Minimization of Region-Scalable Fitting Energy for Image Segmentation

Li, Chunming; Kao, Chiu‐Yen; Gore, John C.; Ding, Zhaohua

doi:10.1109/tip.2008.2002304

Cited by 1,475 publications

(392 citation statements)

References 31 publications

Supporting

Mentioning

341

Contrasting

Unclassified

Order By: Relevance

“…Similarly to region growing thresholding, conventional level set methods rely on seed initialization and require iterative solution, but use an implicit variational approach to solve the optimal segmentation problem [Mumford and Shah, 1989;Osher and Paragios, 2003;Weeratunga and Kamath, 2004]. Extremely high computational demand, a large number of control parameters and dependence on good initialization make this approach less suited for segmentation of high-resolution CT images of natural porous media, although new developments in the use of level set methods [e.g., Li et al, 2008] may provide a solution.…”

Section: Overview Of Segmentation Techniquesmentioning

confidence: 99%

Segmentation of X‐ray computed tomography images of porous materials: A crucial step for characterization and quantitative analysis of pore structures

Iassonov

Gebrenegus

Tuller

2009

Water Resources Research

510

332

View full text Add to dashboard Cite

[1] Nondestructive imaging methods such as X-ray computed tomography (CT) yield high-resolution, three-dimensional representations of pore space and fluid distribution within porous materials. Steadily increasing computational capabilities and easier access to X-ray CT facilities have contributed to a recent surge in microporous media research with objectives ranging from theoretical aspects of fluid and interfacial dynamics at the pore scale to practical applications such as dense nonaqueous phase liquid transport and dissolution. In recent years, significant efforts and resources have been devoted to improve CT technology, microscale analysis, and fluid dynamics simulations. However, the development of adequate image segmentation methods for conversion of gray scale CT volumes into a discrete form that permits quantitative characterization of pore space features and subsequent modeling of liquid distribution and flow processes seems to lag. In this paper we investigated the applicability of various thresholding and locally adaptive segmentation techniques for industrial and synchrotron X-ray CT images of natural and artificial porous media. A comparison between directly measured and image-derived porosities clearly demonstrates that the application of different segmentation methods as well as associated operator biases yield vastly differing results. This illustrates the importance of the segmentation step for quantitative pore space analysis and fluid dynamics modeling. Only a few of the tested methods showed promise for both industrial and synchrotron tomography. Utilization of local image information such as spatial correlation as well as the application of locally adaptive techniques yielded significantly better results.Citation: Iassonov, P., T. Gebrenegus, and M. Tuller (2009), Segmentation of X-ray computed tomography images of porous materials: A crucial step for characterization and quantitative analysis of pore structures, Water Resour. Res., 45, W09415,

show abstract

Section: Overview Of Segmentation Techniquesmentioning

confidence: 99%

Segmentation of X‐ray computed tomography images of porous materials: A crucial step for characterization and quantitative analysis of pore structures

Iassonov

Gebrenegus

Tuller

2009

Water Resources Research

510

332

View full text Add to dashboard Cite

show abstract

“…At present, there are a number of methods of segmentation. The LBF (Local Binary Fitting Energy) method [21,22] is employed in this paper, because it has a better segmentation result, especially for images with intensity inhomogeneity. The SIFT feature points are invariant to image scale and rotation, with robust matching across a substantial range of affine distortion, addition of noise, and change in illumination [23,24].…”

Section: Matching the Images Of Objectsmentioning

confidence: 99%

An Automatic Measurement Method for Absolute Depth of Objects in Two Monocular Images Based on SIFT Feature

Yang

Kong

et al. 2017

Applied Sciences

View full text Add to dashboard Cite

Abstract:Recovering depth information of objects from two-dimensional images is one of the very important and basic problems in the field of computer vision. In view of the shortcomings of existing methods of depth estimation, a novel approach based on SIFT (the Scale Invariant Feature Transform) is presented in this paper. The approach can estimate the depths of objects in two images which are captured by an un-calibrated ordinary monocular camera. In this approach, above all, the first image is captured. All of the camera parameters remain unchanged, and the second image is acquired after moving the camera a distance d along the optical axis. Then image segmentation and SIFT feature extraction are implemented on the two images separately, and objects in the images are matched. Lastly, an object's depth can be computed by the lengths of a pair of straight line segments. In order to ensure that the most appropriate pair of straight line segments are chosen, and also reduce computation, convex hull theory and knowledge of triangle similarity are employed. The experimental results show our approach is effective and practical.

show abstract

“…Below is the summary of the procedure: (1) Initialize the level set function φ using the method introduced in Ref. 27. (2) Compute local fitting value f 1 (x) and f 2 (x) using Eq.…”

Section: Iid Implementation Of Modelmentioning

confidence: 99%

“…5,[18][19][20][21][22][23][24][25][26][27] Existing active contours models can be classified into two categories: edge-based models [18][19][20][21] and region-based models. [22][23][24][25][26][27] The geodesic active contour model 21 (GAC) is a typical edgebased model. It utilizes image gradient information to guide evolving curve, and can detect a specific target from a complex background.…”

Section: Introductionmentioning

confidence: 99%

“…In order to address the common issue of intensity inhomogeneity in the medical image segmentation, Li et al 27 proposed a region-based level set method, called region-scalable fitting (RSF) model. Due to its capability of using intensity information in local regions at a controllable scale, the RSF model obtained good performance for images with intensity inhomogeneity.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

An active contour model for medical image segmentation with application to brain CT image

et al. 2013

View full text Add to dashboard Cite

Purpose: Cerebrospinal fluid (CSF) segmentation in computed tomography (CT) is a key step in computer-aided detection (CAD) of acute ischemic stroke. Because of image noise, low contrast and intensity inhomogeneity, CSF segmentation has been a challenging task. A region-based active contour model, which is insensitive to contour initialization and robust to intensity inhomogeneity, was developed for segmenting CSF in brain CT images. Methods:The energy function of the region-based active contour model is composed of a range domain kernel function, a space domain kernel function, and an edge indicator function. By minimizing the energy function, the region of edge elements of the target could be automatically identified in images with less dependence on initial contours. The energy function was optimized by means of the deepest descent method with a level set framework. An overlap rate between segmentation results and the reference standard was used to assess the segmentation accuracy. The authors evaluated the performance of the proposed method on both synthetic data and real brain CT images. They also compared the performance level of our method to those of region-scalable fitting (RSF) and global convex segment (GCS) models. Results: For the experiment of CSF segmentation in 67 brain CT images, their method achieved an average overlap rate of 66% compared to the average overlap rates of 16% and 46% from the RSF model and the GCS model, respectively. Conclusions: Their region-based active contour model has the ability to achieve accurate segmentation results in images with high noise level and intensity inhomogeneity. Therefore, their method has great potential in the segmentation of medical images and would be useful for developing CAD schemes for acute ischemic stroke in brain CT images.

show abstract

Minimization of Region-Scalable Fitting Energy for Image Segmentation

Cited by 1,475 publications

References 31 publications

Segmentation of X‐ray computed tomography images of porous materials: A crucial step for characterization and quantitative analysis of pore structures

Segmentation of X‐ray computed tomography images of porous materials: A crucial step for characterization and quantitative analysis of pore structures

An Automatic Measurement Method for Absolute Depth of Objects in Two Monocular Images Based on SIFT Feature

An active contour model for medical image segmentation with application to brain CT image

Contact Info

Product

Resources

About