Local Region Information Research Articles

2D-Sigmoid Enhancement Prior to Segment MRI Glioma Tumour

Tumour identification has always been a topic that interested researchers around the world. The most challenging phase in tumour identification based on brain MR image is the segmentation of the tumour contour which may contain many unwanted details. Intensity inhomogeneities often occur in real world images and may cause the difficulties in image segmentation. In order to overcome the difficulties caused by intensity inhomogeneity, the study presented pre-processing prior to a region based active contour model with modification of Region Scalable Fitting (MRF) method for image segmentation. Region based active contour model that draw upon intensity information in local regions. The pre-processing is a kind of image enhancement which applies the 2D-sigmoid function at tumour boundary. 2D-sigmoid function enhances the contrast in the brain MRI image for pre-processing steps. Enhanced pixel value, F(x, y), is the ‘S’ shape function of intensity I (x, y) of the image at the point (x, y) , width of the gradient magnitude around brain image (α) and gradient magnitude around brain image (β). Experimental results show desirable of MRF method in terms of computation efficiency.

Video anomaly detection and localization by local motion based joint video representation and OCELM

Nowadays, human-based video analysis becomes increasingly exhausting due to the ubiquitous use of surveillance cameras and explosive growth of video data. This paper proposes a novel approach to detect and localize video anomalies automatically. For video feature extraction, video volumes are jointly represented by two novel local motion based video descriptors, SL-HOF and ULGP-OF. SL-HOF descriptor captures the spatial distribution information of 3D local regions’ motion in the spatio-temporal cuboid extracted from video, which can implicitly reflect the structural information of foreground and depict foreground motion more precisely than the normal HOF descriptor. To locate the video foreground more accurately, we propose a new Robust PCA based foreground localization scheme. ULGP-OF descriptor, which seamlessly combines the classic 2D texture descriptor LGP and optical flow, is proposed to describe the motion statistics of local region texture in the areas located by the foreground localization scheme. Both SL-HOF and ULGP-OF are shown to be more discriminative than existing video descriptors in anomaly detection. To model features of normal video events, we introduce the newly-emergent one-class Extreme Learning Machine (OCELM) as the data description algorithm. With a tremendous reduction in training time, OCELM can yield comparable or better performance than existing algorithms like the classic OCSVM, which makes our approach easier for model updating and more applicable to fast learning from the rapidly generated surveillance data. The proposed approach is tested on UCSD ped1, ped2 and UMN datasets, and experimental results show that our approach can achieve state-of-the-art results in both video anomaly detection and localization task.

BoSCC: Bag of Spatial Context Correlations for Spatially Enhanced 3D Shape Representation.

Highly discriminative 3D shape representations can be formed by encoding the spatial relationship among virtual words into the Bag of Words (BoW) method. To achieve this challenging task, several unresolved issues in the encoding procedure must be overcome for 3D shapes, including: 1) arbitrary mesh resolution; 2) irregular vertex topology; 3) orientation ambiguity on the 3D surface; and 4) invariance to rigid and non-rigid shape transformations. In this paper, a novel spatially enhanced 3D shape representation called bag of spatial context correlations (BoSCCs) is proposed to address all these issues. Adopting a novel local perspective, BoSCC is able to describe a 3D shape by an occurrence frequency histogram of spatial context correlation patterns, which makes BoSCC become more compact and discriminative than previous global perspective-based methods. Specifically, the spatial context correlation is proposed to simultaneously encode the geometric and spatial information of a 3D local region by the correlation among spatial contexts of vertices in that region, which effectively resolves the aforementioned issues. The spatial context of each vertex is modeled by Markov chains in a multi-scale manner, which thoroughly captures the spatial relationship by the transition probabilities of intra-virtual words and the ones of inter-virtual words. The high discriminability and compactness of BoSCC are effective for classification and retrieval, especially in the scenarios of limited samples and partial shape retrieval. Experimental results show that BoSCC outperforms the state-of-the-art spatially enhanced BoW methods in three common applications: global shape retrieval, shape classification, and partial shape retrieval.

