Menerapkan K-Means Clustering untuk Segmentasi Gambar Database Berwarna
Main Article Content
Abstract
Image segmentation is very important in the approach of image analysis to learn about any image. The K-means clustering technique is an algorithm widely used in image segmentation systems. This work utilizes the Lab* color space and K-means clustering to offer color-based image segmentation. This research demonstrates image segmentation of a database based on color characteristics using unsupervised K-means clustering technique implemented with MATLAB coding. The entire work is divided into two phases. Firstly, color separation augmentation from the color image database is enhanced through de-correlation stretching. Then, the six areas of the image database are clustered into three groups using the K-means clustering technique. By using the Lab* color space and K-means clustering method in the color image database, we can only show the central area of any image. We can isolate contaminated areas in medical color image databases with this approach and treat diseases quickly. We can use various approaches such as Particle swarm Optimization (PSO) for better results.
Article Details
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with FIDELITY : Jurnal Teknik Elektro agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution-ShareAlike 4.0 International License (CC BY-SA 4.0) that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work.
Jurnal FIDELITY : Jurnal Teknik Elektro is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Accepted 2020-08-16
Published 2020-09-30
References
Image Segmentation for the Purpose Of Object-Based Classification, by Ahmed Darwish 2003 IEEE, pp 2039-2041
Colour-based image segmentation using k-means clustering by Anil Z chitade published in IJEST, vol. 2,2010.
Brain tumor detection of MR images based on colour converted hybrid PSO+Kmeans clustering segmentation published in European journal of scientific research vol.70(2012).
Database image classification using k-means clustering & PSO by Madhusmita Sahu published in IJSAA journal, vol.2, May 2012.
A colour image segmentation algorithm based on region growing by Jun Tang IEEE, vol 6, 2010, pp 634-637.
Evaluation of colour image segmentation hierarchies by Darren MacDonald Proceeding of the 3rd Canadian conference on computer and Robot Vision, IEEE, 2006.
Digital image processing by R.C.Gonzalez and R. E. Woods, chapter 10, paper 567-630 2nd edition.
Image Segmentation via Adaptive K-Mean Clustering and Knowledge-Based Morphological Operations with Biomedical Applications by Chang Wen Chen, Jiebo Luo, and Kevin J. Parker, published in IEEE transaction on IMAGE PROCESSING, VOL. 7, NO. 12, DECEMBER 1998.
Neuro-Fuzzy and soft computing Textbook by jyh-shubg Roger jang, page no-450.
R. C. Gonzalez and R. E. Woods, "Digital Image Processing using MATLAB",2nd edition.