检索结果-内蒙古大学图书馆

conference on Medical Imaging 2010 - Biomedical Applications in Molecular, Structural, and Functional Imaging

作者： Alic, Lejla Haeck, Joost C. Klein, Stefan Bol, Karin Van Tiel, Sandra T. Wielepolski, Piotr A. Bijster, Magda Niessen, Wiro J. Bernsen, Monique Veenland, Jifke F. de Jong, Marion Erasmus MC BIGR Biomed Imaging Grp Rotterdam POB 2040 NL-3000 CA Rotterdam Netherlands Erasmus MC Dept Radiol NL-3000 CA Rotterdam Netherlands Erasmus MC Dept Nucl Med NL-3000 CA Rotterdam Netherlands Delft Univ Technol Fac Appl Sci Delft Netherlands

ISBN: (纸本)9780819480279

Spatial correspondence between histology and multi sequence MRI can provide information about the capabilities of non-invasive imaging to characterize cancerous tissue. However, shrinkage and deformation occurring during the excision of the tumor and the histological processing complicate the co registration of MR images with histological sections. This work proposes a methodology to establish a detailed 3D relation between histology sections and in vivo MRI tumor data. The key features of the methodology are a very dense histological sampling (up to 100 histology slices per tumor), mutual information based non-rigid B-spline registration, the utilization of the whole 3D data sets, and the exploitation of an intermediate ex vivo MRI. In this proof of concept paper, the methodology was applied to one tumor. We found that, after registration, the visual alignment of tumor borders and internal structures was fairly accurate. Utilizing the intermediate ex vivo MRI, it was possible to account for changes caused by the excision of the tumor: we observed a tumor expansion of 20%. Also the effects of fixation, dehydration and histological sectioning could be determined: 26% shrinkage of the tumor was found. The annotation of viable tissue, performed in histology and transformed to the in vivo MRI, matched clearly with high intensity regions in MRI. With this methodology, histological annotation can be directly related to the corresponding in vivo MRI. This is a vital step for the evaluation of the feasibility of multi-spectral MRI to depict histological ground-truth.

关键词： multi-modal registration MRI histology tumor tissue characterization

来源：评论

学校读者我要写书评

暂无评论

DSP hardware implementation of transform-based compression algorithm for AUV telemetry

DSP hardware implementation of transform-based compression a...

引用

OCEANS

作者： D.M. Kocak F.M. Caimi Department of Electrical and Software Engineering Harbor Branch Oceanographic Institution Inc. Fort Pierce FL USA

Operation of AUVs or other platforms that rely upon robust communications for navigation and mission critical tasks is facilitated by the use of on-board data compression. Data compression eliminates redundancy of transmitted information and therefore improves the efficiency of the entire mission. In some applications, acoustic and non-acoustic sensor information is acquired and processed to produce a visual representation for ease of human-in-the-loop analysis and interpretation. Many image and data compression methods are currently in development. Emphasis has been placed on achieving high efficiency as characterized by compression ratio while retaining the least error between the original image and the compressed image. Although some algorithms produce excellent results, computational complexity, and hence speed of compression or decompression, can become a limiting factor in real-time use depending upon the capability of the on-board processor. This paper describes the implementation of a high performance image compression transform using a dedicated DSP processor and supporting computer host. The system architecture and strategy for efficient code implementation are described. Example performance measures are presented for non-acoustic undersea studies. Future plans and developments for specialized applications are also discussed.

关键词： Digital signal processing Hardware image coding Data compression Robustness Navigation Mission critical systems Redundancy Acoustic applications Sensor phenomena and characterization

来源：评论

学校读者我要写书评

暂无评论

Eye Movement Analysis using Virtual Reality in Early Detection of Alzheimer’s Disease

Eye Movement Analysis using Virtual Reality in Early Detecti...

