Translator Disclaimer
23 March 1994 Image segmentation by nonsupervised neural networks
Author Affiliations +
Proceedings Volume 2182, Image and Video Processing II; (1994)
Event: IS&T/SPIE 1994 International Symposium on Electronic Imaging: Science and Technology, 1994, San Jose, CA, United States
In this paper, we propose a nonsupervised neural network approach to an image segmentation issue. The purpose is to extract spectral lines from sonar images. A Kohonen's self-organizing map is used to approximate the probability density function of the input data in a nonlinear way. The originality of our work with regards to the Kohonen approach is that constraints due to spectral lines features (temporal continuity, high mean energy), are encoded into the network. The process consists of two steps. First, searching for each point in the image whether a spectral line goes through this point. This step is achieved using a one-dimension map which self-organizes until a stable state is reached. The second step consists in evaluating whether network topology recovers spectral lines properties. For this purpose, we define an objective function which depends on neurons mean energy and global curvature of the network seen as a topological set of units. This process enhances spectral lines perception in a noisy image and has been successfully applied to a set of lofargrams with different signal to noise ratio.
© (1994) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Jean-Claude Di Martino and Brigitte Colnet "Image segmentation by nonsupervised neural networks", Proc. SPIE 2182, Image and Video Processing II, (23 March 1994);

Back to Top