A Cumulative Sums Algorithm for Segmentation of Digital X-ray Images
A mathematical model of digital X-ray image of the test object is presented for the case when the main type of image distortion is the noise due to the quantum nature of the radiation. The new multilevel cumulative sums algorithm for automatic image segmentation is proposed. The algorithm is based on the edge detection of the segments homogeneous in brightness along the image rows and columns by repeatedly applying the cumulative sums procedure. The efficiency of the proposed algorithm is compared with the known threshold and Leader algorithms. The comparison was performed on simulated images as well as on the X-ray image of a weld. The mean square errors for the new algorithm were about two and three times less than for the threshold and Leader algorithms, correspondingly.
KeywordsInspected object Mathematical model Digital X-ray image Segmentation algorithms
The research is carried out at Tomsk Polytechnic University within the frameworks of Tomsk Polytechnic University Competitiveness Enhancement Program Grant and Tomsk State University Competitiveness Enhancement Program Grant. This study was partly supported by The Ministry of Education and Science of the Russian Federation, Goszadanie No 2.3208.2017/4.6.
- 6.Shubochkin A.E.: Development of methods and means of Eddy current and magnetic inspection of metal rolling for an estimation of its residual resource. In: Abstract of the Dissertation of Doctor of Technical Science, Moscow (2014) (in Russian) Google Scholar
- 8.Zakharov A.V., Kol’tsov P.P., Kotovich N.V., Kravchenko A.A., Kutsaev A.S., Osipov A.S.: Criteria for assessing the quality of segmentation of images. In: Proceedings of the Research Institute for System Studies of the Russian Academy of Sciences, 2(2), pp. 87–99 (2012) (in Russian) Google Scholar
- 11.Samoilenko, D.E.: Structural image segmentation. Artif. Intell. 4, 521–528 (2004)Google Scholar
- 13.Ogorodnikov S.A.: Recognition of materials during radiation customs control based on a linear electron accelerator. The Dissertation of the Candidate of Technical Sciences: 01.04.20, St. Petersburg. (2002) (in Russian) Google Scholar
- 18.Overview of K-Means Clustering: Web-page by Prof. Miriam Leeser. http://www.ece.neu.edu/groups/rpl/kmeans/
- 19.Pisarevski, A.N., Chernjavski, A.F., Afanaciev, G.K.: Systems of Technical Vision (Fundamental Principles, Hardware and Software). Mashinostroenie. Leningr. Branch, St. Petersburg (1988). (in Russian) Google Scholar
- 20.Haralick, R.M., Shapiro, L.G.: Computer and Robot Vision. Addison-Wesley Longman Publishing. Co., Inc., Boston (1992)Google Scholar
- 24.Levashkina, A.O., Porshnev, S.V.: Survey of supervisory criteria for assessing the quality of image segmentation. Proc. Tomsk Polytech. Univ. 313(5), 28–33 (2008)Google Scholar