引用

image processing, Computer Vision and Machine Learning (ICICML), International conference on

作者： Haiwei Zuo King Hann Lim Eswaran Sivaraman Jonathan Then Sien Phang Shenzhen City Polytechnic School of Information and Communications Technology Curtin Malaysia Research Institute Curtin University Malaysia

ISBN: (数字)9798350355413

ISBN: (纸本)9798350355420

Early detection of Alzheimer’s disease (AD) is important at the initial stage to provide prior treatment and control. In traditional diagnostic methods, medical doctors perform manual AD checking by asking patients to repeat several round of text reading and game exercises. The quantification of this manual assessment can be subjective due to the profession experience and it requires a further verification using the brain imaging. In this paper, an automated digital AD assessment method using Virtual Reality (VR) console is proposed to evaluate patient’s condition by tracking their eye movement during text reading. First, the eye movement pattern is captured using VR console during text reading. The recorded eye movement is then converted into frequency domain to study its frequency components during reading process. The simulation of AD symptom is set up by prompting subjects to read their familiar native language and unfamiliar language. As a result, the experiment shows that there are significant differences in eye movement patterns between native and unfamiliar language reading. The group of subjects reading unfamiliar language have random eye movement in less efficient visual processing. This pattern is similar to the patients who suffer in the AD symptom. In addition, the frequency features are extracted to study its correlations with reading comprehension performance in order to detect the early AD condition.

关键词： visualization Correlation Tracking Frequency-domain analysis Virtual reality Manuals Frequency conversion Feature extraction Alzheimer's disease Medical diagnostic imaging

来源：评论

学校读者我要写书评

暂无评论

An Anisotropic Diffusion Filtering Implementation to Execute in Parallel Distributed Systems

An Anisotropic Diffusion Filtering Implementation to Execute...

引用

IEEE International conference on Computational Science and Engineering Workshops (CSEWORKSHOPS)

作者： Antonio C. Sobieranski Leandro Coser M.A.R. Dantas Aldo v. Wangenheim Eros Comunello LAPIX-Image Processing and Graphic Computing Lab The Cyclops Group Federal University of Santa Catarina Brazil LaPeSD-Distributed Systems Research Laboratory Federal University of Santa Catarina Brazil Graduate Program Applied Computer Science Universidade do Vale do Itajaí Brazil

ISBN: (纸本)9780769532578

In this paper, we present a parallelization of a filtering algorithm related to non-linear anisotropic diffusion, used to enhance the performance of an application in a parallel distributed system. The anisotropic diffusion is a well-established technique for image enhancement by means of diffusivity functions, which act as border attenuators. However, it requires a high computational cost when a large amount of data is used. The proposed implementation was parallelized considering both point-to-point and collective communications, adopting the MPI paradigm. Results from both approaches indicate that the proposed algorithm has reached interesting levels of performance (81% and 93% of efficiency, respectively) when compared to the execution of one process in a single computer node. In addition, our results indicate an enhancement of around 21% utilizing the collective communication strategy when compared to point-to-point communication.

关键词： Filtering Magnetic separation Anisotropic magnetoresistance Ions Kernel Maximum likelihood detection Pixel

来源：评论

学校读者我要写书评

暂无评论

OBJECT RECOGNITION USING MULTI-VIEW IMAGING

OBJECT RECOGNITION USING MULTI-VIEW IMAGING

引用

9th International conference on Signal processing(第九届国际信号处理学术会议)(ICSP'08)

作者： Yizhou Wang Mike Brookes Pier Luigi Dragotti Communications and Signal Processing Group Electrical and Electronic Engineering Department Imperial College LondonExhibition RoadLondon SW7 2AZEngland

Difficult situations such as high noise or low resolution can seriously degrade the performance of object recognition algorithms that operate on isolated *** show that recognition performance may be improved substantially in such cases by fusing the information available from a sequence of multi-view *** this paper we present two algorithms for object recognition based on SIFT feature *** first operates on single images and uses chirality constraints to reduce the recognition errors that arise when only a small number of feature points are *** procedure is extended in the second algorithm which operates on a multi-view image sequence and,by tracking feature points in the plenoptic domain,is able to fuse feature point matches from all the available images resulting in more robust recognition.

