To see the other types of publications on this topic, follow the link: Multimedia information retrieval system.
Dissertations / Theses on the topic 'Multimedia information retrieval system'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 50 dissertations / theses for your research on the topic 'Multimedia information retrieval system.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse dissertations / theses on a wide variety of disciplines and organise your bibliography correctly.
1
Mills, Timothy J. "Content modelling in multimedia information retrieval systems : the Cobra retrieval system." Thesis, University of Cambridge, 1997. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.442405.
Full text
2
Wayshak, Corinne. "MIT in motion : an interactive multimedia information retrieval system." Thesis, Massachusetts Institute of Technology, 1989. http://hdl.handle.net/1721.1/14291.
Full text
3
Morelock, Mark Geoffrey. "A multimedia information system for architectural design." Thesis, Georgia Institute of Technology, 1992. http://hdl.handle.net/1853/21604.
Full text
4
Chen, Xin. "Human-centered semantic retrieval in multimedia databases." Birmingham, Ala. : University of Alabama at Birmingham, 2008. https://www.mhsl.uab.edu/dt/2008p/chen.pdf.
Full textAbstract:
Thesis (Ph. D.)--University of Alabama at Birmingham, 2008.<br>Additional advisors: Barrett R. Bryant, Yuhua Song, Alan Sprague, Robert W. Thacker. Description based on contents viewed Oct. 8, 2008; title from PDF t.p. Includes bibliographical references (p. 172-183).
5
Chen, Junjie. "Learning hash codes for multimedia retrieval." HKBU Institutional Repository, 2019. https://repository.hkbu.edu.hk/etd_oa/684.
Full textAbstract:
The explosive growth of multimedia data in online media repositories and social networks has led to the high demand of fast and accurate services for large-scale multimedia retrieval. Hashing, due to its effectiveness in coding high-dimensional data into a low-dimensional binary space, has been considered to be effective for the retrieval application. Despite the progress that has been made recently, how to learn the optimal hashing models which can make the best trade-off between the retrieval efficiency and accuracy remains to be open research issues. This thesis research aims to develop hashing models which are effective for image and video retrieval. An unsupervised hashing model called APHash is first proposed to learn hash codes for images by exploiting the distribution of data. To reduce the underlying computational complexity, a methodology that makes use of an asymmetric similarity matrix is explored and found effective. In addition, the deep learning approach to learn hash codes for images is also studied. In particular, a novel deep model called DeepQuan which tries to incorporate product quantization methods into an unsupervised deep model for the learning. Other than adopting only the quadratic loss as the optimization objective like most of the related deep models, DeepQuan optimizes the data representations and their quantization codebooks to explores the clustering structure of the underlying data manifold where the introduction of a weighted triplet loss into the learning objective is found to be effective. Furthermore, the case with some labeled data available for the learning is also considered. To alleviate the high training cost (which is especially crucial given a large-scale database), another hashing model named Similarity Preserving Deep Asymmetric Quantization (SPDAQ) is proposed for both image and video retrieval where the compact binary codes and quantization codebooks for all the items in the database can be explicitly learned in an efficient manner. All the aforementioned hashing methods proposed have been rigorously evaluated using benchmark datasets and found to outperform the related state-of-the-art methods.
6
Yang, Yin-Wei. "Online multimedia communication system." CSUSB ScholarWorks, 2005. https://scholarworks.lib.csusb.edu/etd-project/2661.
Full textAbstract:
Online Multimedia Communication System is a project aimed at providing people the ability to store and share their multimedia files. The users and administrator can modify and view the files and database information from a normal web browser. Furthermore, this site offers a secure environment to keep all the users' information private.
7
Lin, Chang-Mei. "CICC Information System /." Online version of thesis, 1992. http://hdl.handle.net/1850/11094.
Full text
8
Watkins, Alfred R. "Continuous media object modeling, storage, and retrieval." Diss., Georgia Institute of Technology, 1996. http://hdl.handle.net/1853/9184.
Full text
9
Fuhr, Norbert Roelleke Thomas Goevert Norbert. "DOLORES: A System for Logic-Based Retrieval of Multimedia Objects." Gerhard-Mercator-Universitaet Duisburg, 2004. http://www.ub.uni-duisburg.de/ETD-db/theses/available/duett-04232004-133407/.
Full textAbstract:
We describe the design and implementation of a system for logic-based multimedia retrieval. As high-level logic for retrieval of hypermedia documents, we have developed a probabilistic object-oriented logic (POOL) which supports aggregated objects, different kinds of propositions (terms, classifications and attributes) and even rules as being contained in objects. Based on a probabilistic four-valued logic, POOL uses an implicit open world assumption, allows for closed world assumptions and is able to deal with inconsistent knowledge. POOL programs and queries are translated into probabilistic Datalog programs which can be interpreted by the HySpirit inference engine. For storing the multimedia data, we have developed a new basic IR engine which yields physical data abstraction. The overall architecture and the flexibility of each layer supports logic-based methods for multimedia information retrieval.
10
Vesilo, Rein Andres. "Issues in software engineering for implementing a multimedia document communication system using international standards." Thesis, The University of Sydney, 1989. https://hdl.handle.net/2123/26384.
Full textAbstract:
Multimedia documents are extensions of electronic documents, integrating text with other information types such as raster graphics images, geometric graphics images and audio. This thesis presents software strategies and techniques for implementing systems for processing and transferring multimedia documents based on international standards. The particular standards used are the ISO Office Document Architecture and Office Document Interchange Format (ODA/ODIF) standards and the ISO Open Systems Interconnection (OSI) standards. The three main areas of work are on the implementation of a multimedia document processing system, the development of software techniques for converting multimedia documents into ODA/ODIF and the development of strategies for implementing general 081 layers.
A review of recent multimedia work is given. Two types of characteristics are examined: general characteristics of multimedia systems, which distinguishes them from other systems, and characteristics which distinguish different types of services provided by multimedia systems. A useful classification was found to be between highly multi-functional systems and single paradigm systems. The review also examines functional requirements of systems and recent trends in multimedia systems including use of tools and object-oriented approaches.
The multimedia document system implemented is based on an IBM/PC compatible computer and uses the TEX document processing system as a basis for defining multimedia documents. Additional content types supported are images, structured voice, unstructured voice and limited graphics. Multimedia documents occur in three representations: logical form documents as multimedia TEX documents, formatted documents as multimedia DVI documents and interchange format documents as ODA/ODIF documents. System facilities include those to create, format, present and transfer documents. An important component of work on this system was the development of techniques to integrate the different media types and new system components with existing system components. These include standard command formats, file formats, generic interfaces, modular system design, shareable modules, reusable software and application of object oriented concepts.
