Paper Details: Downloads: 771
Serial Number: P1151142873
Title: Color Image Segmentation based on the optimal multilevel thresholding technique
Authors: Rafika Harrabi and Ezzeddine Ben Braiek
Abstract: Automatic thresholding has been widely used in the domain of image processing for automated segmentation images. A commonly used thresholding technique, the Otsu method, provides satisfactory results for thresholding an image with a histogram of bimodal distribution, but they are impractical when extended to multilevel thresholding. In this paper, a new automatic thresholding method to color image segmentation called the TSMO (Two-Stage Multi-level Thresholding) is studied. We revised the Otsu method for selecting optimal threshold values for both unimodal and bimodal distributions, and tested the performance of the revised method, on the color images segmentation. This algorithm is iterative and outperforms Otsu’s method by greatly reducing the iterations required for computing the between-class variance in an image. The experimental results for synthetic and biomedical color images demonstrate the success of the proposed method, compared to many existing methods.
Keywords: Thresholding, Otsu method, two stage multi-threshold, segmentation, color image, space color.
Journal/Conference: International Journal of Graphics, Vision and Image Processing
Volume: 12
Issue: 1
Submission Date: 10/15/2011 12:00:00 AM
Review Date: 11/9/2011 12:00:00 AM
Publishing Date: 1/29/2012 12:05:47 PM
Article Downloads: 771
Download:

Facebook