Multi-scale UDCT dictionary learning based highly undersampled MR image reconstruction using patch-based constraint splitting augmented Lagrangian shrinkage algorithm

Recently, dictionary learning(DL) based methods have been introduced to compressed sensing magnetic resonance imaging(CS-MRI), which outperforms pre-defined analytic sparse priors. However, single-scale trained dictionary directly from image patches is incapable of representing image features from multi-scale, multi-directional perspective, which influences the reconstruction performance. In this paper, incorporating the superior multi-scale properties of uniform discrete curvelet transform(UDCT) with the data matching adaptability of trained dictionaries, we propose a flexible sparsity framework to allow sparser representation and prominent hierarchical essential features capture for magnetic resonance(MR) images. Multi-scale decomposition is implemented by using UDCT due to its prominent properties of lower redundancy ratio, hierarchical data structure, and ease of implementation. Each sub-dictionary of different sub-bands is trained independently to form the multi-scale dictionaries. Corresponding to this brand-new sparsity model, we modify the constraint splitting augmented Lagrangian shrinkage algorithm(C-SALSA) as patch-based C-SALSA(PB C-SALSA) to solve the constraint optimization problem of regularized image reconstruction. Experimental results demonstrate that the trained sub-dictionaries at different scales, enforcing sparsity at multiple scales, can then be efficiently used for MRI reconstruction to obtain satisfactory results with further reduced undersampling rate. Multi-scale UDCT dictionaries potentially outperform both single-scale trained dictionaries and multi-scale analytic transforms. Our proposed sparsity model achieves sparser representation for reconstructed data, which results in fast convergence of reconstruction exploiting PB C-SALSA. Simulation results demonstrate that the proposed method outperforms conventional CS-MRI methods in maintaining intrinsic properties, eliminating aliasing, reducing unexpected artifacts, and removing noise. It can achieve comparable performance of reconstruction with the state-of-the-art methods even under substantially high undersampling factors.

基于卷积神经网络的晶圆缺陷检测与分类算法

针对晶圆检验时扫描电镜图像的缺陷检测和缺陷分类问题,利用ZFNet卷积神经网络对晶圆缺陷进行分类,并在此基础上,设计基于块的卷积神经网络缺陷检测算法。为提高准确率和加快速度,通过改进Faster RCNN分类器,提出另一种检测算法。实验结果表明,2种检测算法都能通过学习已标记位置和类型的缺陷数据,从扫描电镜图像中准确检测并分类多种类型缺陷。

Simulation of Urban Land Expansion Under Ecological Constraints in Harbin-Changchun Urban Agglomeration,China

Under the demand of urban expansion and the constraints of China’s’National Main Functional Area Planning’policy,urban agglomerations are facing with a huge contradiction between land utilization and ecological protection,especially for HarbinChangchun urban agglomeration who owns a large number of land used for the protection of agricultural production and ecological function.To alleviate this contradiction and provide insight into future land use patterns under different ecological constraints’scenarios,we introduced the patch-based land use simulation(PLUS)model and simulated urban expansion of the Harbin-Changchun urban agglomeration.After verifying the accuracy of the simulation result in 2018,we predicted future urban expansion under the constraints of three different ecological scenarios in 2026.The morphological spatial pattern analysis(MSPA)method and minimum cumulative resistance(MCR)model were also introduced to identify different levels of ecological security pattern(ESP)as ecological constraints.The predicted result of the optimal protection(OP)scenario showed less proportion of water and forest than those of natural expansion(NE)and basic protection(BP)scenarios in 2026.The conclusions are that the PLUS model can improve the simulation accuracy at urban agglomeration scale compared with other cellular automata(CA)models,and the future urban expansion under OP scenario has the least threat to the ecosystem,while the expansion under the natural expansion(NE)scenario poses the greatest threat to the ecosystem.Combined with the MSPA and MCR methods,PLUS model can also be used in other spatial simulations of urban agglomerations under ecological constraints.