Hybrid active contour model based on edge gradients and regional multi-features for infrared image segmentation

Infrared image segmentation is always a tough task due to blurred boundaries, low contrasts and noises. Active contour model (ACM) is an efficient tool which has been proved to be useful when applied to image segmentation, but still has lots of drawbacks. In this paper, a hybrid ACM for infrared image segmentation is presented via combing both edge gradients and regional multi-features which are seldom considered in previous researches, meaning that its level set formulation (LSF) is made up of an edge-based term, a region-related term and a regularization term. The first term steams from intensity gradients and promotes the contour to approach the object boundary. The second term is constructed by means of integrating a novel multi-feature signed pressure function (MSPF) with a traditional signed pressure function (SPF) through an adaptive weight coefficient. In this case, both local and global regional information are considered and challenges caused by inhomogeneity are thus overcome. Lastly, the third term provides a stable evolution for the contour. In addition, a Gaussian filter is introduced to avoid computationally expensive re-initializations of the LSF efficiently. Both qualitative and quantitative experiments demonstrate the effectiveness and robustness of the proposed method with the initial contour being set randomly.

A new coordinated backup protection scheme for distribution network containing distributed generation

This paper proposes a new backup protection scheme, named coordinated backup protection (CBP) scheme, for distribution networks containing distributed generation. The proposed protection scheme takes into account the issues faced by traditional backup protection, such as difficulty in setting parameters and complex cooperation, and considers the features of distribution networks, such as changeable power flow because of high penetration of distributed generation sources and insufficient measuring quantities. The CBP scheme includes two aspects: coordinated substation protection and regional master substation protection, who also work as nearby backup protection and remote backup protection respectively. The two protections support each other by local information coordination and regional information sharing, in order to improve the reliability of fault identification. The configuration principles and performances of the proposed backup protection scheme are addressed in the paper. Different fault conditions in the IEEE 14-node system have been used to illustrate and verify the feasibility of the CBP scheme.

Region scalable active contour model with global constraint

Existing Active Contour methods suffer from the deficiencies of initialization sensitivity, slow convergence, and being insufficient in the presence of image noise and inhomogeneity. To address these problems, this paper proposes a region scalable active contour model with global constraint (RSGC). The energy function is formulated by incorporating local and global constraints. The local constraint is a region scalable fitting term that draws upon local region information under controllable scales. The global constraint is constructed through estimating the global intensity distribution of image content. Specifically, the global intensity distribution is approximated with a Gaussian Mixture Model (GMM) and estimated by Expectation Maximization (EM) algorithm as a prior. The segmentation process is implemented through optimizing the improved energy function. Comparing with two other representative models, i.e. region-scalable fitting model (RSF) and active contour model without edges (CV), the proposed RSGC model achieves more efficient, stable and precise results on most testing images under the joint actions of local and global constraints.

Active contours driven by region-scalable fitting and optimized Laplacian of Gaussian energy for image segmentation

It had been known that the famous region scalable-fitting model can segment the images with intensity inhomogeneity effectively, but it largely depends on the position of initial contour. In this paper, an active contour model which combines region-scalable fitting energy and optimized Laplacian of Gaussian (LoG) energy is proposed for image segmentation. We first present a LoG energy term optimized by an energy functional which can smooth the homogeneous regions and enhance edge information at the same time. Then, we integrate the optimized LoG energy term with the region-scalable fitting energy term which makes use of local region information to drive the curve towards the boundaries. With the addition of LoG term, the proposed model is insensitive to the positions of initial contour and realizes an accurate segmentation result. Experiments on some synthetic and real images have proved that the proposed model not only has a good robustness of initialization, but also has a higher segmentation accuracy and efficiency than other major region-based models.

A novel pixel neighborhood differential statistic feature for pedestrian and face detection

Motivated by the successful application of Local Binary Pattern (LBP), in this paper we propose a novel pixel neighborhood differential statistic feature for pedestrian and face detection based on the multiple channel maps. The calculation of LBP comprises of two steps, Pixel Differential Feature (PDF) calculation and PDF sign encoding. The PDF distills discriminative information of local region that can improve the performance of the pedestrian detector, but the encoding step degrades the performance due to the quantization error. Although PDF is more discriminative than original channel maps, it has a much higher dimension than the original feature maps, and consequently requiring large computation cost. To address this issue, the pixel neighborhood differential pattern is learned with both supervised and unsupervised learning methods, which allow discovering discriminative pixel differential patterns in local area and achieving state-of-the-art results. Specifically, our method firstly aggregates the image channel maps into cell maps with max pooling. Then, pixel neighborhood differential feature based on each channel cell maps are calculated which contributes to encoding discriminative information in each local area and benefits the performance improvements. In addition, we attempt to learn discriminative differential statistic patterns by using linear discriminative analysis (LDA) and principle component analysis (PCA) for further performance improvement. Two sets of experiments are conducted on pedestrian detection and face detection respectively. The INRIA, Caltech, and ETH datasets are used for pedestrian detection, and the FDDB and AFW datasets for multi-view face detection. The experimental results show that our method achieves superior performance in comparison with the state-of-the-arts while running at 20fps for 480×640 images.

