A segmentation method of texture image by using pyramid linking and neural networks

Author

Zhang, Jing ; Oe, Shun´ichiro

Author_Institution

Inf. Sci. & Intelligent Syst., Tokushima Univ., Japan

fYear

1997

fDate

29-31 Jul 1997

Firstpage

1267

Lastpage

1272

Abstract

We introduce a segmentation method by using pyramid linking with band-pass neural networks. This approach is applied to segment an image composed of some types of texture to several homogeneous areas. The texture properties of the image are extracted by using a two-dimensional autoregressive method and fractal dimension, and then feature vector pyramids are built of reduced-resolution versions of these arrays. By using band-pass neural networks, the pyramid node linking process is applied. The resulting trees define the segmentation of the original image. The validity of this method is verified by several numerical examples

Keywords

fractals; image resolution; image segmentation; image texture; multilayer perceptrons; 2D autoregressive method; band-pass neural networks; feature vector pyramids; fractal dimension; image segmentation; multilayer neural networks; pyramid linking; texture image; two-dimensional autoregressive method; Data mining; Fractals; Image analysis; Image processing; Image segmentation; Image texture analysis; Information science; Intelligent systems; Joining processes; Neural networks;

fLanguage

English

Publisher

ieee

Conference_Titel

SICE '97. Proceedings of the 36th SICE Annual Conference. International Session Papers

Conference_Location

Tokushima

Type

conf

DOI

10.1109/SICE.1997.625004

Filename

625004