Abstract
The recognitions of phases and precise grain boundaries based on metallographic images are useful for conducting micromechanical simulations, such as finite element analysis and peridynamics. In this work, those processes are automatized by using a Sobel operator for identifying edges, which is normalized by different proposed Gaussian filters (on intensity, rugosity, or both). After that, a threshold is used to discretize the edges. Different neighboring pixel configurations, sensitive to edge intensity, are proposed for thinning and cleaning the discretized edges, and hence, grain boundaries with a one-pixel thickness are obtained. Then, the phase is selected by averaging color of each delimited grain. Finally, the precision on the phase recognition was found to increase from 75.61 to 83.6% for the unmodified and the normalized Sobel operator, respectively.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