A new lattice Boltzmann algorithm for assembling local statistical information with MR brain imaging segmentation applications

Recently, the lattice Boltzmann (LB) model has been used in medical imaging segmentation as alternatives for level set methods. The advantages of the LB model include its simple programming and the fact that it is easily paralleled, which can shorten computing times during real-time processing. However, traditional LB algorithms often fail to segment magnetic resonance (MR) brain images, which usually contain low-contrast intensity levels, noise and bias field. To solve these problems, this paper proposes a new LB algorithm assembled by local statistical region information, which can increase the between-class variances of the foreground and background by reducing intra-class variations and can achieve a better anti-noise performance by smoothing the noise of neighborhood pixels. To test its effectiveness and efficiency, comparison experiments were carried out with other LB and non-LB algorithms. The results show that our algorithm was validated on synthetic images and real MR images with desirable performance in the presence of low-contrast gray levels and noise. It also achieved best segmentation performance (with Dice coefficient 97.9 %) compared to other algorithms (with Dice coefficient 80.33, 58.11, 88.2, 81.77, 96.1 % respectively). In addition, the computing speed of the new algorithm is acceptable (18.65–27.62 s).

An improved edge-based level set method combining local regional fitting information for noisy image segmentation

Level set methods (LSMs) have been widely used in image segmentation because of their good properties which provide more smooth and accurate segmentation results. The edge-based LSMs use the gradient information of images through edge stop functions (ESFs) to guide the contour curve approaching to object edges. The traditional edge-based LSMs cannot obtain satisfactory segmentation results for noisy images because their regional coefficients are constant and their ESFs are easily influenced by noises. To solve the problems, this paper analyzes the different properties between noise points and object edge points and uses the local regional properties of images points to distinguish noises and object edge points. Based on the local regional properties, we introduce a variable regional coefficient and an improved ESF to overcome shortcomings of the constant regional coefficient and the traditional ESFs. Then we propose an improved edge-based level set method combining local regional fitting information by applying the proposed variable regional coefficient and the improved ESF to the energy function of level set function. The experimental results show that our method obtains accurate segmentation results for noisy images with insensitive to noises and without missing object edges and prove that the method is efficient and robust.

Local region-based ACM with fractional calculus for boundary segmentation in images with intensity inhomogeneity

This study proposes a novel local region-based active contour model (ACM) for image segmentation based on fractional calculus with consideration of the Riemann–Liouville operators. The proposed method aims to achieve accurate boundary segmentation in the presence of severe intensity inhomogeneity. The strength of fractional calculus is exploited with Gaussian Kernel namely, Fractional Gaussian Kernel (FGK) that provides an effective method of edge detection and has good noise immunity. An adaptive window mechanism with various sizes and orientations is employ to maintain and enhance image details especially at the object’s boundary and angle. The powerful combination of adaptive window and Fractional Gaussian Kernel (AFGK) provide an efficient way to utilize image information in local regions. Specifically, the fractional differential Heaviside function (FDH) extracts the image gradient and its various intensities for an accurate boundary segmentation outcome. Experiments on both synthetics and medical images demonstrate that the proposed local region-based ACM including fractional calculus realizes accurate boundary segmentation on images even under the most challenging situations, such as severe intensity inhomogeneity interface.

