Compliant biomechanics of abdominal aortic aneurysms: A fluid–structure interaction study

Abdominal aortic aneurysm (AAA) rupture is believed to represent the culmination of a complex mechanism partially driven by the forces exerted along the lumen. In the present investigation, partially and fully coupled fluid–structure interaction (FSI) computations of three patient-specific AAA models are presented. This work advances previous FSI studies by including the iliac bifurcation and localized intraluminal thrombus. Among the patient models analyzed in this investigation, the FSI resulted in a maximum wall stress that varied 3–25% from the stress obtained with computational solid stress methods, demonstrating the importance of modeling blood flow for the assessment of AAA wall mechanics.     

Model-based quantitative AAA image analysis using a priori knowledge

Abdominal aortic aneurysm (AAA) is a serious vascular disease which may have a fatal outcome. AAA shape and size is important for diagnostics and intervention planning. In this paper, we present a new method for segmentation of AAA from computed tomography (CT) angiography images. The method works by segmenting the inner and the outer aortic border. Segmentation of AAA is a challenging problem because of low contrast of the outer aortic border. In our method, the inner aortic border is segmented using a geometric deformable model (GDM) and morphological postprocessing. The GDM is implemented using the level-set algorithm. The outer aortic border is segmented by a preprocessing method utilizing a priori knowledge about the aorta shape, followed by the GDM-based method, and morphological postprocessing. The preprocessing algorithm operates on a slice-by-slice basis with some information flow among neighboring slices. The GDM performs three-dimensional (3D) segmentation, reducing possible errors in the previous step. The proposed method is automatic and requires minimal user assistance. The method was statistically validated on 12 patient scans having a total number of 497 image slices. Statistical analysis has confirmed high correlation between the results obtained by the proposed method and the gold standard obtained by manual segmentation by an expert radiologist.     

一种新的基于统计的词典扩展方法

在建立统计语言模型时,往往会遇到词典的词汇量不够的问题。对于医学等专业领域的语料,这一问题尤为严重。针对这一问题,本文提出了一种新的基于统计的识别新词方法——右边缘扩展法。该方法对分词后的语料中产生的连续单字词进行关联范数估计,利用右边缘扩展的方法判断词的边界。在实验中,我们将右边缘扩展法与基于Witten-Bell back off方法的两两合并法相结合,循环地调整词典,优化语言模型。实验结果表明,该算法具有很高的识别正确率与检出率,可以有效地识别出语料中出现的新词汇,尤其是专业术语。     

基于深度学习的卫星图像道路分割算法

针对道路分割时存在的梯度消失问题,构建基于U-Net的卫星道路图像语义分割模型。通过密集连接模块减少梯度消失,并引入空间空洞金字塔结构保留更多的图像特征,在学习深层次特征信息时采用注意力监督机制,提取道路要素的特征信息。在卫星图像道路数据集上的测试结果表明,与FCN、SegNet、U_Net算法相比,该算法模型的准确率、召回率和精确率指标分别达到96.3%、96.9%和96.6%,能够有效地对道路元素进行准确分割。     

基于可变模型的腹主动脉瘤分割算法

提出了一种基于可变模型的腹主动脉瘤分割算法。它利用相邻两个切片间的相关性以及医学先验知识,可以快速地分割腹主动脉瘤CTA图像序列,并且结果与专家人工分割结果接近。本文将像素点分为三类：边界内,边界点,边界外,这样就直接决定了模型形变方向,大大提高了分割效率。     

Prior-based Segmentation and Shape Registration in the Presence of Perspective Distortion

Challenging object detection and segmentation tasks can be facilitated by the availability of a reference object. However, accounting for possible transformations between the different object views, as part of the segmentation process, remains difficult. Recent statistical methods address this problem by using comprehensive training data. Other techniques can only accommodate similarity transformations. We suggest a novel variational approach to prior-based segmentation, using a single reference object, that accounts for planar projective transformation. Generalizing the Chan-Vese level set framework, we introduce a novel shape-similarity measure and embed the projective homography between the prior shape and the image to segment within a region-based segmentation functional. The proposed algorithm detects the object of interest, extracts its boundaries, and concurrently carries out the registration to the prior shape. We demonstrate prior-based segmentation on a variety of images and verify the accuracy of the recovered transformation parameters.     