关键词： Object recognition multi-view images local interest features plenoptic function SIFT

来源：评论

学校读者我要写书评

暂无评论

Evaluation of signal enhancement algorithms for hearing instruments

Evaluation of signal enhancement algorithms for hearing inst...

引用

European Signal processing conference (EUSIPCO)

作者： Koen Eneman Heleen Luts Jan Wouters Michael Büchler Norbert Dillier Wouter Dreschler Matthias Froehlich Giso Grimm Volker Hohmann Rolph Houben Arne Leijon Anthony Lombard Dirk Mauler Marc Moonen Henning Puder Michael Schulte Ann Spriet Matthias Vormann ExpORL - Dept. Neurosciences Katholieke Universiteit Leuven Leuven Belgium Denartment of Otorhinolaryngology University Hospital Zürich Switzerland AMC KNO-Audiologie Amsterdam the Netherlands Siemens Audiologische Technik GmbH Erlangen Germamy Medical Physics Section Carl von Ossietzky-Universität Oldenburg Germany Sound and Image Processing Lab Royal Institute of Technology (KTH) Stockholm Sweden Multimedia Communications and Signal Processing Universität Erlangen-Nürnberg Germany Institute of Communication Acoustics (IKA) Ruhr-Universität Bochum Germany ESAT/SISTA Katholieke Universiteit Leuven Belgium Hörzentrum Oldenburg GmbH Oldenburg Germany Hörzentrum Oldenburg GmbH Germany

In the frame of the HearCom1 project five promising signal enhancement algorithms are validated for future use in hearing instrument devices. To assess the algorithm performance solely based on simulation experiments, a number of physical evaluation measures have been proposed that incorporate basic aspects of normal and impaired human hearing. Additionally, each of the algorithms has been implemented on a common real-time hardware/software platform, which facilitates a profound subjective validation of the algorithm performance. Recently, a multicenter study has been set up across five different test centers in Belgium, the Netherlands, Germany and Switzerland to perceptually evaluate the selected signal enhancement approaches with normally hearing and hearing impaired listeners.

关键词： Auditory system Signal processing algorithms Speech Signal to noise ratio Noise measurement

来源：评论

学校读者我要写书评

暂无评论

A review paper on diagnosis of approximal and occlusal dental caries using digital processing of medical images

A review paper on diagnosis of approximal and occlusal denta...

引用

International conference on Emerging Trends in Electrical Electronics & Sustainable Energy Systems (ICETEESES)

作者： Raghav Agarwal Abhay Kumar Agrawal Harsh Vikram Singh Sonam Tyagi Electronics Engineering Department Kamla Nehru Institute of Technology Sultanpur India Computer Science Engineering Department Kamla Nehru Institute of Technology Sultanpur India

Diagnosis of Approximal and Occlusal caries is a difficult process in the clinical setting, because of the edge line in the Approximal surfaces is not so clear and also the complicated setting of pits and fissures in the Occlusal surface. Detection of these two types of dental caries can be carried out using two processes (1.) Carious legion has to be identified (2.) We have to assess the depth and the percentage of its activity in the mouth. Basically, caries at first is detected through visual inspection but it is not sufficient and also it is not periodic since lots of subjective parameters are involved and also the experience of the doctor plays a key role in this process. For the same problem there can be difference in the opinion between the doctors which directly affect the treatment process. Therefore this work aims on using certain parameters included in one algorithm which will refine the image taken and process it. Comparing that image with previous image will give the reasons that why there are the differences in opinions among the doctors for the same image and hence a better treatment process could be used after solving this problem. The images used in this work are of DICOM (Digital Imaging and communications in Medicine) standard. It is a standard set by NEMA and is used for handling, storing, printing and transmitting all types of medical images related to different types of diseases. These images has been captured using the digital radiography technology which is widely used in clinical settings to diagnose the dental caries.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Memory-Efficient Point Cloud Registration via Overlapping Region Sampling

arXiv

引用

arXiv 2024年

作者： Shimada, Tomoyasu Murasaki, Kazuhiko Sato, Shogo Nishimura, Toshihiko Yoshida, Taiga Tanida, Ryuichi NTT Corporation Japan

