检索结果-内蒙古大学图书馆

arXiv 2017年

作者： Pei, Wenjie Dibeklioǧlu, Hamdi Baltrušaitis, Tadas Tax, David M.J. Pattern Recognition Laboratory Delft University of Technology Delft2628 CD Netherlands Department of Computer Engineering Bilkent University Ankara06800 Turkey Microsoft Corporation Microsoft Research Lab Cambridge CB1 2FD United Kingdom

The main challenges of age estimation from facial expression videos lie not only in the modeling of the static facial appearance, but also in the capturing of the temporal facial dynamics. Traditional techniques to this problem focus on constructing handcrafted features to explore the discriminative information contained in facial appearance and dynamics separately. This relies on sophisticated feature-refinement and framework-design. In this paper, we present an end-to-end architecture for age estimation which is able to simultaneously learn both the appearance and dynamics of age from raw videos of facial expressions. Specifically, we employ convolutional neural networks to extract effective latent appearance representations and feed them into recurrent networks to model the temporal dynamics. More importantly, we propose to leverage attention models for salience detection in both the spatial domain for each single image and the temporal domain for the whole video as well. We design a specific spatially-indexed attention mechanism among the convolutional layers to extract the salient facial regions in each individual image, and a temporal attention layer to assign attention weights to each frame. This two-pronged approach not only improves the performance by allowing the model to focus on informative frames and facial areas, but it also offers an interpretable correspondence between the spatial facial regions as well as temporal frames, and the task of age estimation. We demonstrate the strong performance of our model in experiments on a large, gender-balanced database with 400 subjects with ages spanning from 8 to 76 years. Experiments reveal that our model exhibits significant superiority over the state-of-the-art methods given sufficient training data. Copyright © 2017, The Authors. All rights reserved.

关键词： Dynamics

来源：评论

学校读者我要写书评

暂无评论

Integrating semi-supervised label propagation and random forests for multi-atlas based hippocampus segmentation

arXiv

引用

arXiv 2017年

作者： Zheng, Qiang Fan, Yong Department of Radiology Perelman School of Medicine University of Pennsylvania PhiladelphiaPA19104 United States School of Computer and Control Engineering Yantai University Yantai264005 China National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences Beijing100190 China

A novel multi-atlas based image segmentation method is proposed by integrating a semi-supervised label propagation method and a supervised random forests method in a pattern recognition based label fusion framework. The semi-supervised label propagation method takes into consideration local and global image appearance of images to be segmented and segments the images by propagating reliable segmentation results obtained by the supervised random forests method. Particularly, the random forests method is used to train a regression model based on image patches of atlas images for each voxel of the images to be segmented. The regression model is used to obtain reliable segmentation results to guide the label propagation for the segmentation. The proposed method has been compared with state-of-the-art multi-atlas based image segmentation methods for segmenting the hippocampus in MR images. The experiment results have demonstrated that our method obtained superior segmentation performance. Copyright © 2017, The Authors. All rights reserved.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

The Liver Tumor Segmentation Benchmark (LiTS)

