Guo Cao

Robust spatially constrained fuzzy c-means algorithm for brain MR image segmentation

Abstract Objective Accurate brain tissue segmentation from magnetic resonance (MR) images is an essential step in quantitative brain image analysis, and hence has attracted extensive research attention. However, due to the existence of noise and intensity inhomogeneity in brain MR images, many segmentation algorithms suffer from limited robustness to outliers, over-smoothness for segmentations and limited segmentation accuracy for image details. To further improve the accuracy for brain MR image segmentation, a robust spatially constrained fuzzy c-means (RSCFCM) algorithm is proposed in this paper. Method Firstly, a novel spatial factor is proposed to overcome the impact of noise in the images. By incorporating the spatial information amongst neighborhood pixels, the proposed spatial factor is constructed based on the posterior probabilities and prior probabilities, and takes the spatial direction into account. It plays a role as linear filters for smoothing and restoring images corrupted by noise. Therefore, the proposed spatial factor is fast and easy to implement, and can preserve more details. Secondly, the negative log-posterior is utilized as dissimilarity function by taking the prior probabilities into account, which can further improve the ability to identify the class for each pixel. Finally, to overcome the impact of intensity inhomogeneity, we approximate the bias field at the pixel-by-pixel level by using a linear combination of orthogonal polynomials. The fuzzy objective function is then integrated with the bias field estimation model to overcome the intensity inhomogeneity in the image and segment the brain MR images simultaneously. Results To demonstrate the performances of the proposed algorithm for the images with/without skull stripping, the first group of experiments is carried out in clinical 3T-weighted brain MR images which contain quite serious intensity inhomogeneity and noise. Then we quantitatively compare our algorithm to state-of-the-art segmentation approaches by using Jaccard similarity on benchmark images obtained from IBSR and BrainWeb with different level of noise and intensity inhomogeneity. The comparison results demonstrate that the proposed algorithm can produce higher accuracy segmentation and has stronger ability of denoising, especially in the area with abundant textures and details. Conclusion In this paper, the RSCFCM algorithm is proposed by utilizing the negative log-posterior as the dissimilarity function, introducing a novel factor and integrating the bias field estimation model into the fuzzy objective function. This algorithm successfully overcomes the drawbacks of existing FCM-type clustering schemes and EM-type mixture models. Our statistical results (mean and standard deviation of Jaccard similarity for each tissue) on both synthetic and clinical images show that the proposed algorithm can overcome the difficulties caused by noise and bias fields, and is capable of improving over 5% segmentation accuracy comparing with several state-of-the-art algorithms.

Interval-valued possibilistic fuzzy C-means clustering algorithm

Type-2 fuzzy sets have drawn increasing research attentions in the pattern recognition community, since it is capable of modeling various uncertainties that cannot be appropriately managed by usual fuzzy sets. Although it has been introduced to data clustering, most widely used clustering approaches based on type-2 fuzzy sets still suffer from inherent drawbacks, such as the sensitiveness to outliers and initializations. In this paper, we incorporate the interval-valued fuzzy sets into the hybrid fuzzy clustering scheme, and thus propose the interval-valued possibilistic fuzzy c-means (IPFCM) clustering algorithm. We use both fuzzy memberships and possibilistic typicalities to model the uncertainty implied in the data sets, and develop solutions to overcome the difficulties caused by type-2 fuzzy sets, such as the construction of footprint of uncertainty, type-reduction and defuzzification. We compare the proposed algorithm with five fuzzy clustering approaches, including the FCM, PCM, PFCM, IFCM and IPCM, on two-dimensional Gaussian data sets and four multi-dimensional benchmark data sets. We also apply these clustering techniques to segment the brain magnetic resonance images and natural images. Our results show that the proposed IPFCM algorithm is more robust to outliers and initializations and can produce more accurate clustering results.

