Improved active contour segmentation model based on phase consistency

ZHENG Wei; ZHANG Jing; LI Kaixuan; HAO Dongmei

doi:10.7510/jgjs.issn.1001-3806.2016.02.031

In order to realize rapid and accurate segmentation of nodular tissue in thyroid ultrasound images and overcome the effects of uneven gray distribution and fuzzy boundary of images on segmentation results, an improved active contour segmentation model based on phase congruency was proposed. First, a new speed function was constructed by means of the principle of phase congruency edge detection. It not only made up the defect of edge damage due to filter processing during gradient operator edge detection but also controlled curve evolution rate flexibly. After that, the speed function was introduced to the energy term of active contour model without edge to avoid the problem of weight distribution in the linear combination and have global segmentation ability. Through theoretical analysis and experimental verification,the relative difference of the improved model is less than 1% and the running time is less than that of the comparison models. The results show that the new model achieves accurate segmentation of image with uneven gray distribution and the efficiency of segmentation is improved.

Improved active contour segmentation model based on phase consistency

1. College of Electronic and Information Engineering, Hebei University, Baoding 071002, China;

2. Key Laboratory of Hebei on Digital Medical Engineering, Hebei University, Baoding 071002, China;

3. The Affiliated Hospital of Hebei University, Baoding 071000, China

Received Date: 2015-01-28

Accepted Date: 2015-03-24

Available Online: 2016-03-25

Abstract: In order to realize rapid and accurate segmentation of nodular tissue in thyroid ultrasound images and overcome the effects of uneven gray distribution and fuzzy boundary of images on segmentation results, an improved active contour segmentation model based on phase congruency was proposed. First, a new speed function was constructed by means of the principle of phase congruency edge detection. It not only made up the defect of edge damage due to filter processing during gradient operator edge detection but also controlled curve evolution rate flexibly. After that, the speed function was introduced to the energy term of active contour model without edge to avoid the problem of weight distribution in the linear combination and have global segmentation ability. Through theoretical analysis and experimental verification,the relative difference of the improved model is less than 1% and the running time is less than that of the comparison models. The results show that the new model achieves accurate segmentation of image with uneven gray distribution and the efficiency of segmentation is improved.

HTML

Reference (17)

[1]	ZHANG Z S,XI J Q,LIU Y. Canny operator study based on GCV criteria and Otsu[J].Computer Science, 2013, 40(6):279-282(in Chinese).
[2]	WANG L,HE L, ARABINDA M. Active contours driven by local Gaussian distribution fitting energy[J].Signal Processing, 2009, 89(12):2435-2447.
[3]	CHAN T, VESE L. Active contours without edges[J]. IEEE Transactions on Image Processing, 2001, 10(2):266-277.
[4]	LI C M, KAO C Y, JOHN C G, et al. Implicit active contours driven by local binary fitting energy[C]//IEEE Conference on Computer Vision and Pattern Recognition. New York, USA:IEEE, 2007:1-7.
[5]	WANG L, LI C M, SUN Q, et al. Active contours driven by local and global intensity fitting energy with application to brain MR image segmentation[J]. Computerized Medical Imaging and Graphics, 2009, 33(7):520-531.
[6]	LIU R J, HE C J, YUAN Y. Active contours driven by local and global image fitting energy[J]. Journal of Computer-Aided Design Computer Graphics, 2012, 24(3):364-371(in Chinese).
[7]	ZHANG J W, FANG L, CHEN Y J, et al. Left ventricle MRI segmentation based on active contour model[J]. Acta Electronica Sinica, 2011, 39(11):2670-2673(in Chinese).
[8]	WANG X H, JIN Y B. The active contour model for segmentation of coastal hyperspectral remote sensing image[J].Journal of Image and Graphics, 2013, 18(8):1031-1037(in Chinese).
[9]	CHEN K, LI B, TIAN L F, et al. Fuzzy speed function-based active contour model for segmentation of pulmonary nodules[J].Bio-Medical Materials and Engineering,2014, 24(1):539-547.
[10]	MORRONE M C, OWENS R A. Feature detection from local energy[J]. Pattern Recognition Letters, 1987, 6(5):303-313.
[11]	MORRONE M C, BURR D C. Feature detection in human vision:a phase-dependent energy model[J]. Proceedings of the Royal Society of London, 1988, B235(1280):221-245.
[12]	ZHENG W, PAN Z Y, HAO D M. The improved DRLSE ultrasound image segmentation model based on phase congruency[J]. Opto-Electronic Engineering, 2014,41(1):60-64(in Chinese).
[13]	KOVESI P. Phase preserving denoising of images[C]//The Australian Pattern Recognition Society Conference:DICTA'99. Perth, Australia:The University of Western Australia, 1999:212-217.
[14]	KOVESI P. Image features from phase congruency[J]. Journal of Computer Vision Research, 1999, 1(3):1-26.
[15]	LI C M, XU C Y, GUI C F, et al. Level set evolution without re-initialization:a new variational formulation[C]//IEEE International Conference on Computer Vision and Pattern Recognition. New York, USA:IEEE,2005:430-436.
[16]	LI C M, XU C Y, GUI C F, et al. Distance regularized level set evolution and its application to image segmentation[J].IEEE Transactions on Image Processing,2010,19(12):3243-3254.
[17]	COLLINS D L,EVANS A C,HOLMS C, et al. Automatic 3-D segmentation of neuro-anatomical structures from MRI[C]//14th International Conference on Information Processing in Medical Imaging. New York, USA:IEEE, 1995:139-152.

Improved active contour segmentation model based on phase consistency

Abstract

References

Proportional views

通讯作者: 陈斌, bchen63@163.com

Proportional views