arXiv

引用

arXiv 2019年

作者： Bilic, Patrick Christ, Patrick Li, Hongwei Bran Vorontsov, Eugene Ben-Cohen, Avi Kaissis, Georgios Szeskin, Adi Jacobs, Colin Mamani, Gabriel Efrain Humpire Chartrand, Gabriel Lohöfer, Fabian Holch, Julian Walter Sommer, Wieland Hofmann, Felix Hostettler, Alexandre Lev-Cohain, Naama Drozdzal, Michal Amitai, Michal Marianne Vivanti, Refael Sosna, Jacob Ezhov, Ivan Sekuboyina, Anjany Navarro, Fernando Kofler, Florian Paetzold, Johannes C. Shit, Suprosanna Hu, Xiaobin Lipková, Jana Rempfler, Markus Piraud, Marie Kirschke, Jan Wiestler, Benedikt Zhang, Zhiheng Hülsemeyer, Christian Beetz, Marcel Ettlinger, Florian Antonelli, Michela Bae, Woong Bellver, Míriam Bi, Lei Chen, Hao Chlebus, Grzegorz Dam, Erik B. Dou, Qi Fu, Chi-Wing Georgescu, Bogdan Giró-I-Nieto, Xavier Gruen, Felix Han, Xu Heng, Pheng-Ann Hesser, Jürgen Moltz, Jan Hendrik Igel, Christian Isensee, Fabian Jäger, Paul Jia, Fucang Kaluva, Krishna Chaitanya Khened, Mahendra Kim, Ildoo Kim, Jae-Hun Kim, Sungwoong Kohl, Simon Konopczynski, Tomasz Kori, Avinash Krishnamurthi, Ganapathy Li, Fan Li, Hongchao Li, Junbo Li, Xiaomeng Lowengrub, John Ma, Jun Maier-Hein, Klaus Maninis, Kevis-Kokitsi Meine, Hans Merhof, Dorit Pai, Akshay Perslev, Mathias Petersen, Jens Pont-Tuset, Jordi Qi, Jin Qi, Xiaojuan Rippel, Oliver Roth, Karsten Sarasua, Ignacio Schenk, Andrea Shen, Zengming Torres, Jordi Wachinger, Christian Wang, Chunliang Weninger, Leon Wu, Jianrong Xu, Daguang Yang, Xiaoping Yu, Simon Chun-Ho Yuan, Yading Yue, Miao Zhang, Liping Cardoso, Jorge Bakas, Spyridon Braren, Rickmer Heinemann, Volker Pal, Christopher Tang, An Kadoury, Samuel Soler, Luc van Ginneken, Bram Greenspan, Hayit Joskowicz, Leo Menze, Bjoern Department of Informatics Technical University of Munich Germany Department of Quantitative Biomedicine University of Zurich Switzerland Ecole Polytechnique de Montréal Canada Department of Medical Imaging Radboud University Medical Center Nijmegen Netherlands Department of Biomedical Engineering Tel-Aviv University Israel Germany Pattern Analysis and Learning Group Department of Radiation Oncology Heidelberg University Hospital Heidelberg Germany Philips Research China Philips China Innovation Campus Shanghai China School of Biomedical Engineering & Imaging Sciences King0s College London London United Kingdom Institute for AI in Medicine Technical University of Munich Germany Department of Computer Science Guangdong University of Foreign Studies China Institute for diagnostic and interventional radiology Klinikum rechts der Isar Technical University of Munich Germany Institute for Diagnostic and Interventional Neuroradiology Klinikum Rechts der Isar Technical University of Munich Germany Department of Hepatobiliary Surgery The Affiliated Drum Tower Hospital Nanjing University Medical School China Department of Computing Imperial College London London United Kingdom Institute for Tissue Engineering and Regenerative Medicine Helmholtz Zentrum München Neuherberg Germany Brigham and Women's Hospital Harvard Medical School United States School of Computer Science and Engineering The Hebrew University of Jerusalem Israel University of Pennsylvania PA United States Pte. Ltd. Singapore Medical Imaging and Reconstruction Lab Department of Engineering Design Indian Institute of Technology Madras India Sensetime Shanghai China Department of Radiology Perelman School of Medicine University of Pennsylvania United States Department of Pathology and Laboratory Medicine Perelman School of Medicine University of Pennsylvania PA United States Co. Ltd China MontréalQC Canada Department of Radiology Radiation Oncology and Nuclear Medicine University of Montréal

