检索结果-内蒙古大学图书馆

International Conference on Intelligent Information Hiding and Multimedia Signal Processing (IIHMSP)

作者： Naser Damer Benedikt Führer Competence Center Identification and Biometrics Fraunhofer Institute for Computer Graphics Darmstadt Germany Department of Computer Science Technische Universität Darmstadt Darmstadt Germany

Ear recognition is a promising biometric measure, especially with the growing interest in multi-modal biometrics. Histogram of Oriented Gradients (HOG) have been effectively and efficiently used solving the problems of object detection and recognition, especially when illumination variations are present. This work presents a robust approach for ear recognition using multi-scale dense HOG features as a descriptor of 2D ear images. The multi-scale features assure to capture the different and complicated structures of ear images. Dimensionality reduction was performed to avoid feature redundancy and provide a more efficient recognition process while being prone to over-fitting. Finally, a test was performed on a large and realistic database and the results were compared to the state of the art ear recognition approaches tested on the same dataset and under the same test procedure.

关键词： Ear Biometrics Feature extraction Face Face recognition Principal component analysis Lighting

来源：评论

学校读者我要写书评

暂无评论

Visual and force-feedback guidance for robot-assisted interventions in the beating heart with real-time MRI

Visual and force-feedback guidance for robot-assisted interv...

引用

IEEE International Conference on Robotics and Automation (ICRA)

作者： Nikhil V. Navkar Zhigang Deng Dipan J. Shah Kostas E. Bekris Nikolaos V. Tsekos The Computer Graphics & Interactive Media Lab and the Medical Robotics Lab at University of Houston TX USA The Computer Graphics & Interactive Media Lab and Computer Science Department at University of Houston Houston TX USA Methodist DeBakey Heart & Vascular Center Methodist Hospital Houston TX 77030 USA The Computer Science & Engineering Department’ University of Nevada Reno NV USA The Medical Robotics Lab and Computer Science Department at University of Houston Houston TX USA

Robot-assisted surgical procedures are perpetually evolving due to potential improvement in patient treatment and healthcare cost reduction. Integration of an imaging modality intraoperatively further strengthens these procedures by incorporating the information pertaining to the area of intervention. Such information needs to be effectively rendered to the operator as a human-in-the-loop requirement. In this work, we propose a guidance approach that uses real-time MRI to assist the operator in performing robot-assisted procedure in a beating heart. Specifically, this approach provides both real-time visualization and force-feedback based guidance for maneuvering an interventional tool safely inside the dynamic environment of a heart's left ventricle. Experimental evaluation of the functionality of this approach was tested on a simulated scenario of transapical aortic valve replacement and it demonstrated improvement in control and manipulation by providing effective and accurate assistance to the operator in real-time.

关键词： Manipulators Robot kinematics Real time systems Visualization Instruction sets Heart

来源：评论

学校读者我要写书评

暂无评论

Perimeter estimation of some discrete sets from horizontal and vertical projections

Perimeter estimation of some discrete sets from horizontal a...

引用

IASTED International Conference on Signal Processing, Pattern Recognition and Applications, SPPRA 2012

作者： Tasi, Tamás Sámuel Hegedus, Máté Balázs, Péter Department of Image Processing and Computer Graphics University of Szeged Árpád tér 2. H-6720 Szeged Hungary Faculty of Science and Informatics University of Szeged Aradi vértanúk tere 1. H-6720 Szeged Hungary

ISBN: (纸本)9780889869219

In this paper, we design neural networks to estimate the perimeter of simple and more complex discrete sets from their horizontal and vertical projections. The information extracted this way can be useful to simplify the problem of reconstructing the discrete set from its projections, which task is in focus of discrete tomography. Beside presenting experimental results with neural networks, we also reveal some statistical properties of the perimeter of the studied discrete sets.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

XioScreen: Experiences gained from building a series of prototypes of interactive public displays

Cognitive Technologies

引用

Cognitive Technologies 2012年 125-142页

作者： John, K. P. Ludwig Rist, Thomas Department of Graphics Design Hochschule für Angewandte Wissenschaften Augsburg Augsburg Germany Department of Computer Science Hochschule für Angewandte Wissenschaften Augsburg Augsburg Germany

ISBN: (纸本)9783642276620

xioScreen stands for a series of prototype installations of interactive public displays that have been developed, deployed, and evaluated at Hochschule Augsburg over the last 5 years. On the one hand xioScreen installations are part of an emerging digital signage system that informs students and campus visitors about events, talks, etc. On the other hand, xioScreen installations serve as testbeds for exploring new forms of interactive entertainment. Our initial working hypothesis was that students would take advantage of public screens as shared playgrounds for new gaming experiences. In terms of user participation, however, this did not work out so far - therefore other forms of active user participation have been explored as well. In this paper, we report on a number of conducted design-deployment-evaluation cycles and discuss lessons learned so far. © 2012 Springer-Verlag Berlin Heidelberg.

