Research on image segmentation method using a structure-preserving region model-based MRF
- 136 Downloads
Abstract
This paper proposes a structure-preserving region model for machine images. Under the Bayesian framework, the proposed model is combined with MRF (Markov random field) to offer a new method for the segmentation of machine images. The structure-preserving region model aims to deal with problems with MRF-based segmentation on parameter estimation and optimization. Construction of the structure-preserving region model involves two processes. The bilateral filter algorithm is first applied to machine images to remove noise and restore image structures, followed by an initial segmentation by applying MRF on the images and represented by a region adjacency graph (RAG). The proposed segmentation method has been evaluated using machine images. Relative to existing MRF-based methods, testing results have demonstrated that our proposed method substantially improves the segmentation performance.
Keywords
Markov random field (MRF) Region adjacency graph Bilateral filter Image segmentationNotes
Acknowledgements
This research was financially supported by Excellent Young Talents Fund Program of Higher Education Institutions of Anhui Province (Grant: gxyq2017049), the Foundation of Hefei Normal University (Grant: 2015JG05).
References
- 1.Gao, R., Yang, X., Cheng, Q.I.: Study on image enhancement based on detection of steel plate surface defect. J. Henan Polytech. Univ. 6, 850–854 (2015)Google Scholar
- 2.Saati, M., Amini, J., Maboudi, M.: A method for automatic road extraction of high resolution SAR imagery. J. Indian Soc. Remote Sens. 43(4), 697–707 (2015)CrossRefGoogle Scholar
- 3.Pajor, M., Grudziński, M.: Intelligent machine tool-vision based 3D scanning system for positioning of the workpiece. Solid State Phenom. 220–221, 497–503 (2015)CrossRefGoogle Scholar
- 4.Arora, A.R., Pande, N.A.: Image processing using bilateral filtering with future scope in parellel processing. Int. J. Res. Comput. Commun. Technol. 2(12), 1470–1473 (2013)Google Scholar
- 5.Wang, Y., Zhang, J., Deng, K., et al.: An automated matching method for stereo SAR images based on geometry constraint. J. China Univ. Min. Technol. 44(1), 164–169 (2015)Google Scholar
- 6.Liu, X., Tanaka, M., Okutomi, M.: Practical signal-dependent noise parameter estimation from a single noisy image. IEEE Trans. Image Process. 23(10), 4361–4371 (2014)MathSciNetCrossRefGoogle Scholar
- 7.Hua Xie, L.E., Pierce, L.E., Ulaby, F.T.: Statistical properties of logarithmically transformed speckle. IEEE Trans. Geosci. Remote Sens. 40(3), 721–727 (2002)CrossRefGoogle Scholar
- 8.Yu, Q., Clausi, D.A.: SAR sea-ice image analysis based on iterative region growing using semantics. IEEE Trans. Geosci. Remote Sens. 45(12), 3919–3931 (2007)CrossRefGoogle Scholar
- 9.Gao, F.Z.: The simulation of the psychological impact of computer vision de-noising technology. Appl. Mech. Mater. 556–562, 5013–5016 (2014)CrossRefGoogle Scholar
- 10.Wang, D.G., Li, Y., Jin, F.L.: SAR images recognition combined bidirectional 2DPCA with KPCA. Adv. Mater. Res. 756–759, 4045–4049 (2013)CrossRefGoogle Scholar
- 11.Guerrout, E.H., Mahiou, R., Ait-Aoudia, S.: Hidden Markov random fields and swarm particles: a winning combination in image segmentation. Ieri Procedia 10, 19–24 (2014)CrossRefGoogle Scholar
- 12.Yin, W.L., Li, H.S., Zhang, H.R., et al.: Application of Markov random field in the retinal vessel segmentation. Appl. Mech. Mater. 696, 114–118 (2015)CrossRefGoogle Scholar