks affect the accuracy. Several studies have been carried out using image processing techniques but no studies that can identify more than one type of spot diseases that infects the leaves of sugarcane. This study proposed a texture feature extraction from segmented image with combining fractal dimension and Gray Level Co-occurrence Matrix GLCM concept namely the Segmentation-based Fractal Co-occurrence Texture Analysis SFCTA and Lab color moments to identify the tendency of spot disease severity using classification technique. The model consists of process a Determination of intervenum sugarcane leaf area b Split into small parts the intervenum leaf area c Feature extraction d Determination of the type of spot diseases using kNN classification approach and e Calculation of the percentage of each spot diseases type. The image dataset acquisition is done by utilizing the digital camera for capture the sugarcane leaf. The identified spot diseases type in this study are yellow spot rust spot and ring spot. Evaluation of identification models are compared with visual observations by experts. Identification model resulted in this thesis can determine the type of spot diseases with accuracy 96 based on proposed feature extraction method and the average of RMSE of 7.49 and average of error identification 6.66 are achieved by apply the model to measure the spot disease severity.



Keywordsidentifikasi penyakit noda, citra daun tebu, dimensi fraktal, GLCM, color moment, klasifikasi
 
Subject:  Sistem Pengoperasian
Contributor
  1. Dr. Ir. R.V. Hari Ginardi, M. Sc.
  2. Dr. Eng. Chastine Fatichah, S. Kom, M. Kom
Date Create: 17/07/2014
Type: Text
Format: PDF
Language: Indonesian
Identifier: ITS-Master-51103150001405
Collection ID: 51103150001405
Call Number: RTIf 006.42 Rat i


Source
Master Theses of informatics Engineering RTIf 006.42 Rat i, 2015

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-37837-5112201058-abstract_id.pdf - 180 KB
  2.  ITS-Master-37837-5112201058-abstract_en.pdf - 181 KB
  3.  ITS-Master-37837-5112201058-conclusion.pdf - 350 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 34.204.200.74
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