A Machine Learning Approach for Expression Detection in Healthcare Monitoring Systems

Expression detection plays a vital role to determine the patient’s condition in healthcare systems.It helps the monitoring teams to respond swiftly in case of emergency.Due to the lack of suitable methods,results are often compromised in an unconstrained environment because of pose,scale,occlusion and illumination variations in the image of the face of the patient.A novel patch-based multiple local binary patterns(LBP)feature extraction technique is proposed for analyzing human behavior using facial expression recognition.It consists of three-patch[TPLBP]and four-patch LBPs[FPLBP]based feature engineering respectively.Image representation is encoded from local patch statistics using these descriptors.TPLBP and FPLBP capture information that is encoded to find likenesses between adjacent patches of pixels by using short bit strings contrary to pixel-based methods.Coded images are transformed into the frequency domain using a discrete cosine transform(DCT).Most discriminant features extracted from coded DCT images are combined to generate a feature vector.Support vector machine(SVM),k-nearest neighbor(KNN),and Naïve Bayes(NB)are used for the classification of facial expressions using selected features.Extensive experimentation is performed to analyze human behavior by considering standard extended Cohn Kanade(CK+)and Oulu–CASIA datasets.Results demonstrate that the proposed methodology outperforms the other techniques used for comparison.

Kernelized Correlation Filter Target Tracking Algorithm Based on Saliency Feature Selection

To address the problem of using fixed feature and single apparent model which is difficult to adapt to the complex scenarios, a Kernelized correlation filter target tracking algorithm based on online saliency feature selection and fusion is proposed. It combined the correlation filter tracking framework and the salient feature model of the target. In the tracking process, the maximum Kernel correlation filter response values of different feature models were calculated respectively, and the response weights were dynamically set according to the saliency of different features. According to the filter response value, the final target position was obtained, which improves the target positioning accuracy. The target model was dynamically updated in an online manner based on the feature saliency measurement results. The experimental results show that the proposed method can effectively utilize the distinctive feature fusion to improve the tracking effect in complex environments.

Label fusion for segmentation via patch based on local weighted voting

Label fusion is a powerful image segmentation strategy that is becoming increasingly popular in medical imaging. However, satisfying the requirements of higher accuracy and less running time is always a great challenge. In this paper we propose a novel patch-based segmentation method combining a local weighted voting strategy with Bayesian inference. Multiple atlases are registered to a target image by an advanced normalization tools(ANTs) algorithm. To obtain a segmentation of the target, labels of the atlas images are propagated to the target image. We first adopt intensity prior and label prior as two key metrics when implementing the local weighted voting scheme, and then compute the two priors at the patch level. Further, we analyze the label fusion procedure concerning the image background and take the image background as an isolated label when estimating the label prior. Finally, by taking the Dice score as a criterion to quantitatively assess the accuracy of segmentations, we compare the results with those of other methods, including joint fusion, majority voting, local weighted voting, majority voting based on patch, and the widely used Free Surfer whole-brain segmentation tool. It can be clearly seen that the proposed algorithm provides better results than the other methods. During the experiments, we make explorations about the influence of different parameters(including patch size, patch area, and the number of training subjects) on segmentation accuracy.

Image editing by object-aware optimal boundary searching and mixed-domain composition

When combining very different images which often contain complex objects and backgrounds,producing consistent compositions is a challenging problem requiring seamless image editing. In this paper, we propose a general approach, called objectaware image editing, to obtain consistency in structure,color, and texture in a unified way. Our approach improves upon previous gradient-domain composition in three ways. Firstly, we introduce an iterative optimization algorithm to minimize mismatches on the boundaries when the target region contains multiple objects of interest. Secondly, we propose a mixeddomain consistency metric for measuring gradients and colors, and formulate composition as a unified minimization problem that can be solved with a sparse linear system. In particular, we encode texture consistency using a patch-based approach without searching and matching. Thirdly, we adopt an objectaware approach to separately manipulate the guidance gradient fields for objects of interest and backgrounds of interest, which facilitates a variety of seamless image editing applications. Our unified method outperforms previous state-of-the-art methods in preserving global texture consistency in addition to local structure continuity.