Physics-based model of the Kohonen ring
Petia I. Radeva, Jordi Guerrero, M.C. Molina, R. Serneels · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · 1998
In this paper, we introduce a new segmentation technique (called Kohonen snake) based on the neural simulation of deformable models designed to reconstruct 3D objects. Kohonen snake possesses all properties of Kohonen networks (lateral interaction during the learning process, topologically preserving mapping) and of deformable models (namely, elastic properties). Elastic properties of the physics-based Kohonen ring improves the shortcomings of the Kohonen network related to twisting, `dead' neurons, accumulation and rounding the network, whereas the data- driven approach of Kohonen snake improves the problem of initialization and local minima of the snakes. When integrating both models, the first question is how to combine their parameters. We simulate the Kohonen snake behavior with different parameter values using sequential and parallel weight updating, study the need of decreasing the parameters and of reordering image features. As a result, we conclude that Kohonen snake has better control on its shape that makes it less dependent on the values of its parameters and initial conditions. Our tests on segmentation of synthetic and real images illustrate the usefulness of the Kohonen snake technique.