Active contours driven by weighted region-scalable fitting energy based on local entropy
Highlights
► We improve the region-scalable fitting model by “mollifying” kernel and local entropy. ► “Mollifying” kernel improves the model's ability of handling intensity inhomogeneity. ► Local entropy enhances robustness of the model to initialization and noise.
Introduction
Image segmentation has always been an essential problem in image processing and computer vision. The goal is to change the representation of an image into something that is more meaningful and easier to analyze. This is a critical intermediate step in many high level tasks such as objects recognition and tracking. So far, a large number of good algorithms and methodologies including active contour models [1] have been proposed for image segmentation. In this study, we focus on implicit active contour models, i.e., active contour models in a level set formulation.
Implicit active contour models have been proved to be a class of efficient techniques for image segmentation [2], [3]. They constitute very interesting applications of the level set method within the active contour framework [1]. The basic idea behind them is that an active contour is implicitly represented as the zero level set of a function in higher dimension (called level set function), and then the level set function is deformed according to an evolution partial differential equation (PDE). A remarkable advantage of implicit models is that the level set evolution allows for automatic topological change of active contour, which is generally impossible in traditional parametric active contour models [4] when direct implementations are performed. Early implicit models [5], [6], [7] first yield an evolution equation of a parameterized contour, and then convert it to the evolution PDE of the level set function whose zero level set represents the parameterized contour. Alternatively, the evolution PDE for level set function can be directly derived by gradient descent from the minimization problem for an energy functional over level set functions [8], [9], [10], [11], [12], [13], [14], [15], [16], [17], [18], [19].
Existing implicit active contour models can be roughly categorized into two basic classes: the edge-based [5], [6], [7], [8], [9] and the region-based [10], [11], [12], [13], [14], [15], [16], [17], [18], [19], depending on image features used for segmentation. Edge-based models utilize typically an edge indicator depending on image gradient to perform contour extraction. They have been successfully used to extract contours defined by gradient, but they have difficulty to detect edges without gradient, for instance very smooth or discontinuous boundaries [10]. Region-based models usually use global and/or local statistics inside regions rather than gradient on edges to find a partition of image domain. They generally have better performances in the presence of weak or discontinuous boundaries. Early popular region-based models tend to rely on intensity homogeneous (roughly constant or smooth) statistics in each of the regions to be segmented. Therefore, they either lack the ability to deal with intensity inhomogeneity like the PC (piecewise constant) model [10] or are excessively expensive in computation like the PS (piecewise smooth) model [12].
Intensity inhomogeneity often occurs in medical images such as X-ray radiography/tomography and magnetic resonance (MR) images [14], [15], [16]. The intensity inhomogeneity usually refers to the slow, nonanatomic intensity variations of the same tissue over the image domain [20]; in MR images, it often appears as an intensity variation across an image, and similar artifacts also in CT images and ultrasound images [16]. Although the presence of intensity inhomogeneity is usually hardly noticeable to a human observer, region-based models such as the PC model [10] are highly sensitive to the spurious variations of image intensities. Thus, segmentation of such medical images usually requires intensity inhomogeneity correction as a preprocessing step [20].
In order to handle directly intensity inhomogeneity within the active contour framework, Li et al. [15] proposed recently a region-scalable fitting (RSF) active contour model (originally termed as local binary fitting (LBF) model [14]) in a variational level set formulation. The RSF model draws upon intensity information in spatially varying local regions depending on a scale parameter, so it is able to deal with intensity inhomogeneity accurately and efficiently. However, the RSF model easily gets stuck in local minimums if the contour is initialized inappropriately. This makes it need user intervention to define the initial contours professionally. The multiple seed initialization used by Vese and Chan [12] also cannot always produce better results than the single seed initialization. Therefore, it is a great challenge to find an efficient way to address the initialization problem of the RSF model.
More recently, Wang et al. [16] proposed a novel local and global intensity fitting (LGIF) model in a variational level set formulation, which combines the advantages of the LBF model [14] and the PC model [10]. They first define an LGIF energy by a linear combination of local intensity fitting (LIF) energy [14] and global intensity fitting (GIF) energy [10] of the form , where the parameter controls the influence of the LIF energy and the GIF energy . The LGIF energy is then incorporated into a variational level set formulation with two extra regularization terms. The resulting evolution of level set function is the gradient flow that minimizes the overall energy functional. Since the PC model [10] is insensitive to initialization as well as noise and the LBF model can handle intensity inhomogeneity, the LGIF model can deal with intensity inhomogeneity by choosing appropriately the value of , while robust to initialization and noise. The inconvenience of the LGIF model in applications is mainly that the value of the parameter must be determined and adjusted in reference to initialization and noise level.
