Application of Majorization-Minimization Method to Chan --- Vese Algorithm in the Image Segmentation Problem

The purpose of the study was to modify Chan --- Vese algorithm in order to overcome its shortcomings, such as high computational complexity and the use of approximations. In the considered modification, optimization is carried out by the majorization-minimization method, the main idea of which is to reduce the complexity of the problem using the majority function. Due to the proposed optimization method, it is possible to use the Heaviside step function and Dirac delta function. This enabled the same or better saturation levels when optimization is done by the graph cut method in a smaller number of iterations, which reduced the operation time. The proposed algorithm was tested on a Caltech101 dataset. The algorithm is general, does not depend on the subject area and does not require prior training. This allows it to be used as the basis for a wide range of image segmentation algorithms

References

[1] Chan T.F., Vese L.A. Active contours without edges. IEEE Trans. Image Process., 2001, vol. 2, no. 10, pp. 266--277. DOI: 10.1109/83.902291

[2] Hunter D., Lange K. Quantile regression via an MM algorithm. J. Comput. Sc., 2000, vol. 9, no. 1, pp. 60--77. DOI: 10.2307/1390613

[3] Sonka M., Hlavac R.B.V. Image processing, analysis and machine vision. Thomson Learning, 2007.

[4] Engel K. Real-time volume graphics. AK Peters, 2006.

[5] Canny J. A computational approach to edge detection. IEEE Trans. Pattern Anal. Mach. Intell., 1986, vol. 8, no. 6, pp. 679--698. DOI: 10.1109/TPAMI.1986.4767851

[6] Chen L. The lambda-connected segmentation and the optimal algorithm for split-and-merge segmentation. Chinese J. Computers, 1991, vol. 14, no. 5, pp. 321--331.

[7] MacQueen J. Some methods for classification and analysis of multivariate observations. Proc. 5th Berkeley Symp. Mathematical Statistics and Probability, 1967, pp. 281--297.

[8] Zhang Y., Brady M., Smith S. Segmentation of brain MR images through a hidden Markov random field model and the expectation-maximization algorithm. IEEE Trans. Med. Imag., 2001, vol. 20, no. 1, pp. 45--57. DOI: 10.1109/42.906424

[9] Boykov Y., Kolmogorov V. An experimental comparison of min-cut/max-flow algorithms for energy minimization in vision. IEEE Trans. Pattern Anal. Mach. Intell., 2004, vol. 26, no. 9, pp. 1124--1137. DOI: 10.1109/TPAMI.2004.60

[10] Wang X., Guo L., Yin J., et al. Narrowband Chan --- Vese model of sonar image segmentation: an adaptive ladder initialization approach. Appl. Acoust., 2016, vol. 113, pp. 238--254. DOI: 10.1016/j.apacoust.2016.06.028

[11] Abdelsamea M.M., Gnecco G., Gaber M.M. A SOM-based Chan --- Vese model for unsupervised image segmentation. Soft Comput., 2017, vol. 21, no. 8, pp. 2047--2067. DOI: 10.1007/s00500-015-1906-z

[12] Chai T.Y., Goi B.M., Tay Y.H., et al. Local Chan --- Vese segmentation for non-ideal visible wavelength iris images. TAAI, 2015. DOI: 10.1109/TAAI.2015.7407059

[13] Barbosa D., Dietenbeck T., Schaerer J., et al. B-spline explicit active surfaces: an efficient framework for real-time 3-D region-based segmentation. IEEE Trans. Image Process., 2012, vol. 21, no. 1, pp. 241--251. DOI: 10.1109/TIP.2011.2161484

[14] Zhao Y., Karypis G. Criterion functions for document clustering: experiments and analysis. Minneapolis, 2001.

[15] Otsu N. A threshold selection method from gray-level histograms. IEEE Trans. Sys., Man., Cyber., 1979, vol. 9, no. 1, pp. 62--66. DOI: 10.1109/TSMC.1979.4310076

[16] Dutta R. Image segmentation using thresholding. Kolkata, 2018.

[17] Yuheng S., Hao Y. Image segmentation algorithms overview. arxiv.org: website. Available at: https://arxiv.org/abs/1707.02051 (accessed: 15.03.2019).

[18] Fauza B., Kiweewa A., Bai L. A review of vessel segmentation technique. ICCAIS, 2017. DOI: 10.1109/CAIS.2018.8441989