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 hassane at 25/11/2008 17:09:40  •  5263 Views


PENGENALAN CITRA MANUSIA DENGAN FITUR-FITUR TEPI TEKSTUR DAN WARNA KULIT MENGGUNAKAN NEURAL NETWORK

HUMAN IMAGE RECOGNITION WITH EDGE TEXTURE AND SKIN COLOUR FEATURES USING NEURAL NETWORK

Author :
Sukmawati, Rias 




ABSTRAK

Suatu citra dapat terdiri dari beberapa obyek. Masingmasing obyek mempunyai ciri tersendiri. Pengenalan pada obyek-obyek dari suatu citra sangat diperlukan terutama pada sistem temu kembali citra image information retrieval. Untuk dapat mengenali obyek-obyek pada suatu citra maka hal yang dilakukan adalah dengan memecah suatu kesatuan citra atau biasa disebut segmentasi citra berdasarkan fitur tertentu kemudian dikenali ciri-ciri dasarnya dan akhirnya dapat diklasifikasikan pada obyek tertentu. Dalam Tugas Akhir ini akan dibahas suatu analisis dari beberapa fitur-fitur dalam mengklasifikasikan obyek dengan benar. Pengenalan obyek didasarkan pada fitur-fitur antara lain warna tepi dan tekstur. Pengklasifikasian obyek berdasarkan fitur-fitur tersebut akan dilakukan dengan jaringan syaraf neural network menggunakan metode backpropagation. Dari hasil uji coba terhadap jaringan syaraf yang telah terbentuk untuk mengklasifikasikan obyek maka dapat didapatkan suatu kesimpulan dari ketiga fitur tersebut mana yang memiliki nilai validitas paling baik untuk mengenali obyek manusia. Sebagai hasil dari uji coba didapatkan suatu hasil analisis bahwa dari ketiga fitur antara lain warna tepi dan tekstur maka fitur yang paling baik untuk mengklasifikasikan obyek manusia adalah fitur warna atau gabungan antara fitur warna dan tekstur. Sedangkan untuk mengklasifikasikan obyek hewan kera fitur yang paling baik adalah dari gabungan antara fitur tepi dan tekstur. Dan untuk mengklasifikasikan obyek berupa benda lain fitur yang paling baik adalah dari gabungan antara fitur warna dan fitur tepi.


ABSTRACT

An image can be consisted by some object. Each object have the separate characteristic. Recognition of object from the image very needed especially for image information retrieval. For that reason recognizing the object at one particular image the way which have been taken is breaking an image union or referred as image segmentation based on its feature then recognized by the its base marking and finally it can be classified at certain object. This Thessis will talk about the way to anaylize some features to classified object correctly. The object recognizing is based on feature such as color edge and texture. Object classification which based on the feature will be processed by neural network especially using backpropagation method. From the result of the network test that has been made to classifiying an object can be concluded which one is the best feature to representing the best validity value for recognizing object. As result from the test we have been got results that from third features for example colour edge and texture hence best features for classifiying of object for human images are colour and combination between colour and texture feature. While for classifiying of animal object for example is monkey combination between edge and texture is the best feature. And for classifiying another object best feature is combination between colour and edge.



KeywordsCitra ; Obyek Manusia ; Tepian ; Warna Kulit ; Texture ; Neural Network ; Backpropagation
 
Subject:  Jaringan Saraf Tiruan
Contributor
  1. Dr.Ir Joko Lianto B
    Darlis Heru Murti, S.Kom
Date Create: 25/11/2008
Type: Text
Format: pdf
Language: Indonesian
Identifier: ITS-Undergraduate-3100008031682
Collection ID: 3100008031682
Call Number: RSIf 006.42 Suk p


Source
Undergraduate Theses of Informatics Engineering Department, RSIf 006.42 Suk p, 2008

Coverage
ITS Community

Rights
Copyright @2008 by ITS Library. This publication is protected by copyright and permission should be obtained from the ITS Library prior to any prohibited reproduction, storage in a retrievel system, or transmission in any form or by any means, electronic, mechanical, photocopying, recording, or likewise. For information regarding permission(s), write to ITS Library




[ Download - Summary ]

ITS-Undergraduate-3100008031682-2433.pdf




 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