Software strategies for developing document translators to and from ODA/ODIF are discussed, using the multimedia TEX/DVI document as a particular case of local document representation. Document conversion is viewed as a process which preserves document semantics while converting document syntax. Software engineering issues involved in the design of document translators are examined. These include the use of interpreters and intermediate data structures, binding-time considerations, object oriented approaches, software reuse and software sharing. Specific ODA related considerations which affect the faithfulness of the document conversion process are discussed. These include structure conversion, content architecture conversion, tree handling, font handling, dimension conversion, coordinate system translation and positioning. Two document translators were implemented, one for encoding and one for decoding. Both use a four layer program structure which promotes generic handling of content types and modularity. The design of common modules used by both translators as well as other multimedia system programs are described, including an ASN.1 coding module (two versions), Computer Graphics Metafile (CGM) module, font modules, buffer module and file module.
The work on 081, begun as part of the multimedia system, became a separate work area on the development of strategies for implementing a. general 081 layer. A key result was the development of a layer model consisting of six sublayers which extended existing layer models by including specific and generic sublayers in both the upper and lower layer interfaces. Finite state machine descriptions were developed to describe module functionality within the layer model. Strategies for realisation of the model included the development of a Pseudo Multitasking Operating System (PMOS) within which layer model components could be realised. Additional resource manager, timer, upper layer interface manager and lower laver interface manager modules were added to complete the layer functionality. To realise sublayer modules a program template and three-layer model were developed. Implementation of an 081 Session service using the layer model is described.
11
Jeong, Ki Tai. "A Common Representation Format for Multimedia Documents." Thesis, University of North Texas, 2002. https://digital.library.unt.edu/ark:/67531/metadc3336/.
Full textAbstract:
Multimedia documents are composed of multiple file format combinations, such as image and text, image and sound, or image, text and sound. The type of multimedia document determines the form of analysis for knowledge architecture design and retrieval methods. Over the last few decades, theories of text analysis have been proposed and applied effectively. In recent years, theories of image and sound analysis have been proposed to work with text retrieval systems and progressed quickly due in part to rapid progress in computer processing speed. Retrieval of multimedia documents formerly was divided into the categories of image and text, and image and sound. While standard retrieval process begins from text only, methods are developing that allow the retrieval process to be accomplished simultaneously using text and image. Although image processing for feature extraction and text processing for term extractions are well understood, there are no prior methods that can combine these two features into a single data structure. This dissertation will introduce a common representation format for multimedia documents (CRFMD) composed of both images and text. For image and text analysis, two techniques are used: the Lorenz Information Measurement and the Word Code. A new process named Jeong's Transform is demonstrated for extraction of text and image features, combining the two previous measurements to form a single data structure. Finally, this single data measurements to form a single data structure. Finally, this single data structure is analyzed by using multi-dimensional scaling. This allows multimedia objects to be represented on a two-dimensional graph as vectors. The distance between vectors represents the magnitude of the difference between multimedia documents. This study shows that image classification on a given test set is dramatically improved when text features are encoded together with image features. This effect appears to hold true even when the available text is diffused and is not uniform with the image features. This retrieval system works by representing a multimedia document as a single data structure. CRFMD is applicable to other areas of multimedia document retrieval and processing, such as medical image retrieval, World Wide Web searching, and museum collection retrieval.
12
Stegmaier, Florian [Verfasser], and Harald [Akademischer Betreuer] Kosch. "Unified Retrieval in Distributed and Heterogeneous Multimedia Information Systems / Florian Stegmaier. Betreuer: Harald Kosch." Passau : Universitätsbibliothek der Universität Passau, 2014. http://d-nb.info/1053119267/34.
Full text
13
Chu, Wei 1966. "Auditory-based noise-robust audio classification algorithms." Thesis, McGill University, 2008. http://digitool.Library.McGill.CA:80/R/?func=dbin-jump-full&object_id=115863.
Full textAbstract:
The past decade has seen extensive research on audio classification algorithms which playa key role in multimedia applications, such as the retrieval of audio information from an audio or audiovisual database. However, the effect of background noise on the performance of classification has not been widely investigated. Motivated by the noise-suppression property of the early auditory (EA) model presented by Wang and Shamma, we seek in this thesis to further investigate this property and to develop improved algorithms for audio classification in the presence of background noise.<br>With respect to the limitation of the original analysis, a better yet mathematically tractable approximation approach is first proposed wherein the Gaussian cumulative distribution function is used to derive a new closed-form expression of the auditory spectrum at the output of the EA model, and to conduct relevant analysis. Considering the computational complexity of the original EA model, a simplified auditory spectrum is proposed, wherein the underlying analysis naturally leads to frequency-domain approximation for further reduction in the computational complexity. Based on this time-domain approximation, a simplified FFT-based spectrum is proposed wherein a local spectral self-normalization is implemented. An improved implementation of this spectrum is further proposed to calculate a so-called FFT-based auditory spectrum, which allows more flexibility in the extraction of noise-robust audio features.<br>To evaluate the performance of the above FFT-based spectra, speech/music/noise and noise/non-noise classification experiments are conducted wherein a support vector machine algorithm (SVMstruct) and a decision tree learning algorithm (C4.5) are used as the classifiers. Several features are used for the classification, including the conventional mel-frequency cepstral coefficient (MFCC) features as well as DCT-based and spectral features derived from the proposed FFT-based spectra. Compared to the conventional features, the auditory-related features show more robust performance in mismatched test cases. Test results also indicate that the performance of the proposed FFT-based auditory spectrum is slightly better than that of the original auditory spectrum, while its computational complexity is reduced by an order of magnitude.<br>Finally, to further explore the proposed FFT-based auditory spectrum from a practical audio classification perspective, a floating-point DSP implementation is developed and optimized on the TMS320C6713 DSP Starter Kit (DSK) from Texas Instruments.
14
Zhang, Dengsheng 1963. "Image retrieval based on shape." Monash University, School of Computing and Information Technology, 2002. http://arrow.monash.edu.au/hdl/1959.1/8688.
Full text
15
Arnold, Stephen. "Specification and efficient monitoring of local graph-based constraints in hypermedia systems." Diss., Georgia Institute of Technology, 1995. http://hdl.handle.net/1853/12537.
Full text
16
Evans, Paul. "A multimedia system to instruct novice users of online library catalogues." View thesis, 1996. http://library.nepean.uws.edu.au/about/staff/thesis.html.
Full text
17
Evans, Paul. "A multimedia system to instruct novice users of online library catalogues." Thesis, View thesis, 1996. http://hdl.handle.net/1959.7/uws:342.
