面向互联网的大规模重复图像检索技术研究

针对互联网上典型的社交媒体应用,提出了一个基于随机投影和分块DCT系数的大规模分布式重复图像检索方法。该方法在Hadoop集群的基础上,首先利用随机投影映射生成图像签名,再由图像签名高效的检索HBase表以获得具有高召回率的候选图像集,最后依赖分块DCT系数对候选图像进行进一步过滤来提高检索精度。实验结果表明,对于1 200万张微博图像,当H =2且T=150时,该方法的召回率为98%,精确率为93.2%,平均检索时间为6.7 s。     

Medical image categorization and retrieval for PACS using the GMM-KL framework.

This paper presents an image representation and matching framework for image categorization in medical image archives. Categorization enables one to determine automatically, based on the image content, the examined body region and imaging modality. It is a basic step in content-based image retrieval (CBIR) systems, the goal of which is to augment text-based search with visual information analysis. CBIR systems are currently being integrated with picture archiving and communication systems for increasing the overall search capabilities and tools available to radiologists. The proposed methodology is comprised of a continuous and probabilistic image representation scheme using Gaussian mixture modeling (GMM) along with information-theoretic image matching via the Kullback-Leibler (KL) measure. The GMM-KL framework is used for matching and categorizing X-ray images by body regions. A multidimensional feature space is used to represent the image input, including intensity, texture, and spatial information. Unsupervised clustering via the GMM is used to extract coherent regions in feature space that are then used in the matching process. A dominant characteristic of the radiological images is their poor contrast and large intensity variations. This presents a challenge to matching among the images, and is handled via an illumination-invariant representation. The GMM-KL framework is evaluated for image categorization and image retrieval on a dataset of 1500 radiological images. A classification rate of 97.5% was achieved. The classification results compare favorably with reported global and local representation schemes. Precision versus recall curves indicate a strong retrieval result as compared with other state-of-the-art retrieval techniques. Finally, category models are learned and results are presented for comparing images to learned category models.     

基才时间信息的快速检索方法探究

本文研究了利用时间信息实现快速检索视频文件的方法,视频文件的压缩编码标准采用的是H．264,该方法主要包括视频分析和视频检索两个部分的研究。在视频分析部分,对码流中的IDR帧（关键帧）进行抓取和获得其时间、位置、大小等信息。并将得到的时间等信息存入至数据库。该部分的重点是时间信息的获取,由于负责传输码流的RTP数据分组的时间戳记录了码流的时间信息,所以着重描述了获取并且记录RTP时间戳的过程。视频检索部分,利用时间等查询条件从数据库中进行视频检索。对所述方法进行研究。结果表明使用该方法能够快速查看某时刻视频内容．避免了检索视频时的重复处理。     

A Web-Based Secure System for the Distributed Printing of Documents and Images

We propose and consider a secure printing system for the distributed printing of documents and images over the World Wide Web. The main feature of the system is that it allows previewing and printing of selected documents and images, where only a certain number of hardcopies can be generated based on an agreed payment. The security of the system resides on an aggregate of communication protocols, smartcard technologies, and cryptographic algorithms. The system prevents eavesdropping in that people who intercept the communication cannot generate copies of the document.     

Module replication and assignment for real-time distributed processing systems

Response time is an important design criterion for real-time systems. A new analytic model is developed to estimate task response time. It considers such factors as interprocessor communication, module precedence relationship, module scheduling, interconnection network delay, and assignment of modules and files to computers. Since module assignment as well as its replication have great impact on task response time, a new algorithm is developed to iteratively search for module assignments and replications that reduce task response time. An objective function is introduced that is based on the sum of task response time and delay penalty for the violations of thread response time requirements. With this objective function, good module allocations and replications, which minimize task response time and yet satisfy the thread response time requirements, can be determined by the proposed algorithm. To validate the algorithm, we compare the assignments generated by the algorithm for some sample distributed systems to the optimal module assignments obtained from exhaustive search. It shows that with a very small number of initial module assignments, our algorithm is able to generate the optimal or close-to-optimal assignments. The algorithm is also applied to a real-time distributed system for space defense applications where exhaustive search for the optimal assignment is not feasible. The generated module assignments (with replications) satisfy the specified thread response times, and compare closely with the simulation results. A series of experiments is also performed to characterize the behavior of the algorithm. In conclusion, the algorithm can serve as a valuable tool for assigning modules with replications for distributed systems.     

