Chan-Vese Segmentation Of SEM Ferrite-Pearlite Microstructure And Prediction Of Grain Boundary
Subir Gupta, working as Assistant Professor, Department of MCA , Dr. B. C Roy Engineering College, Durgapur, West Bengal, India.
Manuscript received on 21 August 2019. | Revised Manuscript received on 09 September 2019. | Manuscript published on 30 September 2019. | PP: 3434-3437 | Volume-8 Issue-11, September 2019. | Retrieval Number: K25530981119/2019©BEIESP | DOI: 10.35940/ijitee.K2553.0981119
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: The image processing of microstructure for design, measure and control of metal processing has been emerging as a new area of research for advancement towards the development of Industry 4.0 framework. However, exact steel phase segmentation is the key challenge for phase identification and quantification in microstructure employing proper image processing tool. In this article, we report effectiveness of a region based segmentation tool, Chan-Vese in phase segmentation task from a ferrite- pearlite steel microstructure captured in scanning electron microscopy image (SEM) image. The algorithm has been applied on microstructure images and the results are discussed in light of the effectiveness of Chan-Vese algorithms on microstructure image processing and phase segmentation application. Experiments on the ferrite perlite microstructure data set covering a wide range of resolution revealed that the Chan-Vese algorithm is efficient in segmentation of phase region and predicting the grain boundary.
Keywords: Ferrite-Pearlite steel, Phase segmentation, image processing, grain boundary prediction, Chang-Vese.
Scope of the Article: Image processing