Full textAbstract:
The research reported here focuses on the application of multimedia to the teaching of information skills in academic libraries. Specifically, the research project has involved the development and evaluation of a multimedia system to instruct novice users of online library catalogues. The research has included an investigation of the characteristics and needs of novice library users. The ways in which novices approach using library-based information technologies which may be applied to any instructional programme for teaching novices how to use library-based information technologies. The research project has involved the development of a comprehensive multimedia system based on the theoretical model. The multimedia system was designed using Macromedia Director v.4.04. The production techniques and operation of the multimedia system are described in some detail. The multimedia system was evaluated and tested using formative evaluation strategies. The evaluation involved the prototype system being reviewed by expert librarians, and multimedia producers, as well as novice users of online library catalogues. The information gathered during the evaluation was used to make suggestions about improvements to the design of the prototype. The results of the evaluation are reported and analysed.
18
Chan, Wing Sze. "Semantic search of multimedia data objects through collaborative intelligence." HKBU Institutional Repository, 2010. http://repository.hkbu.edu.hk/etd_ra/1171.
Full text
19
Girma, Berhe Hagos Brunie Lionel Pierson Jean-Marc. "Accès et adaptation de contenus multimédia pour les systèmes pervasifs ccess and adaptation of multimedia content for pervasive systems /." Villeurbanne : Doc'INSA, 2006. http://docinsa.insa-lyon.fr/these/pont.php?id=girma.
Full text
20
Lee, Jeannie Su Ann. "Mixed-initiative multimedia for mobile devices: design of a semantically relevant low latency system for news video recommendations." Diss., Georgia Institute of Technology, 2010. http://hdl.handle.net/1853/41189.
Full textAbstract:
The increasing ubiquity of networked mobile devices such as cell phones and PDAs has created new opportunities for the transmission and display of multimedia content. However, any mobile device has inherent resource constraints: low network bandwidth, small screen sizes, limited input methods, and low commitment viewing. Mobile systems that provide information display and access thus need to mitigate these various constraints. Despite progress in information retrieval and content recommendation, there has been less focus on issues arising from a network-oriented and mobile perspective.
This dissertation investigates a coordinated design approach to networked multimedia on mobile devices, and considers the abovementioned system perspectives. Within the context of accessing news video on mobile devices, the goal is to provide a cognitively palatable stream of videos and a seamless, low-latency user experience. Mixed-initiative---a method whereby intelligent services and users collaborate efficiently to achieve the user's goals, is the cornerstone of the system design and integrates user relevance feedback with a content recommendation engine and a content- and network-aware video buffer prefetching technique. These various components have otherwise been considered independently in other prior system designs.
To overcome limited interactivity, a mixed-initiative user interface was used to present a sequence of news video clips to the user, along with operations to vote-up or vote-down a video to indicate its relevance. On-screen gesture equivalents of these operations were also implemented to reduce user interface elements occupying the screen. Semantic relevancy was then improved by extracting and indexing the content of each video clip as text features, and using a Na"ive Bayesian content recommendation strategy that harnessed the user relevance feedback to tailor the subsequent video recommendations. With the system's knowledge of relevant videos, a content-aware video buffer prefetching scheme was then integrated, using the abovementioned feedback to lower the user perceived latency on the client-end.
As an information retrieval system consists of many interacting components, a client-server video streaming model is first developed for clarity and simplicity. Using a CNN news video clip database, experiments were then conducted using this model to simulate user scenarios. As the aim of improving semantic relevancy sometimes opposes user interface tools for interactivity and user perceived latency, a quantitative evaluation was done to observe the tradeoffs between bandwidth, semantic relevance, and user perceived latency. Performance tradeoffs involving semantic relevancy and user perceived latency were then predicted.
In addition, complementary human user subjective tests are conducted with actual mobile phone hardware running on the Google Android platform. These experiments suggest that a mixed-initiative approach is helpful for recommending news video content on a mobile device for overcoming the mobile limitations of user interface tools for interactivity and client-end perceived latency. Users desired interactivity and responsiveness while viewing videos, and were willing to sacrifice some content relevancy in order gain lower perceived latency.
Recommended future work includes expanding the content recommendation to incorporate viewing data from a large population, and the creation of a global hybrid content-based and collaborative filtering algorithm for better results. Also, based on existing user behaviour, users were reluctant to provide more input than necessary. Additional user experiments can be designed to quantify user attention and interest during video watching on a mobile device, and for better definition and incorporation of implicit user feedback.
21
Yapp, Lawrence. "Content-based indexing of MPEG video through the analysis of the accompanying audio /." Thesis, Connect to this title online; UW restricted, 1997. http://hdl.handle.net/1773/5835.
Full text
22
Hrubec, Thomas R. Rhodes Dent. "A web-based accounting instructional prototype for use in improving information system development in a corporate setting." Normal, Ill. : Illinois State University, 2004. http://wwwlib.umi.com/cr/ilstu/fullcit?p3128277.
Full textAbstract:
Thesis (Ed. D.)--Illinois State University, 2004.<br>Title from title page screen, viewed Jan. 21, 2005. Dissertation Committee: Dent M. Rhodes (chair), Temba C. Bassoppo-Moyo, Kenneth F. Jerich, W. Max Rexroad. Includes bibliographical references (leaves 143-149) and abstract. Also available in print.
23
Lu, Shiyang. "Large-scale interactive exploratory visual search." Thesis, The University of Sydney, 2014. http://hdl.handle.net/2123/12029.
Full textAbstract:
Large scale visual search has been one of the challenging issues in the era of big data. It demands techniques that are not only highly effective and efficient but also allow users conveniently express their information needs and refine their intents. In this thesis, we focus on developing an exploratory framework for large scale visual search. We also develop a number of enabling techniques in this thesis, including compact visual content representation for scalable search, near duplicate video shot detection, and action based event detection. We propose a novel scheme for extremely low bit rate visual search, which sends compressed visual words consisting of vocabulary tree histogram and descriptor orientations rather than descriptors. Compact representation of video data is achieved through identifying keyframes of a video which can also help users comprehend visual content efficiently. We propose a novel Bag-of-Importance model for static video summarization. Near duplicate detection is one of the key issues for large scale visual search, since there exist a large number nearly identical images and videos. We propose an improved near-duplicate video shot detection approach for more effective shot representation. Event detection has been one of the solutions for bridging the semantic gap in visual search. We particular focus on human action centred event detection. We propose an enhanced sparse coding scheme to model human actions. Our proposed approach is able to significantly reduce computational cost while achieving recognition accuracy highly comparable to the state-of-the-art methods. At last, we propose an integrated solution for addressing the prime challenges raised from large-scale interactive visual search. The proposed system is also one of the first attempts for exploratory visual search. It provides users more robust results to satisfy their exploring experiences.
24
Araújo, Rodrigo Cascão 1975. "Alinhamento de metadados da indústria de broadcast multimidia no contexto da TV digital com a web semântica." [s.n.], 2013. http://repositorio.unicamp.br/jspui/handle/REPOSIP/260822.
