Image segmentation by combining the global and local properties

Wang, Zhenzhou

doi:10.1016/j.eswa.2017.06.008

Cited by 20 publications

(17 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…When the values of W and N are not determined properly, the threshold will be determined inaccurately. The reason we choose the Fourier transform-based filter instead of other popular filters is based on the quantitative evaluation and comparison [19]. We found that the Fourier transformation-based filter outperforms other filters significantly in this conducted research work.…”

Section: Methodsmentioning

confidence: 99%

“…Since we did not reduce the noise beforehand, we apply a noise reduction procedure immediately after the segmentation. The noise would cause region inhomogeneity, and this inhomogeneity could be formulated by the Gibbs distribution:PX=x=1false∑x∈Le−false∑c∈CVcxe−false∑c∈CVcx,where V c ( x ) is the potential function associated with clique c. The clique c is defined as a set of sites such that any two elements in the clique are neighbours of each other [19]. L is the total number of pixel classes.…”

Section: Methodsmentioning

confidence: 99%

“…At first, we calibrate the parameters of the slope difference distribution-based threshold selection method with several typical CT images and then use the calibrated parameters for all the CT slices. After segmentation by the global threshold, the segmentation result is filtered by minimizing the Gibbs energy function [19] to reduce inhomogeneity. Then, morphological operations [20] are used to merge divided parts of the same organ, and the merged organ is used as liver segmentation constraint.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Fully Automatic Segmentation and Three-Dimensional Reconstruction of the Liver in CT Images

Wang

Zhang

Jiao

et al. 2018

Journal of Healthcare Engineering

Self Cite

View full text Add to dashboard Cite

Automatic segmentation and three-dimensional reconstruction of the liver is important for liver disease diagnosis and surgical treatment. However, the shape of the imaged 2D liver in each CT image changes dramatically across the slices. In all slices, the imaged 2D liver is connected with other organs, and the connected organs also vary across the slices. In many slices, the intensities of the connected organs are the same with that of the liver. All these facts make automatic segmentation of the liver in the CT image an extremely difficult task. In this paper, we propose a heuristic approach to segment the liver automatically based on multiple thresholds. The thresholds are computed based on the slope difference distribution that has been proposed and verified in the previous research. Different organs in the CT image are segmented with the automatically computed thresholds, respectively. Then, different segmentation results are combined to delineate the boundary of the liver robustly. After the boundaries of the 2D liver in all the slices are identified, they are combined to form the 3D shape of the liver with a global energy minimization function. Experimental results verified the effectiveness of all the proposed image processing algorithms in automatic and robust segmentation of the liver in CT images.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Fully Automatic Segmentation and Three-Dimensional Reconstruction of the Liver in CT Images

Wang

Zhang

Jiao

et al. 2018

Journal of Healthcare Engineering

Self Cite

View full text Add to dashboard Cite

show abstract

“…It is an essential step in many image applications. And thus a number of approaches [2], [3] have been proposed to utilize effective techniques to deal with image segmentation. Among the widely applied techniques for image segmentation, clustering [4]- [6] aims to divide a dataset into a finite set of clusters.…”

Section: Introductionmentioning

confidence: 99%

Unsupervised EA-Based Fuzzy Clustering for Image Segmentation

et al. 2020

View full text Add to dashboard Cite

This paper presents an unsupervised fuzzy clustering based on evolutionary algorithm for image segmentation. It needs no prior information about exact numbers of segments. Local and nonlocal spatial information derived from observed images are incorporated into fuzzy clustering process. It consists of three major procedures. First, a multi-objective evolutionary sampling is proposed to locate image pixels with a variety of image information. Secondly, optimizing fuzzy compactness and fuzzy separation, a multiobjective evolutionary fuzzy clustering with spatial information is performed on sampling pixels. The particular numbers of segments and balances of spatial information can be obtained. Then fuzzy clustering segmentation on whole image is carried out by two fuzzy clustering approaches, which are depended on fuzzy c-means and evolutionary algorithm respectively. To enhance qualities of final segmentation results, a label correction based on entropy and local spatial information is introduced. Experiments on different types of images demonstrate the effectiveness of our approach for image segmentation.

show abstract

“…Image segmentation is a one of fundamental techniques in compute vision [1]. Many image segmentation algorithms have been proposed in the past few years [2], [3].…”

Section: Introductionmentioning

confidence: 99%

Fuzzy Superpixels for Polarimetric SAR Images Classification

Guo

Jiao

Wang

et al. 2018

IEEE Trans. Fuzzy Syst.

View full text Add to dashboard Cite

Superpixels technique has drawn much attention in computer vision applications. Each superpixels algorithm has its own advantages. Selecting a more appropriate superpixels algorithm for a specific application can improve the performance of the application. In the last few years, superpixels are widely used in polarimetric synthetic aperture radar image classification. However, no superpixel algorithm is especially designed for image classification. It is believed that both mixed superpixels and pure superpixels exist in an image. Nevertheless, mixed superpixels have negative effects on classification accuracy. Thus, it is necessary to generate superpixels containing as few mixed superpixels as possible for image classification. In this paper, first, a novel superpixels concept, named fuzzy-superpixels, is proposed for reducing the generation of mixed superpixels. In fuzzy-superpixels, not all pixels are assigned to a corresponding superpixel. We would rather ignore the pixels than assign them to improper superpixels. Second, a new algorithm is proposed to generate fuzzy-superpixels for PolSAR image classification. Three PolSAR images are used to verify the effect of the proposed fuzzy superpixels algorithm. Experimental results demonstrate the superiority of the proposed fuzzy-superpixels algorithm over several state-of-the-art superpixels algorithms.

show abstract

Image segmentation by combining the global and local properties

Cited by 20 publications

References 25 publications

Fully Automatic Segmentation and Three-Dimensional Reconstruction of the Liver in CT Images

Fully Automatic Segmentation and Three-Dimensional Reconstruction of the Liver in CT Images

Unsupervised EA-Based Fuzzy Clustering for Image Segmentation

Fuzzy Superpixels for Polarimetric SAR Images Classification

Contact Info

Product

Resources

About