In this work, we report the set-up and results of the Liver Tumor Segmentation Benchmark (LiTS), which was organized in conjunction with the IEEE International Symposium on Biomedical Imaging (ISBI) 2017 and the International Conferences on Medical Image Computing and computer-Assisted Intervention (MICCAI) 2017 and 2018. The image dataset is diverse and contains primary and secondary tumors with varied sizes and appearances with various lesion-to-background levels (hyper-/hypo-dense), created in collaboration with seven hospitals and research institutions. Seventy-five submitted liver and liver tumor segmentation algorithms were trained on a set of 131 computed tomography (CT) volumes and were tested on 70 unseen test images acquired from different patients. We found that not a single algorithm performed best for both liver and liver tumors in the three events. The best liver segmentation algorithm achieved a Dice score of 0.963, whereas, for tumor segmentation, the best algorithms achieved Dices scores of 0.674 (ISBI 2017), 0.702 (MICCAI 2017), and 0.739 (MICCAI 2018). Retrospectively, we performed additional analysis on liver tumor detection and revealed that not all top-performing segmentation algorithms worked well for tumor detection. The best liver tumor detection method achieved a lesion-wise recall of 0.458 (ISBI 2017), 0.515 (MICCAI 2017), and 0.554 (MICCAI 2018), indicating the need for further research. LiTS remains an active benchmark and resource for research, e.g., contributing the liver-related segmentation tasks in http://***/. In addition, both data and online evaluation are accessible via ***. © 2019, CC BY-NC-ND.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Face alignment across large poses: A 3D solution

Face alignment across large poses: A 3D solution

引用

2016 IEEE Conference on computer Vision and pattern recognition, CVPR 2016

作者： Zhu, Xiangyu Lei, Zhen Liu, Xiaoming Shi, Hailin Li, Stan Z. Center for Biometrics and Security Research National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences China Department of Computer Science and Engineering Michigan State University United States

ISBN: (纸本)9781467388511

Face alignment, which fits a face model to an image and extracts the semantic meanings of facial pixels, has been an important topic in CV community. However, most algorithms are designed for faces in small to medium poses (below 45°), lacking the ability to align faces in large poses up to 90°. The challenges are three-fold: Firstly, the commonly used landmark-based face model assumes that all the landmarks are visible and is therefore not suitable for profile views. Secondly, the face appearance varies more dramatically across large poses, ranging from frontal view to profile view. Thirdly, labelling landmarks in large poses is extremely challenging since the invisible landmarks have to be guessed. In this paper, we propose a solution to the three problems in an new alignment framework, called 3D Dense Face Alignment (3DDFA), in which a dense 3D face model is fitted to the image via convolutional neutral network (CNN). We also propose a method to synthesize large-scale training samples in profile views to solve the third problem of data labelling. Experiments on the challenging AFLW database show that our approach achieves significant improvements over state-of-the-art methods.

关键词： Alignment

来源：评论

学校读者我要写书评

暂无评论

Transfer learning for diagnosis of congenital abnormalities of the kidney and urinary tract in children based on ultrasound imaging data

arXiv

引用

arXiv 2017年

作者： Zheng, Qiang Tasian, Gregory Fan, Yong Department of Radiology School of Medicine University of Pennsylvania PhiladelphiaPA19104 United States School of Computer and Control Engineering Yantai University Yantai264005 National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences Beijing100190 China Children's Hospital of Philadelphia PhiladelphiaPA19104 United States

Classification of ultrasound (US) kidney images for diagnosis of congenital abnormalities of the kidney and urinary tract (CAKUT) in children is a challenging task. It is desirable to improve existing pattern classification models that are built upon conventional image features. In this study, we propose a transfer learning-based method to extract imaging features from US kidney images in order to improve the CAKUT diagnosis in children. Particularly, a pre-trained deep learning model (imagenet-caffe-alex) is adopted for transfer learning-based feature extraction from 3-channel feature maps computed from US images, including original images, gradient features, and distanced transform features. Support vector machine classifiers are then built upon different sets of features, including the transfer learning features, conventional imaging features, and their combination. Experimental results have demonstrated that the combination of transfer learning features and conventional imaging features yielded the best classification performance for distinguishing CAKUT patients from normal controls based on their US kidney images. Copyright © 2017, The Authors. All rights reserved.