A Region-Specific Hybrid Sampling Method for Optimal Path Planning

Finding high quality paths within a limited time in configuration space is a challenging issue for path planning. Recently, an asymptotically optimal method called fast marching tree (FMT*) has been proposed. This method converges significantly faster than its state-of-the-art counterparts when addressing a wide range of problems. However, FMT* appears unable to solve the narrow passage problem in optimal path planning, since it is based on uniform sampling. Aiming at solving this problem, a novel region-based sampling method integrating global scenario information and local region information is proposed in this paper. First, global information related to configuration space is extracted from an initial sample set obtained via hybrid sampling. Then, local regions are constructed and local region information is captured to make intelligent decisions regarding regions that are difficult and need to be boosted. Finally, the initial sample set is sent to FMT* using a modified locally optimal one-step connection strategy in order to find an initial and feasible solution. If no solution is found and time permits, the guided hybrid sampling will be adopted in order to add more useful samples to the sample set until a solution is found or the time for doing so runs out. Simulation results for six benchmark scenarios validate that our method can achieve significantly better results than other state-of-the-art methods when applied in challenging scenarios with narrow passages.

System identification through nonstationary data using Time–Frequency Blind Source Separation

Classical output-only system identification (SI) methods are based on the assumption of stationarity of the system response. However, measured response of buildings and bridges is usually non-stationary due to strong winds (e.g. typhoon, and thunder storm etc.), earthquakes and time-varying vehicle motions. Accordingly, the response data may have time-varying frequency contents and/or overlapping of modal frequencies due to non-stationary colored excitation. This renders traditional methods problematic for modal separation and identification. To address these challenges, a new SI technique based on Time–Frequency Blind Source Separation (TFBSS) is proposed. By selectively utilizing “effective” information in local regions of the time–frequency plane, where only one mode contributes to energy, the proposed technique can successfully identify mode shapes and recover modal responses from the non-stationary response where the traditional SI methods often encounter difficulties. This technique can also handle response with closely spaced modes which is a well-known challenge for the identification of large-scale structures. Based on the separated modal responses, frequency and damping can be easily identified using SI methods based on a single degree of freedom (SDOF) system. In addition to the exclusive advantage of handling non-stationary data and closely spaced modes, the proposed technique also benefits from the absence of the end effects and low sensitivity to noise in modal separation. The efficacy of the proposed technique is demonstrated using several simulation based studies, and compared to the popular Second-Order Blind Identification (SOBI) scheme. It is also noted that even some non-stationary response data can be analyzed by the stationary method SOBI. This paper also delineates non-stationary cases where SOBI and the proposed scheme perform comparably and highlights cases where the proposed approach is more advantageous. Finally, the performance of the proposed method is evaluated using a full-scale non-stationary response of a tall building during an earthquake and found it to perform satisfactorily.

Shape-constrained level set segmentation for hybrid CPU–GPU computers

Due to its intrinsic advantages such as the ability to handle complex shapes, the level set method (LSM) has been widely applied to image segmentation. Nevertheless, the LSM is computationally expensive. In order to improve the performance of the traditional LSM both in terms of efficiency and effectiveness, we propose a novel algorithm based on the lattice Boltzmann method (LBM). Using local region statistics and prior shape, we design an effective and local speed function for the LSM, from which we deduce a shape prior based body force for LBM solver. An NVIDIA graphics processing units (GPU) is used to accelerate the method. Our introduced algorithm has several advantages. First, it is accurate even if there are some geometric transformations (rotation angle, scaling factor and translation vector) between the object to be segmented and the prior shape. Second, it is local and therefore suitable for massively parallel architectures. Third, the use of local region information allows it to deal with intensity inhomogeneities. Fourth, including shape prior allows the method to handle occlusion and noise. Fourth, the model is fast. Finally the algorithm can be used without shape prior by means of minor modification. Intensive experiments demonstrate, objectively and subjectively, the performance of the introduced framework.

A new region descriptor for multi-modal medical image registration and region detection.

Establishing accurate anatomical correspondences plays a critical role in multi-modal medical image registration and region detection. Although many features based registration methods have been proposed to detect these correspondences, they are mostly based on the point descriptor which leads to high memory cost and could not represent local region information. In this paper, we propose a new region descriptor which depicts the features in each region, instead of in each point, as a vector. First, feature attributes of each point are extracted by a Gabor filter bank combined with a gradient filter. Then, the region descriptor is defined as the covariance of feature attributes of each point inside the region, based on which a cost function is constructed for multi-modal image registration. Finally, our proposed region descriptor is applied to both multi-modal region detection and similarity metric measurement in multi-modal image registration. Experiments demonstrate the feasibility and effectiveness of our proposed region descriptor.