云平台上基于图像特征索引的并行检索系统技术研究

为了提高建立索引、检索图像的速度,提出云架构上基于图像特征索引的并行检索系统.该检索系统主要有3个模块:海量小图片分布式存储(Store)、并行建立图像特征索引(Indexing)、并行图像检索(Retrieve).在Store模块中提出针对海量图片的合并存储,Indexing模块中提出索引缓存模式,避免重写索引的输出接口,Retrieve模块中对索引进行分片管理,以及并行检索.实验结果表明,相对于其他图像检索系统,基于图像特征索引的检索系统有效减少了图像特征索引建立时间,缩短了图像的检索时间,提高了图像检索速率.     

Unified support for integrated all-optical multicast and burst amplification in transparent optical network

To better support transparent optical network, we present a novel scalable structure design based on multi-wavelength conversion (MWC) for integrated optical multicast and burst amplification in this paper. We also propose a corresponding wavelength assignment algorithm to minimize the cost of wavelength conversions in the multicast tree. MWC-based multicast strategy makes it possible to generate data copies through less processes and simplifies the wavelength assignment problem. Meanwhile, the generated data copies are used as complementary signals to compensate the power variations of original signal for Erbium-doped fiber amplifiers transient suppression. Experiments are conducted to demonstrate the performance of both burst amplification and multicast data generation in one MWC process. Simulation results are given for our new wavelength assignment algorithm, and advantages are shown over greedy algorithms.     

Efficient privacy-preserving image retrieval scheme over outsourced data with multi-user

The traditional privacy-preserving image retrieval schemes not only bring large computational and communication overhead,but also cannot protect the image and query privacy in multi-user scenarios.To solve above problems,an efficient privacy-preserving content-based image retrieval scheme was proposed in multi-user scenarios.The scheme used Euclidean distance comparison technique to rank the pictures according to similarity of picture feature vectors and return top-k returned.Meanwhile,the efficient key conversion protocol designed in proposed image retrieval scheme allowed each search user to generate queries based on his own private key so that he can retrieval encrypted images generated by different data owners.Strict security analysis shows that the user privacy and cloud data security can be well protected during the image retrieval process,and the performance analysis using real-world dataset shows that the proposed image retrieval scheme is efficient and feasible in practical applications.     

Iterative restoration of MR images corrupted with translational motion

Patient motion during the acquisition of magnetic resonance imaging data causes loss of resolution and ghost repetitions of the moving structures in the reconstructed image. In this paper the motion is modeled as being translational, and it is shown that this causes either the magnitude or the phase of the data to be corrupted, depending upon whether the motion is within or perpendicular to the imaging plane. The problem of restoring the image using only the corrupted data and no knowledge about the motion is addressed. The restoration problem is nonlinear in general, but is linear in two special cases. An iterative algorithm is developed that uses projections onto convex sets for magnitude retrieval and generalized projections for phase retrieval. In both cases constraint sets containing all a priori knowledge are used, and this is shown to be necessary for rapid convergence. The two algorithms may be combined to restore images corrupted by three-dimensional motion. The algorithms were verified using simulated data.     

A new way for multidimensional medical data management: volume of interest (VOI)-based retrieval of medical images with visual and functional features.

The advances in digital medical imaging and storage in integrated databases are resulting in growing demands for efficient image retrieval and management. Content-based image retrieval (CBIR) refers to the retrieval of images from a database, using the visual features derived from the information in the image, and has become an attractive approach to managing large medical image archives. In conventional CBIR systems for medical images, images are often segmented into regions which are used to derive two-dimensional visual features for region-based queries. Although such approach has the advantage of including only relevant regions in the formulation of a query, medical images that are inherently multidimensional can potentially benefit from the multidimensional feature extraction which could open up new opportunities in visual feature extraction and retrieval. In this study, we present a volume of interest (VOI) based content-based retrieval of four-dimensional (three spatial and one temporal) dynamic PET images. By segmenting the images into VOIs consisting of functionally similar voxels (e.g., a tumor structure), multidimensional visual and functional features were extracted and used as region-based query features. A prototype VOI-based functional image retrieval system (VOI-FIRS) has been designed to demonstrate the proposed multidimensional feature extraction and retrieval. Experimental results show that the proposed system allows for the retrieval of related images that constitute similar visual and functional VOI features, and can find potential applications in medical data management, such as to aid in education, diagnosis, and statistical analysis.     