Full textAbstract:
Orientador: Ivan Luiz Marques Ricarte<br>Tese (doutorado) - Universidade Estadual de Campinas, Faculdade de Engenharia Elétrica e de Computação<br>Made available in DSpace on 2018-08-22T20:42:17Z (GMT). No. of bitstreams: 1
Araujo_RodrigoCascao_D.pdf: 4349917 bytes, checksum: 0c79f0eb04ac45b3285c6933d153852c (MD5)
Previous issue date: 2013<br>Resumo: A integração da Internet e das tecnologias de comunicação móveis com as plataformas de televisão têm provido aos telespectadores novos serviços interativos de conteúdo digital. Devido a estes fatores, os equipamentos para o consumidor têm se tornado cada vez mais sofisticados, suportando uma variedade de conteúdos e conectividade com outras redes e dispositivos. A TV digital é uma plataforma híbrida que combina elementos da televisão tradicional com a Internet, provendo ao usuário o acesso a uma diversidade de conteúdos de mídia interativa. Com o crescimento do volume e da diversidade de serviços e conteúdos multimídia, a televisão está enfrentando os mesmos desafios de complexidade e excesso de informações que já vinham sendo encarados por outras mídias digitais relacionadas com a Internet. A tecnologia de metadados pode ser uma alternativa para lidar com esta complexidade de serviços e conteúdos digitais de forma prática e eficiente. Metadados são dados que complementam as informações digitais dos conteúdos multimídia com o objetivo de descrevê-los de forma sintática e semântica, facilitando a estruturação e o gerenciamento de grandes volumes de informação. O uso de metadados em TV digital não se restringe a construção de um ferramental de busca e indexação de conteúdos multimídia, e abre oportunidade para o desenvolvimento de uma gama de serviços inovadores. Atualmente existem diversas especificações de metadados utilizadas pela indústria de broadcast multimídia em redes de TV digital. Além disso, existem na Internet diversos repositórios de informação baseados em metadados que complementam as informações de metadados da TV digital. Contudo, como os padrões de metadados da TV digital e da Internet são baseados em diferentes especificações não relacionadas, surge o problema de como integrar estas informações, visando criar novos serviços para telespectadores que utilizem tanto informações de metadados da TV digital como informações de metadados da Internet. Esta tese de doutorado propõe um processo para alinhamento das especificações de metadados existentes em redes abertas de transmissão e recepção de TV digital terrestre com ontologias orientadas para a descrição de domínios de conhecimento específicos existentes em repositórios da Internet, utilizando tecnologias propostas pelo W3C para a Web Semântica. O processo proposto permitirá que o usuário da TV digital possa facilmente pesquisar conteúdos de interesse a partir da grade de programação dos canais existentes e dos conteúdos já gravados em seu receptor; receber sugestões de conteúdos para exibição ou gravação conforme o seu perfil e interesse; enriquecer sua experiência de assistir televisão acessando informações complementares sobre os programas transmitidos como sinopses, críticas especializadas, histórico do elenco e direção, premiações recebidas, fotos, vídeos e conteúdos relacionados disponíveis para livre acesso via Internet; entre outras funções. A presente proposta foi validada através de uma prova de conceito implementada em um receptor híbrido de TV digital, que demonstrou a viabilidade de sua operacionalização sem a necessidade de impactar os padrões utilizados no Brasil para transmissão de sinal de TV digital terrestre (ISDB-T)<br>Abstract: The integration of the Internet and communication technologies with mobile TV platforms has provided viewers with new interactive services for digital content. Due to these factors, the equipment for the consumer have become increasingly sophisticated, supporting a variety of content and connectivity with other networks and devices. Digital TV is a hybrid platform that combines elements of traditional television with the Internet, providing the user access to a variety of interactive media content. With the growth in the volume and diversity of services and multimedia content, television is experiencing the same challenges of complexity and information overload that were already being seen by other digital media related to the Internet. The metadata technology can be an alternative to deal with this complexity of digital content and services in a practical and efficient way. Metadata is data that supplement the information of digital multimedia contents in order to describe them in a syntactic and semantic form, facilitating the structuring and management of large volumes of information. The use of metadata in digital TV is not restricted to building a tool for search and indexing of multimedia content, and opens opportunities to develop a range of innovative services. Currently there are several metadata specifications used by the broadcast industry in multimedia digital TV networks. Moreover, there are many metadata-based information repositories in the Internet that complement the metadata information of digital TV. However, as the metadata standards of digital TV and Internet are based on different unrelated specifications, a problem arises of how to integrate this information in order to create new services for viewers using both metadata information of digital TV as metadata information of Internet. This thesis proposes a method for alignment of existing metadata specifications in open networks for transmission and reception of digital terrestrial TV with ontologies oriented for describing specific domains of knowledge existing in Internet repositories, using technologies proposed by the W3C for the Web semantics. The proposed process allows the digital TV user to easily search for content of interest from the program schedule of the existing channels and content already recorded in the receiver; to receive suggestions of content for viewing or recording according to his interest and profile; to enrich the experience of watching television by accessing additional information about the transmitted programs as synopses, specialized reviews, history of cast and direction, awards received, photos, videos and related content available for free access via Internet; among other functions. This proposal has been validated through a proof of concept implemented in a hybrid digital TV receiver, which demonstrated the feasibility of its implementation without impacting the standards used in Brazil for signal transmission of digital terrestrial TV (ISDB-T)<br>Doutorado<br>Engenharia de Computação<br>Doutor em Engenharia Elétrica
25
Dunlop, Mark David. "Multimedia information retrieval." Thesis, University of Glasgow, 1991. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.358626.
Full text
26
Eibl, Maximilian, Jens Kürsten, and Marc Ritter. "Workshop Audiovisuelle Medien." Universitätsbibliothek Chemnitz, 2009. http://nbn-resolving.de/urn:nbn:de:bsz:ch1-200900957.
Full textAbstract:
Audiovisuelle Medien stellen Archive vor zunehmende Probleme. Ein stark wachsender (Web-)TV-Markt mit Sende- oder Rohmaterial, zunehmender Einsatz von medial aufbereitetem Lehrmaterial in Schulen, Hochschulen und Firmen, die Verbreitung der Videoanalyse als Forschungs- und Lehrmethode, die Ausbreitung von Überwachungskameras sowie die immer günstigeren Produktionsbedingungen vom professionellen Produzenten bis zum Heimvideo sind nur einige Stichworte um die neuen quantitativen Dimensionen zu umreißen. Die archivarischen und dokumentarischen Werkzeuge sind heute mit dieser Situation überfordert.
Der Workshop versucht hier Probleme und Lösungsmöglichkeiten zu umreißen und beschäftigt sich mit den technologischen Fragestellungen rund um die Archivierung audiovisueller Medien, seien es analoge, digitalisierte oder digitale Medien. Dabei werden zum einen die technologischen Probleme angesprochen, die zum Aufbau und Management eines Archivs bewältigt werden müssen. Zum anderen wird der praktische Einsatz von der Gestaltung der Benutzungsoberfläche bis zur Frage des Umgangs mit kritischem Material diskutiert.