基于LSTM网络的中文地址分词法的设计与实现

当前中文地址的分词法主要采用基于规则和传统机器学习的方法。这些方法需要人工长期维护词典和提取特征。为避免特征工程和减少人工维护,提出了将长短时记忆（long short-term memory,LSTM）网络和双向长短时记忆（bi-directional long short-term memory,Bi-LSTM）网络分别应用在中文地址分词任务中,并采用四词位标注法以及增加未标记数据集的方法提升分词性能。在自建数据集上的实验结果表明：中文地址分词任务应用Bi-LSTM网络结构能得到较好性能,在增加未标记数据集的情况下,可以有效提升模型的性能。     

A Metric Approach to Vector-Valued Image Segmentation

We address the issue of low-level segmentation of vector-valued images, focusing on the case of color natural images. The proposed approach relies on the formulation of the problem in the metric framework, as a Voronoi tessellation of the image domain. In this context, a segmentation is determined by a distance transform and a set of sites. Our method consists in dividing the segmentation task in two successive sub-tasks: pre-segmentation and hierarchical representation. We design specific distances for both sub-problems by considering low-level image attributes and, particularly, color and lightness information. Then, the interpretation of the metric formalism in terms of boundaries allows the definition of a soft contour map that has the property of producing a set of closed curves for any threshold. Finally, we evaluate the quality of our results with respect to ground-truth segmentation data.     

An object-based and heterogeneous segment filter convolutional neural network for high-resolution remote sensing image classification

In recent years, object-based segmentation methods and shallow-model classification algorithms have been widely integrated for remote sensing image supervised classification. However, as the image resolution increases, remote sensing images contain increasingly complex characteristics, leading to higher intraclass heterogeneity and interclass homogeneity and thus posing substantial challenges for the application of segmentation methods and shallow-model classification algorithms. As important methods of deep learning technology, convolutional neural networks (CNNs) can hierarchically extract higher-level spatial features from images, providing CNNs with a more powerful recognition ability for target detection and scene classification in high-resolution remote sensing images. However, the input of the traditional CNN is an image patch, the shape of which is scarcely consistent with a given segment. This inconsistency may lead to errors when directly using CNNs in object-based remote sensing classification: jagged errors may appear along the land cover boundaries, and some land cover areas may overexpand or shrink, leading to many obvious classification errors in the resulting image. To address the above problem, this paper proposes an object-based and heterogeneous segment filter convolutional neural network (OHSF-CNN) for high-resolution remote sensing image classi?cation. Before the CNN processes an image patch, the OHSF-CNN includes a heterogeneous segment filter (HSF) to process the input image. For the segments in the image patch that are obviously different from the segment to be classified, the HSF can differentiate them and reduce their negative influence on the CNN training and decision-making processes. Experimental results show that the OHSF-CNN not only can take full advantage of the recognition capabilities of deep learning methods but also can effectively avoid the jagged errors along land cover boundaries and the expansion/shrinkage of land cover areas originating from traditional CNN structures. Moreover, compared with the traditional methods, the proposed OHSF-CNN can achieve higher classification accuracy. Furthermore, the OHSF-CNN algorithm can serve as a bridge between deep learning technology and object-based segmentation algorithms thereby enabling the application of object-based segmentation methods to more complex high-resolution remote sensing images.     

多图谱与联合标签融合策略相结合的主动脉CT图像分割

主动脉图像自动分割技术在主动脉疾病的早期诊断、风险评估及手术治疗中发挥重要作用。本文采用了基于多图谱的医学图像分割技术,并将之与联合标签融合（Joint label fusion,JLF）策略相结合应用于3D主动脉CT图像的自动分割问题中。联合标签融合策略考虑了各个图谱之间的相互关系,能够有效抑制图谱间冗余信息的干扰,进而提高标签融合精度。本文提出了一种图谱更新算法以应对图谱数量不足的问题,在提高分割精度的同时,保持了较低的计算复杂度。在15例主动脉CT图像数据上的分割结果表明,本文方法能有效地对3D主动脉图像进行分割,与3种基于传统融合方式的图谱分割法相比,本文方法具有更高的分割精度。     

Efficient and robust segmentation of noisy iris images for non-cooperative iris recognition

This paper describes the winning algorithm we submitted to the recent NICE.I iris recognition contest. Efficient and robust segmentation of noisy iris images is one of the bottlenecks for non-cooperative iris recognition. To address this problem, a novel iris segmentation algorithm is proposed in this paper. After reflection removal, a clustering based coarse iris localization scheme is first performed to extract a rough position of the iris, as well as to identify non-iris regions such as eyelashes and eyebrows. A novel integrodifferential constellation is then constructed for the localization of pupillary and limbic boundaries, which not only accelerates the traditional integrodifferential operator but also enhances its global convergence. After that, a curvature model and a prediction model are learned to deal with eyelids and eyelashes, respectively. Extensive experiments on the challenging UBIRIS iris image databases demonstrate that encouraging accuracy is achieved by the proposed algorithm which is ranked the best performing algorithm in the recent open contest on iris recognition (the Noisy Iris Challenge Evaluation, NICE.I).     

