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 aprill@is.its.ac.id at 18/11/2015 15:33:56  •  1216 Views


METODE KOREKSI WARNA CITRA DARI KAMERA SMARTPHONE DENGAN MEMBENTUK MODEL LINEAR BERTINGKAT MENGGUNAKAN ALGORITMA REGRESI LINEAR

COLOR CORRECTION METHOD OF CAPTURED IMAGE FROM SMARTPHONE CAMERA WITH STEPWISE LINEAR MODEL USING LINEAR REGRESSION ALGORITHM

Author :
SARI, YUITA ARUM ( 5112201050 )




ABSTRAK

Warna merupakan salah satu fitur penting yang digunakan pada pengolahan citra. Hasil warna pada citra umumnya tidak sama antara yang dikeluarkan oleh layar dan yang tertangkap mata manusia. Salah satu penyebabnya adalah masalah pencahayaan sehingga diperlukan sebuah teknik koreksi warna hasil potret kamera agar sesuai dengan representasi warna pada citra referensi. Penelitian ini mengusulkan sebuah metode koreksi warna untuk memperbaiki kualitas warna citra hasil potret kamera smartphone menggunakan metode clustering sebagai pemilihan data sampel untuk membentuk model linear betingkat dengan algoritma regresi linear. Transformasi ruang warna dari RGB ke Lab dilakukan terlebih dahulu sebelum proses clustering untuk memisahkan komponen warna dari iluminasi yang direpresentasikan dengan L dan komponen warna merah-hijau a serta kuning-biru b. Penelitian ini menggunakan kombinasi regresi linear bertingkat dan color constancy untuk mendapatkan koreksi warna citra secara global tanpa tergantung dari kondisi pencahyaan. Model linear bertingkat dengan regresi linear berfungsi untuk menghilangkan pencilan pada data referensi dan data hasil potret kamera sementara color constancy digunakan untuk data yang invarian terhadap kondisi pencahayaan. Uji coba koreksi warna dilakukan pada dua jenis dataset yaitu dataset citra daun tebu dan citra buah tomat. Hasil dari koreksi warna menggunakan regresi linear bertingkat lebih baik dibandingkan dengan model tanpa bertingkat. Secara mayoritas dari hasil uji coba sistem koreksi warna dapat meningkatkan kualitas citra. Kombinasi metode regresi linear bertingkat dan color constancy Gray World SLRGW menjadi metode yang paling unggul pada hampir keseluruhan uji coba yaitu dapat meningkatkan evaluasi clustering sekitar 10 sampai 30. Hal ini membuktikan bahwa metode regresi linear dengan bertingkat lebih fleksibel dan handal mengoreksi warna pada keadaan cahaya yang tidak konsisten.


ABSTRACT

Color is one of the most important features that is commonly used in image processing. An image which is produced by different devices may have different intensities either from the component value of color space or from human eye perception. Therefore color correction technique is needed to gain the color representation between referenced image and the captured image from smartphone camera. In this research color correction method is proposed to enhance the quality of captured image from smartphone camera using clustering to create stepwise linear model with linear regression algorithm. Color transformation is utilized before clustering process and the color spaces is converted from RGB to Lab. Lab is one of color transformation which represent L as illumination component a represents red to green value and b represents yellow to blue. In order to obtain the whole correction color without depends on lighting condition so the color constancy method is combined with stepwise linear model using linear regression. Linear stepwise model is applied for removing outliers between reference data and captured data while color constancy as invariant lighting condition. The experiment in this research is applied in two kinds of dataset that are captured images of sugarcane leaf and tomatoes. Comparing to the ordinary linear regression method the average result of color correction using linear regression with stepwise model is robust for all experiments and most of them gain the quality of an image. Combined Regression linear with stepwise model and Gray Word SLRGW is the best in almost average observation in which can achieve clustering result up to 10 until 30. It is proved that linear regression with stepwise model is more flexible and robust in unconditional lighting condition.



Keywordskoreksi warna; regresi linear; clustering; transformasi warna; color constancy
 
Subject:  Pengolahan citra
Contributor
  1. Dr. Ir. R.V. Hari Ginardi, M.Sc.
  2. Dr. Eng. Nanik Suciati, S.Kom., M.Kom.
Date Create: 18/11/2015
Type: Text
Format: pdf
Language: Indonesian
Identifier: ITS-Master-51103150001552
Collection ID: 51103150001552
Call Number: RTIf 006.42 Sar m


Source
Master Theses of Informatics Engineering, RTIf 006.42 Sar m, 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-39627-5112201050-abstract_id.pdf - 254 KB
  2.  ITS-Master-39627-5112201050-abstract_en.pdf - 239 KB
  3.  ITS-Master-39627-5112201050-conclusion.pdf - 478 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 34.204.175.38
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