27
Grande, Aleksander. "A Multimedia Approach to Medical Information Retrieval." Thesis, Norwegian University of Science and Technology, Department of Computer and Information Science, 2009. http://urn.kb.se/resolve?urn=urn:nbn:no:ntnu:diva-8966.
Full textAbstract:
<p>From the discovery of DNA by Francis H. C. Crick and James D. Watson in 1953 there have been conducted a lot of research in the field of DNA. Up through the years technological breakthroughs has made DNA sequencing more faster and more available, and has gone from being a very manual task to be highly automated. In 1990 the Human Genome Project was started and the research in DNA skyrocketed. DNA was sequenced faster and faster throughout the 1990s, and more projects with goals of sequencing other specie's DNA was initiated. All this research of DNA led to vast amounts of DNA sequences, but the techniques for searching through these DNA sequences was not developed at the same pace. The need for new and improved methods of searching in DNA is becoming more and more evident. This thesis explores the possibilities of using content based information retrieval to search through DNA sequences. This is a bold proposition but can have great benefits if successfully implemented. By transforming DNA sequences to images, and indexing these images with a content based information retrieval system it can be possible to achieve a successful DNA search. We discover that this is possible but further work has to be done in order to solve some discovered issues with the transforming of the DNA sequences to images.</p>
28
Torres, JoseÌ. "Visual information retrieval through interactive multimedia queries." Thesis, Lancaster University, 2005. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.431417.
Full text
29
Jose, Joemon M. "An integrated approach for multimedia information retrieval." Thesis, Robert Gordon University, 1998. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.266758.
Full text
30
Gonzalez-Gallardo, Carlos. "Automatic Multilingual Multimedia Summarization and Information Retrieval." Thesis, Avignon, 2019. http://www.theses.fr/2019AVIG0234.
Full textAbstract:
Alors que les sources multimédias sont massivement disponibles en ligne, aider les utilisateurs à comprendre la grande quantité d'information générée est devenu un problème majeur. Une façon de procéder consiste à résumer le contenu multimédia, générant ainsi des versions abrégées et informatives des sources. Cette thèse aborde le sujet du résumé automatique (texte et parole) dans un contexte multilingue. Elle a été réalisée dans le cadre du projet CHISTERA-ANR Accès multilingue à l'information (AMIS). Le résumé multimédia basé sur le texte utilise des transcriptions pour produire des résumés qui peuvent être présentés sous forme textuelle ou dans leur format d'origine. La transcription des sources multimédia peut être effectuée manuellement ou automatiquement par un système de Reconnaissance automatique de la parole (RAP). Les transcriptions peuvent différer de la langue écrite car la source étant parlée. De plus, ces transcriptions manquent d'informations syntaxiques. Par exemple, les majuscules et les signes de ponctuation sont absents, ce qu'implique des phrases inexistantes. Pour palier ce problème nous proposons une méthode pour la détection des limites de phrases (DLP). Elle est orientée aux transcriptions et utilise des caractéristiques textuelles pour séparer les Unités sémantiques (US) dans un contexte multilingue. Notre approche, basée sur des vecteurs d'information des n-grammes de lettres et des Réseaux de neurones convolutifs, dépasse les performances des méthodes état-de-l'art en identifiant correctement les frontières des US en français, anglais et arabe standard. Nous étudions ensuite l'impact des corpora entre-domaines en arabe standard, en montrant que le raffinement d'un modèle, conçu initialement avec un grand corpus hors du domaine, avec un petit corpus du domaine améliore la performance de la DLP. Enfin, nous étendons ARTEX, un résumeur textuel extractif état de l'art, pour traiter de documents en arabe standard en adaptant ses modules de prétraitement. Les résumés peuvent être présentés sous une forme textuelle ou dans leur format multimédia original en alignant les US sélectionnées. En ce qui concerne le résumé multimédia basée sur l'audio, nous introduisons une méthode extractive qui représente l'informativité de la source à partir de ses caractéristiques audio pour sélectionner les segments les plus pertinents pour le résumé. Pendant la phase d'entraînement, notre méthode utilise les transcriptions des documents audio pour créer un modèle informatif qui établit une correspondance entre un ensemble de caractéristiques audio et une mesure de divergence. Dans notre système, les transcriptions ne sont plus nécessaires pour résumer des nouveaux documents audio. Les résultats obtenus sur un schéma multi-évaluation montrent que notre approche génère des résumés compréhensibles et informatifs. Nous avons étudié également les mesures d'évaluation et nous avons développé la méthode Window-based Sentence Boundary Evaluation (WiSeBE), une métrique semi-supervisée basée sur le (dés)accord multi-références. On examine si l'évaluation basée sur une référence unique d'un système de DLP suffit à évaluer son performance. Nous explorons également la possibilité de mesurer la qualité des transcriptions automatiques en fonction de leur informativité. De plus, nous étudions dans quelle mesure le résumé automatique peut compenser les problèmes posés au cours de la transcription. Enfin, nous étudions comment les mesures d'évaluation d'informativité peuvent être étendues pour l'évaluation de l'intérêt des passages textuels<br>As multimedia sources have become massively available online, helping users to understandthe large amount of information they generate has become a major issue. Oneway to approach this is by summarizing multimedia content, thus generating abridgedand informative versions of the original sources. This PhD thesis addresses the subjectof text and audio-based multimedia summarization in a multilingual context. It hasbeen conducted within the framework of the Access Multilingual Information opinionS(AMIS) CHISTERA-ANR project, whose main objective is to make informationeasy to understand for everybody.Text-based multimedia summarization uses transcripts to produce summaries thatmay be presented either as text or in their original format. The transcription of multimediasources can be done manually or automatically by an Automatic Speech Recognition(ASR) system. The transcripts produced using either method differ from wellformedwritten language given their source is mostly spoken language. In addition,ASR transcripts lack syntactic information. For example, capital letters and punctuationmarks are unavailable, which means sentences are nonexistent. To deal with thisproblem, we propose a Sentence Boundary Detection (SBD) method for ASR transcriptswhich uses textual features to separate the Semantic Units (SUs) within an automatictranscript in a multilingual context. Our approach, based on subword-level informationvectors and Convolutional Neural Networks (CNNs), overperforms baselines by correctlyidentifying SU borders for French, English and Modern Standard Arabic (MSA).We then study the impact of cross-domain datasets over MSA, showing that tuning amodel that was originally trained with a big out-of-domain dataset with a small indomaindataset normally improves SBD performance. Finally, we extend ARTEX, astate-of-the-art extractive text summarization method, to process documents in MSA byadapting preprocessing modules. The resulting summaries can be presented as plaintext or in their original multimedia format by aligning the selected SUs.Concerning audio-based summarization, we introduce an extractive method whichrepresents the informativeness of the source based on its audio features to select the segmentsthat are most pertinent to the summary. During the training phase, our methoduses available transcripts of the audio documents to create an informativeness modelwhich maps a set of audio features with a divergence value. Subsequently, when summarizingnew audio documents, transcripts are not needed anymore. Results over amulti-evaluator scheme show that our approach provides understandable and informative summaries.Evaluation measures is also a field which we deal with. We developWindow-basedSentence Boundary Evaluation (WiSeBE), a semi-supervised metric based on multireference(dis)agreement, that questions if evaluating an automatic SBD system basedon a single reference is enough to conclude how well the system is performing. We alsoexplore the possibility of measuring the quality of an automatic transcript based on itsinformativeness. In addition, we study to what extent automatic summarization maycompensate for the problems raised during the transcription phase. Lastly, we studyhow text informativeness evaluation measures may be extended to passage interestingnessevaluation
31
Bracamonte, Nole Teresa Jacqueline. "Improving web multimedia information retrieval using social data." Tesis, Universidad de Chile, 2018. http://repositorio.uchile.cl/handle/2250/168681.
