CT image segmentation by self-organizing learning
In this paper we approach the segmentation of tibia CT images using a self-organizing feature map. This type of Artificial Neural Network carries out a competitive learning process which permits the discrimination of different structures found in the images with sensitivity to changes in the distribution and value of the gray levels of the pixels. The results obtained show that this technique is adequate for the segmentation of images with complex structures and a low signal/noise ratio.
Unable to display preview. Download preview PDF.
- .Canny, J.F.: A computational approach to edge detection. IEEE Trans. Patt. Anal. Machine Intell., vol. PAMI-8, 679–698, Nov., 1986.Google Scholar
- .Kohonen, T.: Self-Organized Formation of Topologically Correct Feature Maps. Biological Cybernetics, 43, 59–62, 1982.Google Scholar
- .Pratt, W.K.: Digital Image Processing. Jhon Wiley & Sons, Inc. New York, 1991.Google Scholar
- .Silverman, R.H.: Segmentation of Ultrasonic Images with neural networks. International Journal of Pattern Recognition and Artificial Intelligence, vol. 5, n.4, 619–628, 1991.Google Scholar
- .Springub, A.; D. Scheppelmann and H. Meinzer: Segmentation of multisignal images with kohonens selfleaming topological map. In Computer Analysis of Images and Patterns (R. Klette, ed.) Research in Informatics, Vol. 5, 148–152. Akademie Verlag, Berlin, 1991.Google Scholar