Active contours driven by local likelihood image fitting energy for image segmentation

Accurate image segmentation is an essential step in image analysis and understanding, where active contour models play an important part. Due to the noise, low contrast and intensity inhomogeneity in images, many segmentation algorithms suffer from limited accuracy. This paper presents a novel region-based active contour model for image segmentation by using the variational level set formulation. In this model, we construct the local likelihood image fitting (LLIF) energy functional by describing the neighboring intensities with local Gaussian distributions. The means and variances of local intensities in the LLIF energy functional are spatially varying functions, which can be iteratively estimated during an energy minimization process to guide the contour evolving toward object boundaries. To address diverse image segmentation needs, we also expand this model to the multiphase level set, multi-scale Gaussian kernels and narrowband formulations. The proposed model has been compared with several state-of-the-art active contour models on images with different modalities. Our results indicate that the proposed LLIF model achieves superior performance in image segmentation.

A spatially constrained generative asymmetric Gaussian mixture model for image segmentation

A spatially constrained generative asymmetric GMM is proposed.We modify the asymmetric GMM to introduce the spatial information.We approximate the log-priors with two auxiliaries set.We introduce additional penalty terms involving posterior distributions.We modify our previous work to construct the spatial weight factors. Accurate image segmentation is an essential step in image processing, where Gaussian mixture models with spatial constraint play an important role. Nevertheless, most methods suffer from one or more challenges such as limited robustness to noise, over-smoothness for segmentations, and lack of flexibility to fit the observed data. To address these issues, in this paper, we propose a generative asymmetric Gaussian mixture model with spatial constraint for image segmentation. The asymmetric distribution is modified to be easily incorporated the spatial information. Then our asymmetric model can be constructed based on the posterior and prior probabilities of within-cluster and between-cluster. Based on the Kullback-Leibler divergence, we introduce two pseudo-likelihood quantities which consider the neighboring priors of within-cluster and between-cluster. Finally, we derive an expectation maximization algorithm to maximize the approximation of the data log-likelihood. We compare our algorithm with state-of-the-art segmentation approaches to demonstrate the superior performance of the proposed algorithm.

A Rough Set Bounded Spatially Constrained Asymmetric Gaussian Mixture Model for Image Segmentation

Accurate image segmentation is an important issue in image processing, where Gaussian mixture models play an important part and have been proven effective. However, most Gaussian mixture model (GMM) based methods suffer from one or more limitations, such as limited noise robustness, over-smoothness for segmentations, and lack of flexibility to fit data. In order to address these issues, in this paper, we propose a rough set bounded asymmetric Gaussian mixture model with spatial constraint for image segmentation. First, based on our previous work where each cluster is characterized by three automatically determined rough-fuzzy regions, we partition the target image into three rough regions with two adaptively computed thresholds. Second, a new bounded indicator function is proposed to determine the bounded support regions of the observed data. The bounded indicator and posterior probability of a pixel that belongs to each sub-region is estimated with respect to the rough region where the pixel lies. Third, to further reduce over-smoothness for segmentations, two novel prior factors are proposed that incorporate the spatial information among neighborhood pixels, which are constructed based on the prior and posterior probabilities of the within- and between-clusters, and considers the spatial direction. We compare our algorithm to state-of-the-art segmentation approaches in both synthetic and real images to demonstrate the superior performance of the proposed algorithm.

A fuzzy clustering algorithm with robust spatially constraint for brain MR image segmentation

Fuzzy clustering algorithms have been widely used in brain magnetic resonance (MR) image segmentation. However, due to the existence of noise and intensity inhomogeneity, many segmentation algorithms suffer from limited accuracy. In this paper, we propose a fuzzy clustering algorithm with robust spatially constraint for accurate and robust brain MR image segmentation. A novel spatial factor is proposed by incorporating the spatial information amongst neighborhood pixels with a simple metric. A new weight factor, which utilizes the intensity information of the original image, is constructed to filter the posterior and prior probabilities in the spatial neighborhood. The proposed method can preserve more details and overcome the over-smoothing disadvantage. Finally, the fuzzy objective function is integrated with the bias field estimation model to overcome the intensity inhomogeneity in the image and segment the brain MR images. Experimental results demonstrate that the proposed algorithm can substantially improve the accuracy of brain MR image segmentation.