Full textAbstract:
Tesis para optar al grado de Doctora en Ciencias, Mención Computación<br>Buscar contenido multimedia es una de las tareas más comunes que los usuarios realizan en la Web. Actualmente, los motores de búsqueda en la Web han mejorado la precisión de sus búsquedas de contenido multimedia y ahora brindan una mejor experiencia de usuarios. Sin embargo, estos motores aún no logran obtener resultados precisos para consultas que no son comunes, y consultas que se refieren a conceptos abstractos. En ambos escenarios, la razón principal es la falta de información preliminar.
Esta tesis se enfoca en mejorar la recuperación de información multimedia en la Web usando datos generados a partir de la interacción entre usuarios y recursos multimedia. Para eso, se propone mejorar la recuperación de información multimedia desde dos perspectivas: (1) extrayendo conceptos relevantes a los recursos multimedia, y (2) mejorando las descripciones multimedia con datos generados por el usuario. En ambos casos, proponemos sistemas que funcionan independientemente del tipo de multimedia, y del idioma de los datos de entrada.
En cuanto a la identificación de conceptos relacionados a objetos multimedia, desarrollamos un sistema que va desde los resultados de búsqueda específicos de la consulta hasta los conceptos detectados para dicha consulta. Nuestro enfoque demuestra que podemos aprovechar la vista parcial de una gran colección de documentos multimedia para detectar conceptos relevantes para una consulta determinada. Además, diseñamos una evaluación basada en usuarios que demuestra que nuestro algoritmo de detección de conceptos es más sólido que otros enfoques similares basados en detección de comunidades.
Para mejorar la descripción multimedia, desarrollamos un sistema que combina contenido audio-visual de documentos multimedia con información de su contexto para mejorar y generar nuevas anotaciones para los documentos multimedia. Específicamente, extraemos datos de clicks de los registros de consultas y usamos las consultas como sustitutos para las anotaciones manuales. Tras una primera inspección, demostramos que las consultas proporcionan una descripción concisa de los documentos multimedia.
El objetivo principal de esta tesis es demostrar la relevancia del contexto asociado a documentos multimedia para mejorar el proceso de recuperación de documentos multimedia en la Web. Además, mostramos que los grafos proporcionan una forma natural de modelar problemas multimedia.<br>Fondef D09I-1185, CONICYT-PCHA/Doctorado Nacional/2013-63130260, Apoyo a estadías corta de la Escuela de Postgrado de la U. de Chile, y el Núcleo Milenio CIWS
32
Vila, Duran Marius. "Information theory techniques for multimedia data classification and retrieval." Doctoral thesis, Universitat de Girona, 2015. http://hdl.handle.net/10803/302664.
Full textAbstract:
We are in the information age where most data is stored in digital format. Thus, the management of digital documents and videos requires the development of efficient techniques for automatic analysis. Among them, capturing the similarity or dissimilarity between different document images or video frames are extremely important.
In this thesis, we first analyze for several image resolutions the behavior of three different families of image-based similarity measures applied to invoice classification. In these three set of measures, the computation of the similarity between two images is based, respectively, on intensity differences, mutual information, and normalized compression distance. As the best results are obtained with mutual information-based measures, we proceed to investigate the application of three different Tsallis-based generalizations of mutual information for different entropic indexes. These three generalizations derive respectively from the Kullback-Leibler distance, the difference between entropy and conditional entropy, and the Jensen-Shannon divergence.
In relation to digital video processing, we propose two different information-theoretic approaches based, respectively, on Tsallis mutual information and Jensen-Tsallis divergence to detect the abrupt shot boundaries of a video sequence and to select the most representative keyframe of each shot.
Finally, Shannon entropy has been commonly used to quantify the image informativeness. The main drawback of this measure is that it does not take into account the spatial distribution of pixels. In this thesis, we analyze four information-theoretic measures that overcome this limitation. Three of them (entropy rate, excess entropy, and erasure entropy) consider the image as a stationary stochastic process, while the fourth (partitional information) is based on an information channel between image regions and histogram bins<br>Ens trobem a l’era de la informació on la majoria de les dades s’emmagatzemen en format digital. Per tant, la gestió de documents i vídeos digitals requereix el desenvolupament de tècniques eficients per a l’anàlisi automàtic. Entre elles, la captura de la similitud o dissimilitud entre diferents imatges de documents o fotogrames de vídeo és extremadament important.
En aquesta tesi, analitzem, a diverses resolucions d’imatge, el comportament de tres famílies diferents de mesures basades en similitud d’imatges i aplicades a la classificació de factures. En aquests tres conjunt de mesures, el càlcul de la similitud entre dues imatges es basa, respectivament, en les diferències d’intensitat, en la informació mútua, i en la distància de compressió normalitzada. Degut a que els millors resultats s’obtenen amb les mesures basades en la informació mútua, es procedeix a investigar l’aplicació de tres generalitzacions de la informació mútua basades en Tsallis en diferents índexs entròpics. Aquestes tres generalitzacions es deriven respectivament de la distància de Kullback-Leibler, la diferència entre l’entropia i entropia condicional, i la divergència de Jensen-Shannon.
En relació al processament de vídeo digital, proposem dos enfocaments diferents de teoria de la informació basats respectivament en la informació mútua de Tsallis i en la divergència de Jensen-Tsallis, per detectar els límits d’un pla cinematogràfic en una seqüència de vídeo i per seleccionar el fotograma clau més representatiu de cada pla.