关键词： Ultrasonic imaging

来源：评论

学校读者我要写书评

暂无评论

Theoretical Assessment of Different Ultrasonic Configurations for Delamination Defects Detection in Composite Components

引用

Procedia CIRP 2017年 59卷 29-34页

作者： V. Kappatos G. Asfis K. Salonitis V. Tzitzilonis N.P. Avdelidis E. Cheilakou P. Theodorakeas Department of Technology and Innovation University of Southern Denmark (SDU) Campusvej 55 DK-5230 Odense M Denmark TWI Ltd Granta Park Great Abington Cambridge CB21 6AL UK Manufacturing Department Cranfield University Cranfield MK430AL UK Pattern Recognition Group Wire Communication Laboratory Department of Electrical & Computer Engineering University of Patras Greece Materials Science & Engineering Department School of Chemical Engineering National Technical University of Athens Zografou Campus 157 80 Athens Greece

It is well known that structures’ safety is crucial and of great importance. Part of their maintenance procedure is structural inspection, which is currently performed with the aid of Non Destructive Testing techniques, aiming to detect structural defects in damaged or flawed components and prevent a catastrophic failure by substituting or repairing them. The objective of this work is the theoretical assessment of different ultrasonic configurations that could maximize delamination defect detection in composite components. Modeling study was performed using simulation software, where physical models representative of laminated Carbon Fiber Reinforced Polymer composites, consisting of a variety of artificial delamination defect modes (different sizes and depth), were numerically tested. Different ultrasonic configurations on both the positioning and the firing of the probe's elements including Phased Array delay timings and sampled array techniques were investigated and are presented in this paper. The potential of Full Matrix Capture data acquisition technique, modelled here, along with the post processing Total Focusing Method reconstruction approach is also assessed in terms of their ability to enhance defect detectability and visualization.

关键词： Ultrasonic Assessment Sensor Configuration Phased Array Composite.

来源：评论

学校读者我要写书评

暂无评论

Perturbation treadmill training improves clinical rating of the motor symptoms gait and postural stability, and sensor-based gait parameters in Parkinson’s disease

引用

Gait & Posture 2017年 57卷 7-8页

作者： Gassner, Heiko Steib, Simon Klamroth, Sarah Pasluosta, Cristian Adler, Werner Eskofier, Bjoern Pfeifer, Klaus Winkler, Jürgen Klucken, Jochen Molecular Neurology University Hospital Erlangen Friedrich-Alexander University (FAU) Erlangen-Nürnberg Erlangen Germany Institute of Sport Science and Sport (ISS) FAU Erlangen-Nürnberg Erlangen Germany Pattern Recognition Lab FAU Erlangen-Nürnberg Erlangen Germany Laboratory for Biomedical Microtechnology Department of Microsystems Engineering University of Freiburg Freiburg Germany Department of Medical Informatics Biometry and Epidemiology FAU Erlangen-Nürnberg Erlangen Germany

来源：评论

学校读者我要写书评

暂无评论

Joint depth map interpolation and segmentation with planar surface model 16

Joint depth map interpolation and segmentation with planar s...

引用

2016 SIGGRAPH ASIA Technical Briefs, SA 2016

作者： Xu, Shibiao Dai, Longquan Zhang, Jiguang Tang, Jinhui Kumar, G. Hemanth Zhang, Yanning Zhang, Xiaopeng National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences Beijing China School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing China Department of Computer Science University of Mysore Mysore India School of Computer Science Northwestern Polytechnical University Xi'an China

ISBN: (纸本)9781450345415

Depth map interpolation and segmentation has been a long-standing problem in computer vision. However, many people treat them as two independent problems. Indeed, the two problems are complementary. The results of one problem can aid in improving the results of the other in powerful ways. Assuming that the depth map consists of planar surfaces, we propose a unified variational formula for joint depth map interpolation and segmentation. Specifically, our model uses a multi-label representation of the depth map, where each label corresponds to a parametric representation of the planar surface on a segment. Using alternating direction method, we are able to find the minimal solution. Experiments show our algorithm outperforms other methods. © 2016 ACM.