基于Matrix Profile的时间序列分割技术改进

时间序列分割是数据挖掘领域中的一个重要研究方向.目前基于矩阵轮廓(matrix profile, MP)的时间序列分割技术得到了越来越多研究人员的关注,并且取得了不错的研究成果.不过该技术及其衍生算法仍然存在不足:首先,基于矩阵轮廓的快速低代价语义分割算法中对给定活动状态的时间序列分割时,最近邻之间通过弧进行连接,会出现弧跨越非目标活动状态匹配相似子序列问题;其次,现有提取分割点算法在提取分割点时采用给定长度窗口,容易得到与真实值偏差较大的分割点,降低准确性.针对以上问题,提出一种限制弧跨越的时间序列分割算法(limit arc curve cross-FLOSS, LAC-FLOSS),该算法给弧添加权重,形成一种带权弧,并通过设置匹配距离阈值解决弧的跨状态子序列误匹配问题.此外,提出一种改进的提取分割点算法(improved extract regimes, IER),它通过纠正弧跨越(corrected arc crossings, CAC)序列的形状特性,从波谷中提取极值,避免直接使用窗口在非拐点处取到分割点的问题.在公开数据集datasets＿seg和Mobi Act上面进行...     

融合边界信息的高分辨率遥感影像分割优化算法

目的 针对目前区域分割算法获取的区域边界与真实地物边界不一致问题,利用高分辨率遥感影像地物内具有均质性和地物间边缘信息突出的特点,提出一种融合边界信息的高分辨率遥感影像分割优化算法。方法 首先采用Canny算法对遥感影像进行边缘提取并进行边缘连接处理,产生闭合边界;然后将边界与初始分割结果进行融合处理,获得新的分割结果;最后在闭合边界约束下,基于灰度相似性准则对新的分割结果进行区域合并,获得优化后的最终分割结果。结果 采用本文提出的分割优化算法对Mean Shift算法和eCognition软件获得的分割结果进行优化处理,优化后的分割结果与初始分割结果相比正确分割率（RR）平均提高了4%,验证了本文算法的有效性。结论 该优化算法适用性广,可优化基于区域、基于边界和基于聚类等多种分割方法,同时该算法既能保持高分辨率遥感影像分割的区域完整性,又能保持地物边缘细节特征,提高了分割精度。     

Towards supporting expert evaluation of clustering results using a data mining process model

Clustering is a popular non-directed learning data mining technique for partitioning a dataset into a set of clusters (i.e. a segmentation). Although there are many clustering algorithms, none is superior on all datasets, and so it is never clear which algorithm and which parameter settings are the most appropriate for a given dataset. This suggests that an appropriate approach to clustering should involve the application of multiple clustering algorithms with different parameter settings and a non-taxing approach for comparing the various segmentations that would be generated by these algorithms. In this paper we are concerned with the situation where a domain expert has to evaluate several segmentations in order to determine the most appropriate segmentation (set of clusters) based on his/her specified objective(s). We illustrate how a data mining process model could be applied to address this problem.     

基于卷积神经网络的语义分割算法研究

针对语义分割中残差网络并不能完好地提取图像信息和分割效果差的问题,提出一种联合特征金字塔模型(JFP)用来融合残差网络的输出特征,并结合暗黑空间金字塔池化模型(ASPP)进一步提取特征。在解码部分应用简单的解码结构,恢复图像尺寸完成语义分割;同时引入注意力模型作为辅助语义分割网络,辅助神经网络进行训练。该方法分别在Pascal VOC 2012数据集和增强的Pascal VOC 2012数据集上对网络进行训练,并在Pascal VOC 2012的验证集上进行测试,其平均交并集之比(mIoU)分别达到了78.55%和80.14%,表明该方法具有良好的语义分割性能。     

