Summary
International Symposium on Nonlinear Theory and its Applications
2009
Session Number:B4L-B
Session:
Number:B4L-B2
Dynamic Image Segmentation System for Ultrasonic B-mode Image Based on its Multi-Scaled Feature Maps
Ken’ichi Fujimoto, Mio Musashi, Tetsuya Yoshinaga,
pp.-
Publication Date:2009/10/18
Online ISSN:2188-5079
DOI:10.34385/proc.43.B4L-B2
PDF download (275.2KB)
Summary:
We have developed a dynamic image segmentation system for a gray-level image. It consists of a multi-scaling system and a discrete-time coupled system of chaotic neurons. Since an ultrasonic B-mode image, which is a gray-level image, generally has speckle noise, ordinary our system does not work well for such an image. This paper describes improvement of ordinary our system based on feature maps of an ultrasonic B-mode image. We showed a result of dynamic image segmentation performed for an ultrasonic B-mode image using an improved system.