关键词： Interpolation

来源：评论

学校读者我要写书评

暂无评论

Scale-adaptive low-resolution person re-identification via learning a discriminating surface 25

Scale-adaptive low-resolution person re-identification via l...

引用

25th International Joint Conference on Artificial Intelligence, IJCAI 2016

作者： Zheng, Wang Hu, Ruimin Yu, Yi Jiang, Junjun Chao, Liang Jinqiao, Wang State Key Laboratory of Software Engineering School of Computer Wuhan University China Digital Content and Media Sciences Research Division National Institute of Informatics Japan School of Computer Science China University of Geosciences China National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences China National Engineering Research Center for Multimedia Software Collaborative Innovation Center of Geospatial Technology Hubei Provincial Key Laboratory of Multimedia and Network Communication Engineering Wuhan University China

Person re-identification, as an important task in video surveillance and forensics applications, has been widely studied. But most of previous approaches are based on the key assumption that images for comparison have the same resolution and a uniform scale. Some recent works investigate how to match low resolution query images against high resolution gallery images, but still assume that the low-resolution query images have the same scale. In real scenarios, person images may not only be with low-resolution but also have different scales. Through investigating the distance variation behavior by changing image scales, we observe that scale-distance functions, generated by image pairs under different scales from the same person or different persons, are distinguishable and can be classified as feasible (for a pair of images from the same person) or infeasible (for a pair of images from different persons). The scale-distance functions are further represented by parameter vectors in the scale-distance function space. On this basis, we propose to learn a discriminating surface separating these feasible and infeasible functions in the scale-distance function space, and use it for reidentifying persons. Experimental results on two simulated datasets and one public dataset demonstrate the effectiveness of the proposed framework.

关键词： Vector spaces

来源：评论

学校读者我要写书评

暂无评论

No-reference wavelet based retinal image quality assessment 5th

No-reference wavelet based retinal image quality assessment

引用

5th Eccomas Thematic Conference on Computational Vision and Medical Image Processing, VipIMAGE 2015

作者： Abdel Hamid, L.S. El-Rafei, A. El-Ramly, S. Michelson, G. Hornegger, J. Electronics and Communications Department Misr International University Cairo Egypt Engineering Physics and Mathematics Department Ain Shams University Cairo Egypt Electronics and Communication Engineering Department Ain Shams University Cairo Egypt Department of Ophthalmology Friedrich-Alexander University Erlangen-Nuremberg Germany Pattern Recognition Laboratory Department of Computer Science Friedrich-Alexander University Erlangen-Nuremberg Germany

ISBN: (纸本)9781138029262

Retinal Image Quality Assessment (RIQA) is an essential preliminarily step in Automatic Retinal Screening Systems (ARSS) to avoid misdiagnosis of retinal disease. In this work, a no-reference wavelet based RIQA algorithm suitable for real-time ARSS is introduced. Retinal images are classified into good and bad quality images using two proposed metrics. These measures are extracted from the wavelet decomposition subbands of the image to reflect sharpness and contrast. Wavelet level and regional analyses are performed to determine the most relevant levels and retinal region to be used in the RIQA. The algorithm is tested on two publicly available datasets with different resolutions. Area under the ROC curve (AUC) of 1 and 0.985 are obtained for the low and high resolution datasets respectively with runtime ranging between 0.1 and 2 seconds depending on image resolution. Comparison with other RIQA algorithms shows superiority of the proposed algorithm in both performance and time. © 2016 Taylor & Francis Group, London.

关键词： Real time systems

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：