期刊名称：International Journal of Innovative Research in Science, Engineering and Technology
印刷版ISSN：2347-6710
电子版ISSN：2319-8753
出版年度：2017
卷号：6
期号：1
页码：1352
DOI：10.15680/IJIRSET.2017.0601153
出版社：S&S Publications
摘要：This paper describes an automatic system for segmentation and quantification of the microstructures ofwhite cast iron. Mathematical morphology algorithms are used to segment the microstructures in the input images,which are later identified and quantified by an artificial neuronal network. A new computational system was developedbecause ordinary software could not segment the microstructures of this cast iron correctly, which is composed ofcementite, pearlite and ledeburite. For validation purpose, 30 samples were analyzed. The microstructures of thematerial in analysis were adequately segmented and quantified, which did not happen when we used ordinarycommercial software. Therefore, the proposed system offers researchers, engineers, specialists and others, a valuableand competent tool for automatic and efficient microstructural analysis from images.
关键词：hypoeutectic white cast iron; image processing and analysis; mathematical morphology; artificial;neuronal network; image quantification.