Finalment, l’entropia de Shannon s’ha utilitzat habitualment per quantificar la informativitat d’una imatge. El principal inconvenient d’aquesta mesura és que no té en compte la distribució espacial dels píxels. En aquesta tesi, s’analitzen quatre mesures de teoria de la informació que superen aquesta limitació. Tres d’elles (entropy rate, excess entropy i erasure entropy) consideren la imatge com un procés estocàstic estacionari, mentre que la quarta (partitional information) es basa en un canal d’informació entre les regions d’una imatge i els intervals de l’histograma
33
Guglielmo, Eugene J. "Intelligent information retrieval for a multimedia database using captions." Thesis, Monterey, California. Naval Postgraduate School, 1992. http://hdl.handle.net/10945/23705.
Full textAbstract:
This report describes an intelligent information retrieval system, MARIE, that employs natural language processing techniques for indexing and retrieving multimedia data. Captions describe photographs from the Naval Air Warfare Center Weapons Division, China Lake, California; the captions were written in English consisting mostly of noun phrases. For our work, an object-oriented type hierarchy represents semantic knowledge. Captions are parsed to produce a logical form, from which nouns and verbs are extracted to form keyword files. User queries are also specified in natural language. A two-phase match process is employed between the query and database. A coarse-grain match searches the keyword files and issues SQL queries to a relational database as necessary to find candidate captions for further analysis. A fine-grain match then compares the logical form of the query to the logical form for each caption. A list of caption IDs and accompanying match scores is then presented to the user, who can view the image and supporting data. A companion technical report contains the programs for the system discussed here.
34
Lin, Lin. "Multimedia Data Mining and Retrieval for Multimedia Databases Using Associations and Correlations." Scholarly Repository, 2010. http://scholarlyrepository.miami.edu/oa_dissertations/434.
Full textAbstract:
With the explosion in the complexity and amount of pervasive multimedia data, there are high demands of multimedia services and applications in various areas for people to easily access and distribute multimedia data. Facing with abundance multimedia resources but inefficient and rather old-fashioned keyword-based information retrieval approaches, a content-based multimedia information retrieval (CBMIR) system is required to (i) reduce the dimension space for storage saving and computation reduction; (ii) advance multimedia learning methods to accurately identify target semantics for bridging the semantics between low-level/mid-level features and high-level semantics; and (iii) effectively search media content for dynamical media delivery and enable the extensive applications to be media-type driven. This research mainly focuses on multimedia data mining and retrieval system for multimedia databases by addressing some main challenges, such as data imbalance, data quality, semantic gap, user subjectivity and searching issues. Therefore, a novel CBMIR system is proposed in this dissertation. The proposed system utilizes both association rule mining (ARM) technique and multiple correspondence analysis (MCA) technique by taking into account both pattern discovery and statistical analysis. First, media content is represented by the global and local low-level and mid-level features and stored in the multimedia database. Second, a data filtering component is proposed in the system to improve the data quality and reduce the data imbalance. To be specific, the proposed filtering step is able to vertically select features and horizontally prune instances in multimedia databases. Third, a new learning and classification method mining weighted association rules is proposed in the retrieval system. The MCA-based correlation is used to generate and select the weighted N-feature-value pair rules, where the N varies from one to many. Forth, a ranking method independent of classifiers is proposed in the system to sort the retrieved results and put the most interesting ones on the top of the browsing list. Finally, a user interface is implemented in CBMIR system that allows the user to choose his/her interested concept, searches media based on the target concept, ranks the retrieved segments using the proposed ranking algorithm, and then displays the top-ranked segments to the user. The system is experimented with various high-level semantics from TRECVID benchmark data sets. TRECVID sound and vision data is a large data set, includes various types of videos, and has very rich semantics. Overall, the proposed system achieves promising results in comparison with the other well-known methods. Moreover, experiments that compare each component with some other famous algorithms are conducted. The experimental results show that all proposed components improve the functionalities of the CBMIR system, and the proposed system reaches effectiveness, robustness and efficiency for a high-dimensional multimedia database.
35
Schmitt, Ingo. "Ähnlichkeitssuche in Multimedia-Datenbanken Retrieval, Suchalgorithmen und Anfragebehandlung." München Wien Oldenbourg, 2004. http://deposit.ddb.de/cgi-bin/dokserv?id=2708331&prov=M&dok_var=1&dok_ext=htm.
Full text
36
Morgenroth, Karlheinz. "Kontextbasiertes Information-Retrieval : Modell, Konzeption und Realisierung kontextbasierter Information-Retrieval-Systeme /." Berlin : Logos, 2006. http://deposit.ddb.de/cgi-bin/dokserv?id=2786087&prov=M&dok_var=1&dok_ext=htm.
Full text
37
Laus, Frank O. "Informationsrecherche in Hypertext- und Multimedia-Dokumenten : Entwicklung eines kognitiven Navigationsmodells /." Wiesbaden : Wiesbaden : Dt. Univ.-Verl. ; Gabler, 2001. http://bvbr.bib-bvb.de:8991/F?func=service&doc_library=BVB01&doc_number=009496395&line_number=0001&func_code=DB_RECORDS&service_type=MEDIA.
Full text
38
YU, HONGMING. "A PERSONALIZED INFORMATION ENVIRONMENT SYSTEM FOR INFORMATION RETRIEVAL." University of Cincinnati / OhioLINK, 2003. http://rave.ohiolink.edu/etdc/view?acc_num=ucin1060875911.
Full text
39
Almeida, Junior Jurandy Gomes de 1983. "Recuperação de vídeos comprimidos por conteúdo." [s.n.], 2011. http://repositorio.unicamp.br/jspui/handle/REPOSIP/275706.
