Application of Fuzzy Mathematical Morphology with Adaptive Structuring Elements to Seal Defect Testing
Takuo Kikuchi* and Shuta Murakami**
*Department Of Electronic Technology, Institute of Tokyo, Polytechnic University, 2-32-1, Ogawa-nishimachi, Kodaira, Tokyo, 187-0035 Japan
**Department Of EECE, Faculty of Engineering, Kyushu Institute of Technology, 1-1, Sensui-cho, Tobata, Kitakyushu, Fukuoka, 804-8550 Japan
Fuzzy mathematical morphology has been proposed as a new method of image processing, especially in the analysis of features from an ambiguous image. Fuzzy morphological operators work with 2 images: an original image to be processed and a structuring element. Generally, we must decide on the shape and value of the structuring element before applying fuzzy morphology. A problem arises when the applied image changes largely by the selection of the structuring element, so it is difficult to apply fuzzy morphological operators to inspection for defect testing. In this paper, we propose a new structuring element for fuzzy morphology, called an adaptive structuring element. The adaptive structuring element determines shapes and values of structuring elements dynamically from an input image by searching for the local features in the image. Consequently, the adaptive structuring element is sensitive to ambiguous images, useful for automatic inspection using fuzzy morphology, and effective for extraction. Performance evaluations via simulations show that the adaptive structuring element efficiently extracts features from an ambiguous image. The adaptive structuring element also shows a higher performance in package defect testing than other filters. We attained experimental results (more than 95.5%) by applying the adaptive structuring element to seal defect testing.