基于自定义的LIRe和HBase的海量医学图像检索

为了解决海量医学图像检索效率低的问题,提出一种自定义的LIRe和HBase相结合的方案.首先,将医学图像上传到HDFS;然后,通过自定义LIRe框架分别提取海量医学图像的形状以及纹理特征并将特征向量及图像的绝对路径存储到HBase中.最后,利用MapReduce模型以及图像特征索引工具LIRe方便地对医学图像特征建立索引进行特征匹配实现检索.实验结果证明,自定义的LIRe提高了检索准确性,相比将医学图像以及特征向量均存储在HDFS中,也提高了检索效率.     

An integrated content and metadata based retrieval system for art

A new approach to image retrieval is presented in the domain of museum and gallery image collections. Specialist algorithms, developed to address specific retrieval tasks, are combined with more conventional content and metadata retrieval approaches, and implemented within a distributed architecture to provide cross-collection searching and navigation in a seamless way. External systems can access the different collections using interoperability protocols and open standards, which were extended to accommodate content based as well as text based retrieval paradigms. After a brief overview of the complete system, we describe the novel design and evaluation of some of the specialist image analysis algorithms including a method for image retrieval based on sub-image queries, retrievals based on very low quality images and retrieval using canvas crack patterns. We show how effective retrieval results can be achieved by real end-users consisting of major museums and galleries, accessing the distributed but integrated digital collections.     

Multiple image watermarking applied to health information management.

Information technology advances have brought forth new challenges in healthcare information management, due to the vast amount of medical data that needs to be efficiently stored, retrieved, and distributed, and the increased security threats that explicitly have to be addressed. The paper discusses the perspectives of digital watermarking in a range of medical data management and distribution issues, and proposes a complementary and/or alternative tool that simultaneously addresses medical data protection, archiving, and retrieval, as well as source and data authentication. The scheme imperceptibly embeds in medical images multiple watermarks conveying patient's personal and examination data, keywords for information retrieval, the physician's digital signature for authentication, and a reference message for data integrity control. Experimental results indicate the efficiency and transparency of the scheme, which conforms to the strict requirements that apply to regions of diagnostic significance.     

RAR编码文件格式分析

网络数据在传输过程中要先经过RAR编码进行压缩,节省传输时间。RAR格式的数据压缩编码在信息存储、信息管理、通信及保密方面得到广泛应用。其编码生成的压缩文件,存储格式复杂并且独特,包含有不同的数据块。根据RAR编码的显著特点,对RAR文件二进制码流块所包含的比特位做了定位分析,为研究其译码以及纠错译码算法奠定了基础。     

Managing medical images and clinical information: InCor's experience.

Patients usually get medical assistance in several clinics and hospitals during their lifetime, archiving vital information in a dispersed way. Clearly, a proper patient care should take into account that information in order to check for incompatibilities, avoid unnecessary exams, and get relevant clinical history. The Heart Institute (InCor) of S?o Paulo, Brazil, has been committed to the goal of integrating all exams and clinical information within the institution and other hospitals. Since InCor is one of the six institutes of the University of S?o Paulo Medical School and each institute has its own information system, exchanging information among the institutes is also a very important aspect that has been considered. In the last few years, a system for transmission, archiving, retrieval, processing, and visualization of medical images integrated with a hospital information system has been successfully created and constitutes the InCor's electronic patient record (EPR). This work describes the experience in the effort to develop a functional and comprehensive EPR, which includes laboratory exams, images (static, dynamic, and three dimensional), clinical reports, documents, and even real-time vital signals. A security policy based on a contextual role-based access control model was implemented to regulate user's access to EPR. Currently, more than 10 TB of digital imaging and communications in medicine (DICOM) images have been stored using the proposed architecture and the EPR stores daily more than 11 GB of integrated data. The proposed storage subsystem allows 6 months of visibility for rapid retrieval and more than two years for automatic retrieval using a jukebox. This paper addresses also a prototype for the integration of distributed and heterogeneous EPR.     

