Open Access Subscription Access
Open Access Subscription Access
Graph Based User Interacted Medical Image Segmentation with Multi Threshold Using K-means Clustering
A combination of Graph cut technique efficiently used to solve a wide variety of low-level computer vision problems, such as image smoothing and k-means clustering with multi threshold for medical image segmentation is presented. The main objective of medical image segmentation is to extract the anatomic structures and its characteristics with respect to some input features. There exist various methodologies for medical image segmentation but struggles with missing features due to the noise presence in the medical images. In propose a new technique to increase the resolution of the medical images to identify the features and edges of the medical images. The medical image is preprocessed to reduce the noise, and then multi level histogram is generated in the first phase of the process. In the second stage, with the initial segmentation obtained with gray level contours, and generate the histogram then the construct the pixel adjacency graph in which each nodes represents the set of pixels of the image and edges links the neighbor pixels. A calculate the similarity of neighboring pixels; based on the distance value, cluster the similar pixels to a class. In use k-means clustering to group similar pixels and used Euclidean distance measure to calculate the similarity between pixels. The proposed method is carried out iteratively until the user gets satisfied. The method will be carried out repeatedly with the user defined threshold value. The threshold is used to group pixels with in the distance. With the proposed technique the features are maintained and the resolution of the image enhanced. The time complexity of the process is reduced. Index Terms:K-means clustering, User Interacted Medical image Segmentation, Threshold based segmentation, Weight Map, histogram, edge detection.
K-means Clustering, User Interacted Medical Image Segmentation, Threshold Based Segmentation, Weight Map, Histogram, Edge Detection
- Alvarez L., Lion P. L., and Morel J. M., “Image Selective Smoothing and Edge Detection by Non Linear Diffusion,” SIAM Journal, vol. 29, no. 3, pp. 845-866, 1992.
- Chowdhury M. I. and Robinson J. A., “Improving Image Segmentation Using Edge Information,” in Proceedings of the 1st IEEE Conference on Electrical and Computer Engineering, Halifax,Canada, vol.1, pp. 312-316, 2000.
- Gary R. M. and Linde Y., “Vector Quantizers and Predicative Quantizers for Gauss-Markov Sources,” IEEE Transactions on Communication, vol. 30, no. 2, pp. 381-389, 1982.
- Salman N. and Liu C. Q., “Image Segmentation and Edge Detection Based on Watershed Techniques,” International Journal of Computers and Applications, vol. 25, no. 4, pp. 258-263, 2003.
- Tang H., Wu E. X., Ma Q. Y., Gallagher D., Perera G. M., and Zhuang T., “MRI Brain Image Segmentation by Multi-Resolution Edge Detection and Region Selection,” Computerized Medical Imaging and Graphics, vol. 24, no. 6, pp. 349-357, 2000.
- Thrasyvoulos N. P., “An Adaptive Clustering Algorithm for Image Segmentation,” IEEE Transaction on Signal Processing, vol. 40, no. 4,pp. 901-914, 1992.  Tou J. T. and Gonzalez R. C., Pattern Recognition Principles, Addison Wesley, USA, pp. 75-97, 1974.
- Vincent L. and Soille P. “Watershed in Digital Space: An Efficient Algorithm Based on Immersion Simulations,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 13, no. 6, pp. 583-593, 1991.
- Yan M. X. H. and Karp J. S., “Segmentation of 3D Brain MR Using an Adaptive K-means Clustering Algorithm,” in Proceedings of the 4th IEEE Conference on Nuclear Science Symposium and Medical Imaging, San Francisco, USA, vol.4., pp. 1529-1533, 1995.
- Yu Y. and Wang J., “Image Segmentation Based on Region Growing and Edge Detection,” in Proceedings of the 6th IEEE International Conference on Systems, Man and Cybernetics, Tokyo, vol.6., pp. 798-803, 1999.
Abstract Views: 478
PDF Views: 2