Multiple LREK active contours for knee meniscus ultrasound image segmentation.

Quantification of knee meniscus degeneration and displacement in an ultrasound image requires simultaneous segmentation of femoral condyle, meniscus, and tibial plateau in order to determine the area and the position of the meniscus. In this paper, we present an active contour for image segmentation that uses scalable local regional information on expandable kernel (LREK). It includes using a strategy to adapt the size of a local window in order to avoid being confined locally in a homogeneous region during the segmentation process. We also provide a multiple active contours framework called multiple LREK (MLREK) to deal with multiple object segmentation without merging and overlapping between the neighboring contours in the shared boundaries of separate regions. We compare its performance to other existing active contour models and show an improvement offered by our model. We then investigate the choice of various parameters in the proposed framework in response to the segmentation outcome. Dice coefficient and Hausdorff distance measures over a set of real knee meniscus ultrasound images indicate a potential application of MLREK for assessment of knee meniscus degeneration and displacement.

Active Contour Model Coupling Local and Global Information

The local region term and global region term are combined for image segmentation. Intensity information in local regions is utilized by adding a kernel function in the data fitting term. Experiments have been done on different images to compare the effectiveness of our methods with that of the classic CV model, Li’s Local Binary Fitting (LBF) model. Experiment results show that the new model maintain more satisfactory segmentation results.

3D vasculature segmentation using localized hybrid level-set method.

BackgroundIntensity inhomogeneity occurs in many medical images, especially in vessel images. Overcoming the difficulty due to image inhomogeneity is crucial for the segmentation of vessel image.MethodsThis paper proposes a localized hybrid level-set method for the segmentation of 3D vessel image. The proposed method integrates both local region information and boundary information for vessel segmentation, which is essential for the accurate extraction of tiny vessel structures. The local intensity information is firstly embedded into a region-based contour model, and then incorporated into the level-set formulation of the geodesic active contour model. Compared with the preset global threshold based method, the use of automatically calculated local thresholds enables the extraction of the local image information, which is essential for the segmentation of vessel images.ResultsExperiments carried out on the segmentation of 3D vessel images demonstrate the strengths of using locally specified dynamic thresholds in our level-set method. Furthermore, both qualitative comparison and quantitative validations have been performed to evaluate the effectiveness of our proposed model.ConclusionsExperimental results and validations demonstrate that our proposed model can achieve more promising segmentation results than the original hybrid method does.

A new image segmentation model with local statistical characters based on variance minimization

Chan–Vese (CV) model is a promising active contour model for image segmentation. However, CV model does not utilize local region information of images and thus segmentation method based on CV model cannot achieve good segmentation results for complex image with some in-homogeneity intensities. To overcome the limitation of CV model, this paper presents a new type of geometric active contour model using the strategy of variance minimization of image and introduced local statistics in the new energy formulation. The proposed model not only considers the first and second order moments of objective image statistical measurements, but also regularizes the level set function by incorporating the distance penalized energy function. The major contributions of this paper conclude two aspects. One is the new energy function based on variance minimization and another is the introduction of the local weighted averaging. In this paper, we get the local weighted averaging by the pieces smooth approximation through Gaussian convolution. Experimental results demonstrate that the proposed approach is effective in image segmentation, especially for the image with in-homogeneity intensity.

Local Minimum Energy of LBP Algorithm Concrete CT Image Segmentation

Concrete CT image segmentation is a hot civil engineering research field in recent years. An algorithm of minimizing the energy of local region is proposed to solve the problem of interaction fails to capture statistical property of natural image and to segment concrete CT image. At first, the algorithm utilizes local region information of image to construct the energy model of local region, establishes a segmentation model of local interaction region based on MRF. Then using loopy belief propagation (LBP) algorithm and other algorithms optimizes global energy. In process of optimization, local region energy is converged, and the label of local region is estimated based on MAP algorithm. Then the information of local region is transferred to the region of neighborhood. The result of experiment shows that comparing with standard LBP algorithm, the new algorithm has a better segmentation result, and efficiently restrained effect on image noise and texture for segmentation. Result of concrete CT image segmentation will simplify the following CT statistical analysis and provide an important method for reaching real meso-structure of concrete’s finite element network.