Biological data integration: wrapping data and tools

Scientific data is inevitably digital and stored in a wide variety of formats in heterogeneous systems. Scientists need to access an integrated view of remote or local heterogeneous data sources with advanced data access, analysis, and visualization tools. Building a digital library for scientific data requires accessing and manipulating data extracted from flat files or databases, documents retrieved from the Web as well as data generated by software. We present an approach to wrapping web data sources, databases, flat files, or data generated by tools through a database view mechanism. Generally, a wrapper has two tasks: it first sends a query to the source to retrieve data and, second builds the expected output with respect to the virtual structure. Our wrappers are composed of a retrieval component based on an intermediate object view mechanism called search views mapping the source capabilities to attributes, and an Extensible Markup Language (XML) engine, respectively, to perform these two tasks. The originality of the approach consists of: 1) a generic view mechanism to access seamlessly data sources with limited capabilities and 2) the ability to wrap data sources as well as the useful specific tools they may provide. Our approach has been developed and demonstrated as part of the multidatabase system supporting queries via uniform object protocol model (OPM) interfaces     

Dynamic image data compression in spatial and temporal domains:theory and algorithm

Advanced medical imaging requires storage of large quantities of digitized clinical data. These data must be stored in such a way that their retrieval does not impair the clinician's ability to make a diagnosis. We propose a theory and algorithm for near lossless dynamic image data compression. Taking advantage of domain-specific knowledge related to medical imaging, medical practice and the dynamic imaging modality, a compression ratio greater than 80:1 is achieved. The high compression ratios are achieved by the proposed algorithm through three stages: (1) addressing temporal redundancies in the data through application of image optimal sampling, (2) addressing spatial redundancies in the data through cluster analysis, and (3) efficient coding of image data using standard still-image compression techniques. To illustrate the practicality of the algorithm, a simulated positron emission tomography (PET) study using the fluoro-deoxy-glucose (FDG) tracer is presented. Realistic dynamic image data are generated by virtual scanning of a simulated brain phantom as a real PET scanner. These data are processed using the conventional and proposed algorithms as well as the techniques for storage and analysis. The resulting parametric images obtained from the conventional and proposed approaches are subsequently compared to evaluate the proposed compression algorithm. The storage space for dynamic image data reduced by more than 95%, without loss in diagnostic quality. Therefore, the proposed theory and algorithm are expected to be very useful in medical image database management and telecommunication     

IDAMN: an intrusion detection architecture for mobile networks

We present IDAMN (intrusion detection architecture for mobile networks), a distributed system whose main functionality is to track and detect mobile intruders in real time. IDAMN includes two algorithms which model the behavior of users in terms of both telephony activity and migration pattern. The main novelty of our architecture is its ability to perform intrusion detection in the visited location and within the duration of a typical call, as opposed to existing designs that require the reporting of all call data to the home location in order to perform the actual detection. The algorithms and the components of IDAMN have been designed in order to minimize the overhead incurred in the fixed part of the cellular network     

基于条纹式激光传感器与机器人的扫描成像系统

提出了一种以条纹式激光传感器和工业机器人为平台对工件进行扫描检测并对其轮廓进行成像的系统方案。条纹式激光传感器移动式扫描工件获取工件轮廓的三维点云数据,然后结合特定的算法对点云数据进行去噪、插值、插补处理,使得点云数据能更加真实地反映工件的客观形貌,最终根据点云数据的信息生成工件轮廓的二值化图像。在实验中成像精度能达到0.1 mm 级,从而在某些特殊的工业场合替代传统的CCD 相机实现对工件的成像及检测定位,解决了传统CCD 的抗干扰能力不足的问题。