关键词： Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Progressive parallel coordinates

Progressive parallel coordinates

引用

Pacific (formerly Asia-Pacific APVIS) Visualization Symposium

作者： René Rosenbaum Jian Zhi Bernd Hamann Visual Computing and Computer Graphics group (VCG) Institute for Computer Science University of Rostock Rostock Germany Institute for Data Analysis and Visualization (IDAV) Department of Computer Science University of California Davis CA USA Department of Industrial Engineering and Operations Research Columbia University NY USA

Progressive refinement is a methodology that makes it possible to elegantly integrate scalable data compression, access, and presentation into one approach. Specifically, this paper concerns the effective use of progressive parallel coordinates (PPCs), utilized routinely for high-dimensional data visualization. It discusses how the power of the typical stages of progressive data visualization can also be utilized fully for PPCs. Further, different implementations of the underlying methods and potential application domains are described. The paper also presents empirical results concerning the benefits of PPC with regard to efficient data management and improved presentation, indicating that the proposed approach is able to close the gap between data handling and visualization.

关键词： Lead Visualization Logic gates

来源：评论

学校读者我要写书评

暂无评论

Intraoperative registration of preoperative 4D cardiac anatomy with real-time MR images

Intraoperative registration of preoperative 4D cardiac anato...

引用

IEEE Symposium on Bioinformatics and Bioengineering (BIBE)

作者： Xifeng Gao Nikhil V. Navkar Dipan J. Shah Nikolaos V. Tsekos Zhigang Deng Computer Graphics and Interactive Media Lab Houston TX USA Methodist DeBakey Heart & Vascular Center Houston TX USA Department of Computer Science University of Houston Houston TX USA

Co-registering pre- and intra- operative MR data is an important yet challenging problem due to different acquisition parameters, resolutions, and plane orientations. Despite its importance, previous approaches are often computationally intensive and thus cannot be employed in real-time. In this paper, a novel three-step approach is proposed to dynamically register pre-operative 4D MR data with intra-operative 2D RT-MRI to guide intracardiac procedures. Specifically, a novel preparatory step, executed in the pre-operative phase, is introduced to generate bridging information that can be used to significantly speed up the on-the-fly registration in the intraoperative procedure. Our experimental results demonstrate an accuracy of 0.42 mm and a processing speed of 26 FPS of the proposed approach on an off-the-shelf PC. This approach, is in particularly developed for performing intra-cardiac procedures with real-time MR guidance.

关键词： Real-time systems Heart Accuracy Spatial resolution Computational modeling Registers Solid modeling

来源：评论

学校读者我要写书评

暂无评论

Adaptive figure-ground classification

Adaptive figure-ground classification

引用

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Yisong Chen Antoni B. Chan Guoping Wang Graphics Laboratory EECS Department Key Laboratory of Machine Perception (MOE) Peking University China Department of Computer Science City University of Hong Kong Hong Kong China

We propose an adaptive figure-ground classification algorithm to automatically extract a foreground region using a user-provided bounding-box. The image is first over-segmented with an adaptive mean-shift algorithm, from which background and foreground priors are estimated. The remaining patches are iteratively assigned based on their distances to the priors, with the foreground prior being updated online. A large set of candidate segmentations are obtained by changing the initial foreground prior. The best candidate is determined by a score function that evaluates the segmentation quality. Rather than using a single distance function or score function, we generate multiple hypothesis segmentations from different combinations of distance measures and score functions. The final segmentation is then automatically obtained with a voting or weighted combination scheme from the multiple hypotheses. Experiments indicate that our method performs at or above the current state-of-the-art on several datasets, with particular success on challenging scenes that contain irregular or multiple-connected foregrounds. In addition, this improvement in accuracy is achieved with low computational cost.