Recent advances in deep learning have improved 3D point cloud registration but increased graphics processing unit (GPU) memory usage, often requiring preliminary sampling that reduces accuracy. We propose an overlapping region sampling method to reduce memory usage while maintaining accuracy. Our approach estimates the overlapping region and intensively samples from it, using a k-nearest-neighbor (kNN) based point compression mechanism with multi layer perceptron (MLP) and transformer architectures. Evaluations on 3DMatch and 3DLoMatch datasets show our method outperforms other sampling methods in registration recall, especially at lower GPU memory levels. For 3DMatch, we achieve 94% recall with 33% reduced memory usage, with greater advantages in 3DLoMatch. Our method enables efficient large-scale point cloud registration in resource-constrained environments, maintaining high accuracy while significantly reducing memory requirements. This paper is accepted for IEEE International conference on visual communications and image processing 20241 © 2024, CC BY.

关键词： Graphics processing unit

来源：评论

学校读者我要写书评

暂无评论

Low-bit-rate scalable compression of mobile wireless video

Low-bit-rate scalable compression of mobile wireless video

引用

IEEE Region 10 International conference TENCON

作者： R. Fakeh A.A.A. Ghani M.Y.M. Saman A.R. Ramli Faculty of Computer Science and Information Technology Universiti Putra Malaysia Serdang Malaysia Deptartment Of Computer & Communication Systems Engineering Faculty of Engineering Universiti Putra Malaysia Serdang Selangor Darul Ehsan Malaysia

Low bit rate video coding has triggered intensive research in both academia and industry. To address the problem of heterogeneity, and meeting a very small bandwidth of mobile wireless networks, low bit rate scalable video compression is becoming more important. This paper discusses the current approach to wireless visual communications for the need of low bit rate scalable video compression, using discrete wavelet transform techniques. The discrete wavelet transform (DWT) has provided an efficient framework of multiresolution space-frequency representation with promising applications in image processing. This codec is based on 3D wavelet coding and adaptive quantization of the subbands coefficients. A common problem with some existing quantization methods is that the inherent image structures are severely distorted with course quantization. The Moving Picture Expert Group-4 (MPEG-4), an important component of the ITU standard is referred to as the benchmark of video standards for low bit rate video transmission.

关键词： Video compression Discrete wavelet transforms Bit rate Quantization image coding Video coding Bandwidth Wireless networks Wireless communication visual communication

来源：评论

学校读者我要写书评

暂无评论

An Adaptively Polygonal Simplification Algorithm for Remote Sensing image Segmentation Contours

An Adaptively Polygonal Simplification Algorithm for Remote ...

引用

2014 International conference on Remote Sensing and Wireless communications(RSWC 2014)

作者： JIANHUA LIU ZHAOYING YANG GUOYIN CAI RONGHUA WANG MINGYI DU Key Laboratory for Urban Geomatics of National Administration of Surveying Mapping and Geoinformation

Usually,the contours of polygons generated by image segmentation technology show jagged outlines and a large amount of redundant ***,the original segmentation contours hardly conform to GIS data producing standards without *** is also difficult to automatically give a unique set of parameters per segmentation contour *** order to meet the actual requirements for GIS data producing,we present an Adaptively Improved algorithm based on Douglas-Peucker,named AIDP,which integrated criterions of vertical and radial distance restriction,and design a corresponding parameter adaptive acquisition *** proposed method AIDP was evaluated by comparing with the most widely used Douglas-Peucker algorithm implemented in the ArcGIS through visual inspection,quantitative measures and applications in water body *** experimental results showed AIDP not only can acquire simplification parameters automatically,but also greatly speed up the data processing workflow with acceptable results.

关键词： image An Adaptively Polygonal Simplification Algorithm for Remote Sensing image Segmentation Contours

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：