Proceeding of International Conference
Akira Takeuchi, Tetsushi Ueta, Kenji Terada, An Improvement of Image Segmentation by using Fractal Coding, Proceedings of the Nonlinear Theory and Its Applications(NOLTA'99), Vol.1, 347-350, Hawaii, USA, Dec. 1999.
Abstract: This paper presents improvements for conventional image segmentation algorithm by using fractal coding. The compressed data with fractal coding is a set of parameters of affine mapping. This algorithm utilizes this compressed data to split an original image into some segments which have different feature. Image segmentation can be achieved by calculation for basins of attractions in the dynamical system computing the inverse affine mapping. The higher quality segmentation image can be obtained by adding a small perturbation to inverse affine mappings. This note describes the proposed method and shows some segmentat8oin results by using this algorithm.