关键词： Delta modulation Bandwidth Image segmentation Classification algorithms Color Gaussian distribution Covariance matrix

来源：评论

学校读者我要写书评

暂无评论

HeartPad: Real-time visual guidance for cardiac ultrasound

HeartPad: Real-time visual guidance for cardiac ultrasound

引用

Workshop at SIGGRAPH Asia 2012, WASA 2012

作者： Ford, Steven T. Viola, Ivan Bruckner, Stefan Torp, Hans Kiss, Gabriel Norwegian University of Science and Technology MI Lab. Department of Circulation and Medical Imaging Trondheim Norway Høgskolen I Nord-Trøndelag Norway University of Bergen Norway Christian Michelsen Research Norway Institute of Computer Graphics and Algorithms Vienna University of Technology Austria St. Olavs Hospital Trondheim Norway

ISBN: (纸本)9781450318358

Medical ultrasound is a challenging modality when it comes to image interpretation. The goal we address in this work is to assist the ultrasound examiner and partially alleviate the burden of interpretation. We propose to address this goal with visualization that provides clear cues on the orientation and the correspondence between anatomy and the data being imaged. Our system analyzes the stream of 3D ultrasound data and in real-time identifies distinct features that are basis for a dynamically deformed mesh model of the heart. The heart mesh is composited with the original ultrasound data to create the data-to-anatomy correspondence. The visualization is broadcasted over the internet allowing, among other opportunities, a direct visualization on the patient on a tablet computer. The examiner interacts with the transducer and with the visualization parameters on the tablet. Our system has been characterized by domain specialist as useful in medical training and for navigating occasional ultrasound users. © 2012 ACM.

关键词： Visualization

来源：评论

学校读者我要写书评

暂无评论

Robot-assisted mechanical scanning and co-registration of Magnetic Resonance Imaging and light-induced fluorescence

Robot-assisted mechanical scanning and co-registration of Ma...

引用

IEEE/RAS-EMBS International Conference on Biomedical Robotics and Biomechatronics (BioRob)

作者： Ahmet E. Sonmez William M. Spees Alpay Özcan Zhigang Deng Andrew G. Webb Nikolaos V. Tsekos Medical Robotics Laboratory Department of Computer Science at University of Houston Houston TX USA Biomedical Magnetic Resonance Laboratory Washington University St. Louis MO USA Arlington Innovation Center Virginia Polytechnic Institute and State University Arlington VA USA Computer Graphics & Interactive Media Lab and Computer Science Department at University of Houston Houston TX USA Department of Radiology Leiden University Medical Center Leiden Netherlands

Robotic manipulators offer some unique opportunities to address research and clinical needs. Among those is the potential use of a robotic manipulator to mechanically scan the tissue of interest with biosensors that have limited tissue penetration. In such cases, the robot can serve a dual role. First, it can perform spatial scanning with the biosensor along a pre-selected path inside the tissue. Second, it can function as the mechanical link to spatially co-register the data collected with the biosensor and the images of a guidance modality. Herein, we describe a robotic system to mechanically scan with a light-induced fluorescence (LIF) sensor and co-register LIF data to the guiding modality of MRI. Specifically, a custom-built MR-compatible endoscope was integrated onto the end-effector of an MR-compatible manipulator to collect MRI-guided LIF 1D scans. A miniature radiofrequency (RF) coil attached onto the end-effector was used as a fiducial marker for co-registering LIF and MRI. This mechanically scanning system was investigated on two compartment phantoms, each with different optical agents. Those studies demonstrated “robot-assisted” multi-modality co-registration, i.e. the spatial distribution of the LIF signals matched with the MR guiding images. The system can incorporate additional sensors for collecting complementary biochemical information.

关键词： Optical fibers Manipulators Robot sensing systems Probes Coils

来源：评论

学校读者我要写书评

暂无评论

A Supervised ANN Method for Memory Failure signature Classification

A Supervised ANN Method for Memory Failure signature Classif...

引用

2012 IEEE 11th International Conference on Solid-State and Integrated Circuit Technology(ICSICT-2012)

作者： Jianbo Li Yu Huang Wu-Tung Cheng Chris Schuermyer Dong Xiang Department of Computer Science and Technology Mentor Graphics Corporation School of Software Tsinghua University

ISBN: (纸本)9781467324748

Failure bitmaps of manufactured memory arrays may contain the information associated to some systematic defects and have hence been used to monitor the process and improve the memory *** is very important to develop a method to extract and classify the fault signatures in the failure *** fault signatures can be classified into two categories:local fault signatures and global fault *** on the local fault signatures,this paper introduces a supervised one-layer ANN method to solve the signature classification *** method is efficient for recognizing the local fault signatures in the failure bitmaps,and more importantly,it has the ability to find new signatures unseen before.

关键词： red ANN A Supervised ANN Method for Memory Failure signature Classification

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：