ABSTRACT
Some medical images such as blood vessels or nerve canal are very narrow, it is hardly segmented. In this paper, we propose a two-dimensional image segmentation algorithm combining K-means clustering, Gabor filter and moving mesh method. The mesh is moved adaptively concentrated in steep region and the location feature is added to our clustering algorithm. Moreover, the image feature values are obtained by the convolution operation between the image and Gabor filter. The advantage of this approach is that the segmentation result of the K-means clustering algorithm can be improved by constantly adding new features such as location, pixel or Gabor filter. The experiments indicate that our algorithms can quickly segment medical and crack images without compromising the quality of the results. The results demonstrated that the proposed method achieved precision 94.31%, recall 97.84%, F1 score 95.96%.
Disclosure statement
No potential conflict of interest was reported by the author(s).
Additional information
Funding
Notes on contributors
Hongjian Shi
Prof. Hongjian Shi received his MASc and PhD in Electrical and Computer Engineering from The University of British Columbia and University of Louisville respectively. He also received his BSc, MSc and PhD in Mathematics from Henan Normal University, Peking University, and Simon Fraser University respectively. He was a full research professor at Southern University of Science and Technology before joining UIC.
Wan-Lung Lee
Dr. Wan-Lung Lee received his PhD in Department of Mathematics from Hong Kong Baptist University. His research interests include image segmentation.