In this study, we present an improved version of the RSF model [15] in terms of robustness to initialization and noise. First, the Gaussian kernel for the RSF energy is replaced with a “mollifying” kernel [21] with compact support. Second, the RSF energy is redefined as a weighted energy integral, where the weight function is defined by local entropy that is derived from a grey level distribution of image [22]. The total energy functional is then incorporated into a variational level set formulation with two extra internal energy terms. The new RSF model not only provides desirable segmentation results in the presence of intensity inhomogeneity, but also allows for more flexible localizations of initial contours and more robustness to noise compared to the original RSF model [15].
The remainder of this paper is organized as follows. Section 2 briefly reviews the RSF model. Section 3 introduces the proposed scheme. Section 4 presents experimental results using a set of synthetic and real images, followed by some discussions in Section 5. This paper is summarized in Section 6.
Section snippets
The RSF model
In order to handle intensity inhomogeneity within the active contour framework, Li et al. [14], [15] recently proposed a novel region-based active contour model in a variational level set formulation. Given a gray level image , let C be a closed contour in the image domain , which separates into two regions: and . For a given point , the local intensity fitting (LIF) energy is defined as [14], [15]:where
Local entropy
Since the pioneer works of Frieden [24], the entropy concept has been widely and increasingly used as a powerful tool in image segmentation. Following the Shannon's definition, the entropy or average information of an image is concisely defined by , where pi is a certain distribution of the given image . The definition of the distribution pi is typically dependent on the schemes employed for image segmentation. For image thresholding [25], the distribution pi can be
Implementation
The level set evolution equation (23) is implemented using a simple finite differencing (forward-time central-space finite difference scheme). All the spatial partial derivatives and are approximated by the central difference, and the temporal partial derivative is discretized as the forward difference. The approximation of Eq. (23) can be simply written aswhere is the approximation of the right hand side in Eq. (23) by the above spatial
About the Gaussian and “mollifying” kernels
The kernel function K(u) and its localization property play a key role in handling intensity inhomogeneity by the RSF model [15]. The Gaussian and “mollifying” kernels, and , are both smooth functions having the localization property. A difference is that the “mollifying” kernel has a small compact support , and the Gaussian kernel is different of zero everywhere. Since is zero outside of the compact set , the fitting values f1(x) and f2(x)
Conclusion
In this paper, we propose an improved RSF model based on the “mollifying” kernel and local entropy. The “mollifying” kernel makes the RSF model have better localization property and so improves the ability of the RSF model to deal with intensity inhomogeneity. Meanwhile, local entropy makes the RSF model enhance the robustness to initialization and noise. Therefore, the new RSF model can not only handle better intensity inhomogeneity, but also allow for more flexible initialization and more
Acknowledgements
The authors would like to thank the anonymous reviewers for valuable comments to improve this paper. We are grateful to Dr. Chunming Li for sharing the code of the RSF model in http://www.engr.uconn.edu/∼cmli/. Besides, this work was supported by Chongqing University Postgraduates' Science and Innovation Fund (200904A1B0010313) and the Natural Science Foundation Project of CQ CSTC of China under Grant No. 2010BB9218.
References (29)
- et al.
Deformable template models: a review
Signal Processing
(1998) - et al.
A comparative study of deformable contour methods on medical image segmentation
Image Vision Computing
(2008) - et al.
Active contours driven by local and global intensity fitting energy with application to brain MR image segmentation
Computerized Medical Imaging and Graphics
(2009) - et al.
Active contours driven by local Gaussian distribution fitting energy
Signal Processing
(2009) Edge extraction using entropy operator
Computer Vision, Graphics, and Image Processing
(1986)- et al.
A new method for gray-level picture thresholding using the entropy of the histogram
Graphical Models and Image Processing
(1985) - et al.
Magnetic resonance image tissue classification using a partial volume model
Neuroimage
(2001) - et al.
Probability density difference-based active contour for ultrasound image segmentation
Pattern Recognition
(2010) - et al.
Geometric Level Set Methods in Imaging, Vision, and Graphics
(2003) - et al.
Snakes: active contour models
International Journal of Computer Vision
(1987)
A geometric model for active contours in image processing
Numerische Mathematik
Shape modelling with front propagation: a level set approach
IEEE Transactions on Pattern Analysis and Machine Intelligence
Geodesic active contours
International Journal of Computer Vision
Level set evolution without re-initialization: a new variational formulation
Cited by (142)
An edge map-guided acceleration strategy for multi-scale weighted nuclear norm minimization-based image denoising
2023, Digital Signal Processing: A Review JournalActive contour model based on local absolute difference energy and fractional-order penalty term
2022, Applied Mathematical ModellingDistance regularization energy terms in level set image segment model: A survey
2022, NeurocomputingA hybrid active contour model based on pre-fitting energy and adaptive functions for fast image segmentation
2022, Pattern Recognition Letters