Premium
Automatic description of microstructures
Author(s) -
Gallerneault C. E.,
Kulick J.,
Powley G.
Publication year - 1986
Publication title -
journal of microscopy
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.569
H-Index - 111
eISSN - 1365-2818
pISSN - 0022-2720
DOI - 10.1111/j.1365-2818.1986.tb02796.x
Subject(s) - preprocessor , computer science , segmentation , terminology , texture (cosmology) , artificial intelligence , pattern recognition (psychology) , image processing , image (mathematics) , computer vision , philosophy , linguistics
SUMMARY This is the third in a series of three papers concerned with developing automatic analysis and classification techniques for metallographic images (specifically binary eutectic alloys of aluminium). The goal of the developmental work was to capture and describe image structure, in the descriptive terminology of a metallographer, and to permit quantification of formerly descriptive parameters. The first paper dealt with the preprocessing stage of image analysis and entailed a study of two segmentation techniques. The second paper reported on work demonstrating the use of texture analysis to characterize structural aspects in images of metallic microstructures. In this paper the textural primatives, or phase particles, are subjected to shape analysis and a novel mechanism for within class characterization. The study of the distribution of these shapes may provide a new means of following the effects of mechanical processing.