Adaptive morphological multiresolution decomposition
Year: 1991
Type: conference-paper
Abstract: This paper deals with size-sensitive multiresolution decomposition using adaptive morphological filters with a flat structuring element. This type of decomposition generates a set of images, each containing elements of the original image with a specific size. The authors propose to extract a set of dominant shapes contained in the original image and to assess the size of a particular element by comparison with this set of dominant shapes. This approach is particularly suitable for texture images where dominant shapes are actually present. In a first step, it is shown how a flat structuring element of a morphological filter can be adapted to optimize a statistical criterion such as the mean square error. The approach is suitable for any morphological filters and the proposed algorithms are simple. Moreover, they can be easily modified to achieve a size-constrained optimization of the structuring element, which is an attractive solution for the extraction of dominant shapes. Finally,adaptive morphological filters are used in a multiresolution decomposition scheme which sorts the various components as a function of their size while taking into account the presence of dominant shapes. Two particular applications are presented. They address the problems of noise removal and texture defect detection.
DOI: 10.1117/12.49883
Authors: Philippe Salembier, Laurent Jaquenoud
Institution: ETH Zurich
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W2075251950
