Song Geng
ABSTRACT
In this paper, a grain boundary reconstruction method of metallographical image based on active contour model and mathematical morphology is proposed. Firstly, L1 norm is introduced into CV model, which combined with local binary fitting. The normalized proportionality coefficients of global variance and local variance are used to regulate the evolution of contour curve and the curve is driven to close to the real grain boundary, the effects of precipitated phase in grain boundary on grain boundary reconstruction are reduced. Then the close operation is applied to the image and the grain boundary in the image is thinned by the Rosenfeld algorithm. As a result the grain boundary with multi-pixel width turns into the closed grain boundary with single-pixel width. Finally, the redundant branches of grain boundary are cut off by matching the given templates. The experimental results show that, compared with the existing grain boundary reconstruction methods, the reconstructed grain boundary by the proposed method is more complete and clear with a better visual effect, which is more competitive.
- Zhu Q B and Zhang T Y. 2014. Digital evaluation method and application of metallic materials grain size. Heat Treatment of Metals. 39, (Sep. 2014), 132--136.Google Scholar
- Liu S K, Wang J F, Si S G, Li J F and Han J T. 2008. Recognition and edge-extraction of grain boundary in materials' microstructure. Chinese Journal of Stereology and Image Analysis. 13, (Jun. 2008), 134--137.Google Scholar
- Li X C, Zhao C G, Zhu W X, Ma Z J, Zhuang Z P and Zhang Y. 2013. Restoring method of metallographic image of ultra-fine grain steel based on water-growing. Transactions of Materials and Heat Treatment. 34, (Sep. 2013), 69--73.Google Scholar
- Zhao X X, Jin W Y, Qi X L and Xie J T. 2013. Application of improved Canny algorithm in investigation of GCr15 bearing steel metallographic image. Hot Working Technology. 42, (Sep. 2013), 211--213.Google Scholar
- Xue W H, Wang H, Liu G Q, Feng M N, Qi L and Chen Z P. 2015. Segmentation method of grain microstructure based on similarity among image sequence. Chinese Journal of Stereology and Image Analysis. 20, (Dec. 2015), 400--407.Google Scholar
- Deng S C, Liu T G and Xiao Z X. 2010. Extraction of enclosing image edge for metallographic structure based on Canny and grayscale contour line. Optics and Precision Engineering. 18, (Oct. 2010), 2314--2323.Google Scholar
- Jiang M X and Chen G H. 2011. Restoration and reconstruction of grain boundary in metallographical image. Optics and Precision Engineering. 19, (Oct. 2011), 2541--2549.Google ScholarCross Ref
- Ullah A, Liu G, Wang H and Luan J H. 2013. Optimal approach of three-dimensional microstructure reconstructions and visualizations. Materials Express. 3, (Jun. 2013), 109--118.Google ScholarCross Ref
- T F Chan and L A Vese. 2001. Active contours without edges. IEEE Transactions on Image Processing. 10, (Feb. 2001), 266--277. Google ScholarDigital Library
- Li C M, Kao C Y Y, Gore J C and Ding Z H. 2008. Minimization of region-scalable fitting energy for image segmentation. IEEE Transactions on image processing. 17, (Oct. 2008), 1940--1949. Google ScholarDigital Library
- Zhang L X, Xu Z G, Wei S L, Ren X C and Wang M L. 2016. Grain size automatic determination for 7050 AI alloy based on a fuzzy logic method. Rare Metal Materials and Engineering. 45, (Mar. 2016), 548--554.Google ScholarCross Ref
- Tang L M, Fang Z, Xiang C C, Huang D R and Chen S Q. 2015. An improved Chan-Vese Model integrated with L1 fitting term. Journal of Computer-Aided Design & Computer Graphics. 27, (Sep. 2015), 1707--1715.Google Scholar
- Jia T M, Xun Y, Bao G J, Dong M and Yang Q H. 2013. Skeleton extraction algorithm on grapevine based on machine vision. Journal of Mechanical & Electrical Engineering. 30, (Apr. 2013), 501--504.Google Scholar
Index Terms
- Grain Boundary Reconstruction of Metallographical Image Based on Active Contour Model and Mathematical Morphology
Recommendations
A novel multiphase active contour model for inhomogeneous image segmentation
The problem of image segmentation has been investigated with a focus on inhomogeneous multiphase image segmentation. Intensity inhomogeneity is an undesired phenomenon that represents the main obstacle for magnetic resonance (MR) and natural images ...
Automatic ultrasound image segmentation based on local entropy and active contour model
AbstractIt is still a challenging task to segment ultrasound medical images automatically and accurately because of the poor quality of images. To address these problems, a two-stage automatic segmentation scheme based on local entropy and a ...
Brain tumor segmentation with radius contraction and expansion based initial contour detection for active contour model
AbstractThis paper proposes a novel brain tumor segmentation algorithm that uses Active Contour Model and Fuzzy-C-Means optimization. In Active Contour model, the initial Contour selection is a challenging task for MRI brain tumor segmentation because the ...
Comments