An Improved Local or Global Active Contour Driven by Legendre Polynomials

In the paper, an improved local or global active contour model driven by Legendre Polynomials(LGLP) is proposed. It implemented with a special method, which selectively penalizes the level set function and then uses a filter to regularize it. Firstly, utilizing Legendre Polynomials approximates region intensity. Secondly, an improved region-based signed pressure force (ISPF) function is proposed, which efficiently stop the contours at weak edges, especially for the segmented image with intensity inhomogeneity. Finally, an edge stopping function is added to robustly capture the boundaries of objects. Experimental results show that the improved method is faster and achieve higher accuracy than other models on real images with intensity inhomogeneity, noise and multiple objects.

[1]  Guillermo Sapiro,et al.  Geodesic Active Contours , 1995, International Journal of Computer Vision.

[2]  Demetri Terzopoulos,et al.  Snakes: Active contour models , 2004, International Journal of Computer Vision.

[3]  Chunming Li,et al.  Level set evolution without re-initialization: a new variational formulation , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[4]  Chunming Li,et al.  Implicit Active Contours Driven by Local Binary Fitting Energy , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[5]  Chunming Li,et al.  Minimization of Region-Scalable Fitting Energy for Image Segmentation , 2008, IEEE Transactions on Image Processing.

[6]  Chunming Li,et al.  Active contours driven by local Gaussian distribution fitting energy , 2009, Signal Process..

[7]  Lei Zhang,et al.  Active contours driven by local image fitting energy , 2010, Pattern Recognit..

[8]  Chunming Li,et al.  Distance Regularized Level Set Evolution and Its Application to Image Segmentation , 2010, IEEE Transactions on Image Processing.

[9]  Xiaofeng Wang,et al.  An efficient local Chan-Vese model for image segmentation , 2010, Pattern Recognit..

[10]  Yi Gao,et al.  'Active contour without edges', on parametric manifolds , 2010, Medical Imaging.

[11]  Lei Zhang,et al.  Active contours with selective local or global segmentation: A new formulation and level set method , 2010, Image Vis. Comput..

[12]  Chunming Li,et al.  A Level Set Method for Image Segmentation in the Presence of Intensity Inhomogeneities With Application to MRI , 2011, IEEE Transactions on Image Processing.

[13]  M. Li,et al.  Adaptive Regularized Level Set Method for Weak Boundary Object Segmentation , 2012 .

[14]  Chuanjiang He,et al.  Adaptive level set evolution starting with a constant function , 2012 .

[15]  Jian Yang,et al.  Inhomogeneity-embedded active contour for natural image segmentation , 2015, Pattern Recognit..

[16]  Scott T. Acton,et al.  Region Based Segmentation in Presence of Intensity Inhomogeneity Using Legendre Polynomials , 2015, IEEE Signal Processing Letters.

[17]  Scott T. Acton,et al.  Dictionary Learning Level Set , 2015, IEEE Signal Processing Letters.

[18]  Bin Fang,et al.  Multi-scale B-spline level set segmentation based on Gaussian kernel equalization , 2016, 2016 IEEE International Conference on Image Processing (ICIP).

[19]  David Zhang,et al.  A Level Set Approach to Image Segmentation With Intensity Inhomogeneity , 2016, IEEE Transactions on Cybernetics.

[20]  Yi Wang,et al.  Automatic Liver Lesion Segmentation in CT Combining Fully Convolutional Networks and Non-negative Matrix Factorization , 2017, BIVPCS/POCUS@MICCAI.

[21]  Wei Zhang,et al.  An improved active contour model driven by region-scalable and local Gaussian-distribution fitting energy , 2017, 2017 International Conference on Security, Pattern Analysis, and Cybernetics (SPAC).