一种基于水平集的三维肝脏磁共振图像混合分割方法

针对腹部复杂的内部结构、各组织之间存在相互浸润,使得腹部磁共振(Magnetic resonance, MR)图像存在大量弱边缘的问题,以及使用传统水平集（Level set）方法对肝脏进行分割时易在弱边缘处产生泄露,采取阈值分割等算法进行预处理以获取更好的分割效果,并使用一种改进的水平集方法分割提取三维腹部MR图像中的肝脏。使用阈值分割进行粗分割可以有效减少干扰,将粗分割的结果进行亮度映射,增强边缘信息,然后将预分割的结果作为初始水平集,使用改进的水平集方法对其进行进一步分割。实验证明多种算法的有效结合能够改善传统水平集分割方法在弱边缘处过度演化的问题,获得较为理想的分割效果,拓展了水平集方法的应用。     

An evolutionary approach to pattern-based time series segmentation

Time series data, due to their numerical and continuous nature, are difficult to process, analyze, and mine. However, these tasks become easier when the data can be transformed into meaningful symbols. Most recent works on time series only address how to identify a given pattern from a time series and do not consider the problem of identifying a suitable set of time points for segmenting the time series in accordance with a given set of pattern templates (e.g., a set of technical patterns for stock analysis). However, the use of fixed-length segmentation is an oversimplified approach to this problem; hence, a dynamic approach (with high controllability) is preferable so that the time series can be segmented flexibly and effectively according to the needs of the users and the applications. In view of the fact that this segmentation problem is an optimization problem and evolutionary computation is an appropriate tool to solve it, we propose an evolutionary time series segmentation algorithm. This approach allows a sizeable set of pattern templates to be generated for mining or query. In addition, defining similarity between time series (or time series segments) is of fundamental importance in fitness computation. By identifying the perceptually important points directly from the time domain, time series segments and templates of different lengths can be compared and intuitive pattern matching can be carried out in an effective and efficient manner. Encouraging experimental results are reported from tests that segment both artificial time series generated from the combinations of pattern templates and the time series of selected Hong Kong stocks.     

基于快速凸无穷范数极小化的 大量子空间的子空间分割

摘 要：子空间分割是计算机视觉和机器学习中的一个基本问题。由于实际问题中的数据 往往类数较多,使得大量子空间的子空间分割问题显得尤为重要。近年来基于谱聚类的方法在 子空间分割领域得到了越来越多的关注,但是在相关工作的实验中,子空间的个数却往往不超 过 10 个。无穷范数极小化是近年来提出的一个专门针对大量子空间的子空间分割问题的方法, 其通过降低表示系数矩阵的差异性能有效地处理该问题,但是仍有一定的局限,例如计算速度 仍不够快,缺乏针对独立子空间问题的理论保证。为此,提出快速凸无穷范数极小化,该个方 法不仅能够降低表示系数矩阵的差异性,而且能够对独立子空间情况提供理论保障且计算速度 更快,大量的实验证明了该方法的有效性。     

基于深度感知特征提取的室内场景理解

从深度图RGB-D域中联合学习RGB图像特征与3D几何信息有利于室内场景语义分割,然而传统分割方法通常需要精确的深度图作为输入,严重限制了其应用范围。提出一种新的室内场景理解网络框架,建立基于语义特征与深度特征提取网络的联合学习网络模型提取深度感知特征,通过几何信息指导的深度特征传输模块与金字塔特征融合模块将学习到的深度特征、多尺度空间信息与语义特征相结合,生成具有更强表达能力的特征表示,实现更准确的室内场景语义分割。实验结果表明,联合学习网络模型在NYU-Dv2与SUN RGBD数据集上分别取得了69.5%与68.4%的平均分割准确度,相比传统分割方法具有更好的室内场景语义分割性能及更强的适用性。     

基于区域增长与局部自适应C-V模型的脑血管分割

提出了一种针对TOF MRA(time-of-flight magnetic resonance angiography)磁共振图像的双重分割脑血管提取方法。首先结合高斯滤波,采用二维OTSU算法,结合MIP(maximum intensity projection)图像获得三维血管种子点,定义全局与局部信息相结合的区域增长规则,通过区域增长算法对血管进行粗分割;然后,采用 Catt 扩散模型对体数据场进行各向异性滤波,提出了局部自适应C-V模型,将初步分割结果作为自适应活动轮廓模型的初始轮廓线进行二次分割。实验结果表明,该算法不仅能够有效分割脑血管粗大分支,而且还能精确提取脑血管的细小结构。