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 Elektro - Telematika S2
Posted by dee@its.ac.id at 24/12/2014 23:08:47  •  2546 Views


PENENTUAN KUALITAS KESEGARAN IKAN DENGAN CITRA MATA MENGGUNAKAN METODE SUPPORT VECTOR MACHINE

DETERMINATION OF IMAGE QUALITY FRESHNESS WITH FISH EYE USING SUPPORT VECTOR MACHINE

Author :
ARHAM ( 2212206708 )




ABSTRAK

Selama ini para nelayan dan produsen ikan di Kabupaten Sinjai melakukan identifikasi kesegaran ikan secara manual menggunakan pengamatan kasat mata. Bagaimanapun juga pemilihan ikan-ikan tersebut akan membutuhkan waktu yang lama apalagi dalam jumlah yang sangat banyak sehingga diperlukan sistem yang dapat mendeteksi kesegaran ikan secara otomatis. Sistem deteksi yang dibangun memerlukan sebuah model komputasi untuk mengubah piksel citra mata ikan menjadi suatu ciri mata yang menunjukkan tingkat kesegaran ikan melalui proses pra pengolahan ekstraksi ciri dan proses klasifikasi menggunakan Support Vector Machine. Untuk perbandingan vektor input dievaluasi dengan sistem jaringan saraf tiruan model Backpropagation Neural Network. Data pelatihan yang diberikan berupa fitur citra digital mata ikan dengan kualitas ikan baik sedang dan jelekbusuk. Setelah proses ekstraksi ciri dengan menggunakan metode Statistika Tekstur dari Histogram Warna ciri-ciri yang terpilih digunakan untuk proses klasifikasi kualitas kesegaran ikan. Dari hasil percobaan terhadap 90 data citra mata ikan didapatkan hasil akurasi untuk metode SVM one against one yaitu ikan dengan kualitas segar 86.6 ikan dengan kualitas sedang 81.1 dan ikan dengan kualitas jelek 81.1. SVM one against all didapatkan tingkat akurasi ikan segar 92.2 Ikan sedang 82.2 dan ikan jelekbusuk 82.2. Sedangkan Backpropagation Neural Network didapatkan tingkat akurasi ikan segar 54.4 ikan kualitas sedang 54.4 dan ikan jelekbusuk 74.4 sehingga dapat disimpulkan bahwa klasifikasi menggunakan support vector machine metode one against all memiliki keunggulan dalam tingkat akurasi dibandingkan dengan metode SVM one against one dan Backpropagation Neural Network


ABSTRACT

During this time the fishermen and fish producers in Sinjai identifying fish freshness manually using visible observations. However the selection of these fish will take a long time especially in very much so it requires a system that can automatically detect the freshness of the fish. Detection system that is built requires a computational model to change the fish eye image pixels into a feature eyes that show the freshness of the fish through the process of pre-processing feature extraction and classification process using Support Vector Machine. For comparison the input vector system was evaluated with an artificial neural network model of backackpropagation. Given training data in the form of a digital image features eyelets with fish quality is good moderate and bad rotten. After the process of feature extraction using the method of Histogram Statistics Texture Colour selected traits that are used for the classification process quality fish freshness From the experimental results of the 90 fish eye image data obtained accuracy results for SVM one against one method that fish with fresh quality 86.6 with the quality of the fish and the fish was 81.1 with 81.1 poor quality. SVM one against all available fresh fish accuracy rate 92.2 82.2 fish and fish being badrotten 82.2. While Backpropagation Neural Network obtained an accuracy rate of 54.4 of fresh fish quality fish and fish was 54.4 badrotten 74.4 so it can be concluded that the classification using a support vector machine one against all method has advantages in accuracy rate compared to the one against one SVM method and backpropagation neural network.



KeywordsSistem Deteksi; Citra digital; Statistika Tekstur; Support Vector machine; Kesegaran ikan
 
Subject:  Metode grafis
Contributor
  1. Prof. DR. Ir. Mauridhi Hery P, M. Eng
  2. DR. I Ketut Eddy Purnama, ST., MT
Date Create: 20/01/2014
Type: Text
Format: pdf
Language: Indonesian
Identifier: ITS-Master-22103140000863
Collection ID: 22103140000863
Call Number: RTE 006.42 Arh p


Source
Master Thesis of Electrical Engineering, RTE 006.42 Arh p, 2014

Coverage
ITS Community

Rights
Copyright @2014 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-35106-2212206708-abstract_id.pdf - 198 KB
  2.  ITS-Master-35106-2212206708-abstract_en.pdf - 180 KB
  3.  ITS-Master-35106-2212206708-conclusion.pdf - 178 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 34.229.113.106
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