Fast color quantization using weighted sort-means clustering
JOSA A, Vol. 26, Issue 11, pp. 2434-2443 (2009)
http://dx.doi.org/10.1364/JOSAA.26.002434
Enhanced HTML 
Acrobat PDF (1763 KB)
Abstract
Color quantization is an important operation with numerous applications in graphics and image processing. Most quantization methods are essentially based on data clustering algorithms. However, despite its popularity as a general purpose clustering algorithm, K-means has not received much respect in the color quantization literature because of its high computational requirements and sensitivity to initialization. In this paper, a fast color quantization method based on K-means is presented. The method involves several modifications to the conventional (batch) K-means algorithm, including data reduction, sample weighting, and the use of the triangle inequality to speed up the nearest-neighbor search. Experiments on a diverse set of images demonstrate that, with the proposed modifications, K-means becomes very competitive with state-of-the-art color quantization methods in terms of both effectiveness and efficiency.
© 2009 Optical Society of America
OCIS Codes
(100.2000) Image processing : Digital image processing
(100.5010) Image processing : Pattern recognition
ToC Category:
Image Processing
History
Original Manuscript: April 22, 2009
Revised Manuscript: July 24, 2009
Manuscript Accepted: August 15, 2009
Published: October 27, 2009
Citation
M. Emre Celebi, "Fast color quantization using weighted sort-means clustering," J. Opt. Soc. Am. A 26, 2434-2443 (2009)
http://www.opticsinfobase.org/josaa/abstract.cfm?URI=josaa-26-11-2434
You do not have subscription access to this journal. Citation lists with outbound citation links are available to subscribers only. You may subscribe either as an OSA member, or as an authorized user of your institution.
Contact your librarian or system administrator
or
Log in to access OSA Member Subscription
You do not have subscription access to this journal. Cited by links are available to subscribers only. You may subscribe either as an OSA member, or as an authorized user of your institution.
Contact your librarian or system administrator
or
Log in to access OSA Member Subscription
You do not have subscription access to this journal. Figure files are available to subscribers only. You may subscribe either as an OSA member, or as an authorized user of your institution.
Contact your librarian or system administrator
or
Log in to access OSA Member Subscription
You do not have subscription access to this journal. Article level metrics are available to subscribers only. You may subscribe either as an OSA member, or as an authorized user of your institution.
Contact your librarian or system administrator
or
Log in to access OSA Member Subscription
Related Journal Articles 
- Developments in generalized ranked-order filters (JOSAA)
- Operating-Curve Selection for Optical and Digital Correlation of Fingerprints (AO)
- All-Digital Ring-Wedge Detector Applied to Fingerprint Recognition (AO)
- Method of Target Detection in Images by Moment Analysis of Correlation Peaks (AO)
- Image Compression by Vector Quantization with Noniterative Derivation of a Codebook: Applications to Video and Confocal Images (AO)
Related Conference Papers
- Diffraction-Limited Impulse Response Image Reconstruction with a Single Imaging Pixel
- Diffraction-Limited Impulse Response Image Reconstruction with a Single Imaging Pixel
- Recovery of Myosin Filament Positions in Muscle Electron Micrographs
- Impact of the 2D-Structured Noise in the Post-Processing of Hybrid Optical-Digital Imaging Systems
- Automatic classification of biological specimens: Diatoms
« Previous Article | Next Article »
OSA is a member of 