A novel ensemble method for k-nearest neighbor

Abstract In this paper, to address the issue that ensembling k-nearest neighbor (kNN) classifiers with resampling approaches cannot generate component classifiers with a large diversity, we consider ensembling kNN through a multimodal perturbation-based method. Since kNN is sensitive to the input attributes, we propose a weighted heterogeneous distance Metric (WHDM). By using a WHDM and evidence theory, a progressive kNN classifier is developed. Based on a progressive kNN, the random subspace method, attribute reduction, and Bagging, a novel algorithm termed RRSB (reduced random subspace-based Bagging) is proposed for construct ensemble classifier, which can increase the diversity of component classifiers without damaging the accuracy of the component classifiers. In detail, RRSB adopts the perturbation on the learning parameter with a weighted heterogeneous distance metric, the perturbation on the input space with random subspace and attribute reduction, the perturbation on the training data with Bagging, and the perturbation on the output target of k neighbors with evidence theory. In the experimental stage, the value of k, the different perturbations on RRSB and the ensemble size are analyzed. In addition, RRSB is compared with other multimodal perturbation-based ensemble algorithms on multiple UCI data sets and a KDD data set. The results from the experiments demonstrate the effectiveness of RRSB for kNN ensembling.

Single-column CNN for crowd counting with pixel-wise attention mechanism

This paper presents a novel method for accurate people counting in highly dense crowd images. The proposed method consists of three modules: extracting foreground regions (EF), pixel-wise attention mechanism (PAM) and single-column density map estimator (S-DME). EF can suppress the disturbance of complex background efficiently with a fully convolutional network, PAM performs pixel-wise classification of crowd images to generate high-quality local crowd density maps, and S-DME is a carefully designed single-column network that can learn more representative features with much fewer parameters. In addition, two new evaluation metrics are introduced to get a comprehensive understanding of the performance of different modules in our algorithm. Experiments demonstrate that our approach can get the state-of-the-art results on several challenging datasets including our dataset with highly cluttered environments and various camera perspectives.

Single image super-resolution via adaptive sparse representation and low-rank constraint

Abstract Sparse representation theory shows effectiveness in single image super-resolution (SR). Existing image super-resolution methods usually make use of l1-regularization, l2-regularization or their combination to restrict the sparsity. However, the nonlocal similarity of images, which can be helpful to image SR, is often neglected. In order to utilize the nonlocal similarity and improve SR results in this paper, we propose a new single image super-resolution method by combining the adaptive sparse representation and robust principal component analysis (RPCA). Furthermore, we adopt the self-similarity learning framework to construct the dictionary pair. In our method, we first compute the sparse coefficient of each testing image patch through adaptive sparse representation with the constructed dictionary. Then, for each testing image block, we search for its similar patches and use RPCA as a low-rank optimization strategy to the corresponding coefficients. Extensive experiment results demonstrate that the proposed method can possesses better performance compared with some state-of-the-art methods.

Unsupervised change detection in high spatial resolution remote sensing images based on a conditional random field model

Abstract In this paper, we propose a novel technique for unsupervised change detection in high spatial remote sensing images based on a conditional random field (CRF) model. The change-detection problem is formulated as a labeling issue to discriminate the changed class from the unchanged class in the difference image. CRF which employs the spatial property on both pixels spectral data and labels have been widely used in many remote sensing applications. However, as there are a large number of model parameters to train, the CRF-based change-detection approach is time consuming and difficult to implement. The proposed method artfully uses memberships of Fuzzy C-means as unary potentials and defines pairwise potentials using a scaled squared Euclidean distance between neighboring pixels. This not only avoids training parameters but also helps improving the accuracy and the degree of automation. The experimental results obtained from three different remote sensing images demonstrate the accuracy and efficiency of our proposed method.