Characteristic extraction from an ambiguous image using fuzzy mathematical morphology with adaptive structuring elements

Fuzzy mathematical morphology (FMM) is proposed as a new method of the image processing, especially the analysis of image characteristics. FMM works with two images: the original image to be processed and a structuring element. However, the shape and value of structuring element must decide before image processing. Also, there is the problem that the image changes largely by the selection of the structuring element. In this paper, we propose a new filter to extract characteristics in an ambiguous image. First, the adaptive structuring elements (ASE) are defined. The ASE can be determined directly from the input image without any arbitrary choice, which is sensitive to ambiguous images. Next, we propose the dynamic fuzzy morphological filter (DFMF) with ASE. This method is useful for automatic inspection systems using image processing and effective to characteristics extraction. Performance evaluation via simulations shows that the DFMF efficiently extracts characteristics. Furthermore, the DFMF shows a good performance compared with the other filters