Normalized RGB Color Space untuk Segmentasi Citra Google Earth

Authors

  • Inggih Permana Universitas Islam Negeri Sultan Syarif Kasim Riau
  • Ismail Marzuki Universitas Islam Negeri Sultan Syarif Kasim Riau
  • Detha Yurisna Universitas Islam Indragiri

Abstract

Model warna RGB merupakan model warna yang paling sering ditemui dalam pengolah citra (Image Processing/ computer graphic). Model warna ini disebut juga sebagai model warna adaptif karena mengandung 3 komponen warna dasar, yaitu warna Red, Green, dan Blue, untuk membentuk warna-warna lainnya. Dalam segmentasi citra yang merupakan salah satu area terpenting dalam image processing yang sering sekali menjadikan warna sebagai output untuk mereprsentasikan hasil segmentasi. Hal tersebut juga dilakukan pada penelitian ini yang memanfaatkan Normalized RGB Color Space untuk melakukan segmentasi sebaran lahan hijau di Kota Pekanbaru dengan memanfaatkan citra Google Earth.Warna dasar RGB yang digunakan untuk melakukan segmentasi adalah hijau yang terbukti mampu mensegementasi sebaran lahan hijau dan yang bukan lahan hijau.

Author Biographies

Inggih Permana, Universitas Islam Negeri Sultan Syarif Kasim Riau

RGB color model was the most frequently color model encountered in image processing
(computer graphics). It was also known as adaptive color model because it contained three primary color
components: Red, Green, and Blue to obtain the other colors. In image segmentation, which was one of
the most important areas in image processing, colorswere often used to represent the results of
segmentation output. This condition was also used in this research which utilized RGB color space to
segment the distribution of green land in Pekanbaru city by using Google Earth imagery. RGB primary
color that used to perform segmentation was proven to segment green land distribution and not green
land.
Keywords: Google Earth Imagery, Image Processing, Normalized RGB Color Space, Segmentation

Ismail Marzuki, Universitas Islam Negeri Sultan Syarif Kasim Riau

RGB color model was the most frequently color model encountered in image processing
(computer graphics). It was also known as adaptive color model because it contained three primary color
components: Red, Green, and Blue to obtain the other colors. In image segmentation, which was one of
the most important areas in image processing, colorswere often used to represent the results of
segmentation output. This condition was also used in this research which utilized RGB color space to
segment the distribution of green land in Pekanbaru city by using Google Earth imagery. RGB primary
color that used to perform segmentation was proven to segment green land distribution and not green
land.
Keywords: Google Earth Imagery, Image Processing, Normalized RGB Color Space, Segmentation

Detha Yurisna, Universitas Islam Indragiri

RGB color model was the most frequently color model encountered in image processing
(computer graphics). It was also known as adaptive color model because it contained three primary color
components: Red, Green, and Blue to obtain the other colors. In image segmentation, which was one of
the most important areas in image processing, colorswere often used to represent the results of
segmentation output. This condition was also used in this research which utilized RGB color space to
segment the distribution of green land in Pekanbaru city by using Google Earth imagery. RGB primary
color that used to perform segmentation was proven to segment green land distribution and not green
land.
Keywords: Google Earth Imagery, Image Processing, Normalized RGB Color Space, Segmentation

References

Plataniotis. K.N, Venetsanopoulos. A.N. Color Image Processing and Application. Springer-Verlag,

Berlin Heidelberg NewYork, London Paris Tokyo, Hong Kong Barcelona, Budapest; 2000.

Park. Jae Byung. Efficient Color Representation for Image Segmentation under Non-white

Illumination. School of Electrical and Computer Engineering, Purdue University, West Lafayette, IN.

, U.S.A. 2003.

K. Sobottka, I. Pitas. Segmentation and Tracking of Faces in Color Images. Proceedings of

Automatic Face and Gesture Recognition. 1996; pp. 236-241.

S. Feyrer, A. Zell. Detection, Tracking, and Pursuit of Humans with an Autonomous Mobile Robot.

Proceedings of IEEE/ RSJ International Conference on Intelligent Robots and Systems. 1999;pp.

-869.

J. Yang, A. Waibel. A Real-time Face Tracker. Proceedings of IEEE Workshop on Applications of

ComputerVision. 1996;pp. 142-147.

Vezhnevets. Vladimir, Sazonov. Vassili, Andreeva. Alla. A Survey on Pixel-Based Skin Color

Detection Techniques. Proceedings Graphicon, Moscow, Rusia. 2003; pp. 85-92.

Soetedjo. Aryuanto, Yamada. Koichi.Skin Color Segmentation Using Coarse-To-Fine Region on

Normalized RGB Chromaticity Diagram for Face Detection. The Institute of Electronics, Information

and Communication Engineers (IEIC TRANS. INF. & SYST). 2008; Vol.E91-D, No.10.

Soetedjo. Aryuanto, Somawirata. Komang, Limpraptono. F. Yudi.A New Color Segmentation Method

Based on Normalized RGB Chromaticity Diagram. Seminar on Intelligent Technology and Its

Applications. 2009; ISSN 2085 – 9732.

Soetedjo. Aryuanto, Yamada. Koichi. Limpraptono. F. Yudi. Segmentation of Road Guidance Sign

Symbols and Characters based on Normalized RGB ChromaticityDiagram. International Journal of

Computer Applications; 2010, Volume 3 No.3, pp. 0975 – 8887.

Son. Hyojoo, Kim. Changmin, Kim. Changwan. Comparative Study on Color Model-Based Concrete

Image Retrieval in Different InvariantColor Spaces.27th International Symposium on Automation and

Robotics in Construction (ISARC). 2010.

S. Ravindra, Hegadi, Sangolli. Rajeshwari K. Segmentation of Google Map Images Based on Color

Features.Proceedings of International Conference on “Communication, Computation, Management &

Nanotechnology” (ICN-2011). 2011.

Moreno. F, Andrade-Cetto. J, dan Sanfeliu.A Localization of Human Faces Fusing Color

Segmentation and Depth from Stereo. Proceedings of the 8th IEEE InternationalConference on

Emerging Technologies and Factory Automation, Antibes, France; 2001, pp. 527-535.

Downloads

Published

2012-10-03

Issue

2012: SNTIKI 4

Section

Information Technology