Journal of Siberian Federal University. Engineering & Technologies / Segmentation Object Strategy on Digital Image

Full text (.pdf)
Issue
Journal of Siberian Federal University. Engineering & Technologies. 2018 11 (2)
Authors
Perfil`ev, Dmitry A.
Contact information
Perfil`ev, Dmitry A.: Siberian Federal University 79 Svobodny, Krasnoyarsk, 660041, Russia;
Keywords
segmentation properties; the rule of segmentation; segmentation strategy; metallographic
Abstract

The article presents peculiarities of segmentation of the object on the digital image of the macrostructure. Analyzed the mathematical formulation of the tasks segmentation and its application in various conditions. The considered basic drawbacks of segmentation based on the iconic signs of the image elements. The proposed segmentation strategy properties of the object in the image based on ascending and descending processes of formation of segmentation rules. Based on the evaluation of the homogeneity of the formed rule segmentation of the image representing object properties. As an example of application of the segmentation strategy used test microstructures image wrought aluminum alloy AMg6. The syntax of images allowed applying possible strategies in the absence of random noise. The results of the experiments with regulation of segmentation showed the following: • the highlighted part of the image representing cracks in macrostructure; • changing the uniformity may be traced in the growth of the cracks in macrostructure, it is possible to follow the dynamics of its immediate context

Pages
213-220
Paper at repository of SibFU
https://elib.sfu-kras.ru/handle/2311/70963

Creative Commons License This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License (CC BY-NC 4.0).