Image feature extraction and segmentation using fractal dimension

Author

Liu, Yuxin ; Li, Yanda

Author_Institution

Dept. of Autom., Tsinghua Univ., Beijing, China

fYear

1997

fDate

9-12 Sep 1997

Firstpage

975

Abstract

After several existing approaches of fractal dimension estimation for image analysis have been introduced, two new approaches are proposed: wavelet energy fractal dimension and morphological fractal dimension. Then we try to obtain variable fractal dimensions of general images such as Lenna instead of typical texture images as done before. Experimental results demonstrate that using different fractal dimension estimation approaches, different instinctive self-similar properties of one image can be achieved, so that they can be used for image feature extraction and segmentation

Keywords

estimation theory; feature extraction; fractals; image segmentation; mathematical morphology; Lenna image; fractal dimension estimation; image analysis; image feature extraction; morphological fractal dimension; segmentation; self-similar properties; variable fractal dimensions; wavelet energy fractal dimension; Feature extraction; Fractals; Image motion analysis; Image segmentation; Image texture analysis; Linear regression; Motion estimation; Rough surfaces; Surface morphology; Surface roughness;

fLanguage

English

Publisher

ieee

Conference_Titel

Information, Communications and Signal Processing, 1997. ICICS., Proceedings of 1997 International Conference on

Print_ISBN

0-7803-3676-3

Type

conf

DOI

10.1109/ICICS.1997.652125

Filename

652125