Full textAbstract:
Orientador: Ricardo da Silva Torres<br>Tese (doutorado) - Universidade Estadual de Campinas, Instituto de Computação<br>Made available in DSpace on 2018-08-19T18:14:01Z (GMT). No. of bitstreams: 1
AlmeidaJunior_JurandyGomesde_D.pdf: 7003455 bytes, checksum: 9f2b66a600d6b6ae595b02265ceb1585 (MD5)
Previous issue date: 2011<br>Resumo: Avanços recentes na tecnologia têm permitido o aumento da disponibilidade de dados de vídeo, criando grandes coleções de vídeo digital. Isso tem despertado grande interesse em sistemas capazes de gerenciar esses dados de forma eficiente. Fazer uso eficiente de informações de vídeo requer o desenvolvimento de ferramentas poderosas capazes de extrair representações semânticas de alto nível a partir de características de baixo nível do conteúdo de vídeo. Devido à complexidade desse material, existem cinco desafios principais na concepção de tais sistemas: (1) dividir o fluxo de vídeo em trechos manuseáveis de acordo com a sua estrutura de organização, (2) implementar algoritmos para codificar as propriedades de baixo nível de um trecho de vídeo em vetores de características, (3) desenvolver medidas de similaridade para comparar esses trechos a partir de seus vetores, (4) responder rapidamente a consultas por similaridade sobre uma enorme quantidade de sequências de vídeo e (5) apresentar os resultados de forma amigável a um usuário. Inúmeras técnicas têm sido propostas para atender a tais requisitos. A maioria dos trabalhos existentes envolve algoritmos e métodos computacionalmente custosos, em termos tanto de tempo quanto de espaço, limitando a sua aplicação apenas ao ambiente acadêmico e/ou a grandes empresas. Contrário a essa tendência, o mercado tem mostrado uma crescente demanda por dispositivos móveis e embutidos. Nesse cenário, é imperativo o desenvolvimento de técnicas tanto eficazes quanto eficientes a fim de permitir que um público maior tenha acesso a tecnologias modernas. Nesse contexto, este trabalho apresenta cinco abordagens originais voltadas a análise, indexação e recuperação de vídeos digitais. Todas essas contribuições são somadas na construção de um sistema de gestão de vídeos por conteudo computacionalmente rápido, capaz de atingir a um padrão de qualidade similar, ou até mesmo superior, a soluções atuais<br>Abstract: Recent advances in the technology have enabled the increase of the availability of video data, creating large digital video collections. This has spurred great interest in systems that are able to manage those data in a efficient way. Making efficient use of video information requires the development of powerful tools to extract high-level semantics from low-level features of the video content. Due to the complexity of the video material, there are five main challenges in designing such systems: (1) to divide the video stream into manageable segments according to its organization structure; (2) to implement algorithms for encoding the low-level features of each video segment into feature vectors; (3) to develop similarity measures for comparing these segments by using their feature vectors; (4) to quickly answer similarity queries over a huge amount of video sequences; and (5) to present the list of results in a user-friendly way. Numerous techniques have been proposed to support such requirements. Most of existing works involve algorithms and methods which are computationally expensive, in terms of both time and space, limiting their application to the academic world and/or big companies. Contrary to this trend, the market has shown a growing demand for mobile and embedded devices. In this scenario, it is imperative the development of techniques so effective as efficient in order to allow more people have access to modern technologies. In this context, this work presents five novel approaches for the analysis, indexing, and retrieval of digital videos. All these contributions are combined to create a computationally fast system for content-based video management, which is able to achieve a quality level similar, or even superior, to current solutions<br>Doutorado<br>Ciência da Computação<br>Doutor em Ciência da Computação
40
Mohan, Kondrahalli Chowdappa. "Choice of retrieval techniques for a multi-strategy retrieval system." Thesis, University of Sheffield, 1987. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.287488.
Full text
41
Taylor, Steven Joseph. "Children's usage of an information retrieval system /." Access Digital Full Text version, 1992. http://pocketknowledge.tc.columbia.edu/home.php/bybib/11230162.
Full textAbstract:
Thesis (Ed.D.)--Teachers College, Columbia University, 1992.<br>Includes tables. Typescript; issued also on microfilm. Sponsor: Robert O. McClintock. Dissertation Committee: Robert P. Taylor. Includes bibliographical references (leaves 149-157).
42
Tarakci, Hilal. "An Ontology-based Multimedia Information Management System." Master's thesis, METU, 2008. http://etd.lib.metu.edu.tr/upload/12609865/index.pdf.
Full textAbstract:
In order to manage the content of multimedia data, the content must be annotated. Although any user-defined annotation is acceptable, it is preferable if systems agree on the same annotation format. MPEG-7 is a widely accepted standard for multimedia content annotation. However, in MPEG-7, semantically identical metadata can be represented in multiple ways due to lack of precise semantics in its XML-based syntax. Unfortunately this prevents metadata interoperability. To overcome this problem, MPEG-7 standard is translated into an ontology. In this thesis, MPEG-7 ontology is used on top and the given user-defined ontologies are attached to the MPEG-7 ontology via a user friendly interface, thus building MPEG-7 based ontologies automatically. Our proposed system is an ontology-based multimedia information management framework due to its modular
architecture, ease of integrating with domain specific ontologies naturally and automatic harmonization of MPEG-7 ontology and domain-specific ontologies. Integration with domain specific ontologies is carried out by enabling import of
domain ontologies via a user-friendly interface which makes the system independent of application domains.
43
Cheng, Jiandong. "Query interface for multimedia database system." Thesis, National Library of Canada = Bibliothèque nationale du Canada, 1998. http://www.collectionscanada.ca/obj/s4/f2/dsk2/ftp01/MQ28408.pdf.
Full text
44
Fourel, Franck. "Modélisation, indexation et recherche de documents structurés." Phd thesis, Université Joseph Fourier (Grenoble), 1998. http://tel.archives-ouvertes.fr/tel-00004888.
Full textAbstract:
Les systèmes actuels de recherche de documents électroniques, que ce soit des systèmes de gestion de bases de données ou des systèmes de recherche d'informations, n'exploitent pas suffisament la richesse des documents. Les uns n'analysent pas le contenu des documents et se laissent diriger par la structure du document alors que les autres délaissent l'aspect structurel en s'appuyant sur des méthodes trop peu adaptées aux nouvelles caractéristiques de ces documents. Le but de notre travail, situé à l'intersection de ces deux types de systèmes, est de réconcilier les différentes modalités d'accès aux documents électroniques et de rendre accessible tout document ou toute partie de documents qui peut résoudre le problème d'informations d'un utilisateur. Notre travail comporte plusieurs phases : la définition de modèles de représentation des documents structurés ainsi que de leurs composantes monomédias et multimédias (texte et image fixe) et la mise en place d'un processus d'indexation structurelle support du processus d'interrogation. Le modèle de représentation des documents structurés s'articule autour de trois relations de structure que nous avons particulièrement identifiées dans les documents textuels : la relation de composition, la relation de séquence et la relation de référence. Elles établissent l'organisation syntaxique des parties des documents, appelées éléments de structure, qui comme nous le montrons, possède une organisation duale, la structure sémantique. Nous exploitons les caractéristiques de cette dernière pour définir des propriétés sur les descripteurs des éléments de structure. Ces propriétés sont formalisées par la notion de portées des attributs et par la classification des attributs qui s'en suit. Pour chaque attribut d'un élément de structure, sa portée indique les autres éléments de structure concernés par l'attribut et par sa valeur. C'est en suivant les relations de structure que nous retrouvons les éléments concernés, puis nous leur assignons un attribut et une valeur dépendante de la valeur de l'attribut de l'élément qui est à la source de l'information. L'application des portées fournit une représentation du document au sein de laquelle les informations, si elles ne sont pas modifiées, sont mieux réparties et pour laquelle la plupart des informations sont explicitées pour chaque élément de structure et sont rendues dépendantes les unes des autres. Le processus d'interrogation utilise ces dépendances pour retrouver le ou les éléments de structure pertinents d'un document structuré. Nous avons validé ce travail par le développement du prototype my Personal Daily News qui permet d'interroger une base constituée de quotidiens d'informations en mêlant dans les requêtes des critères structurels et des critères de contenu. Nous montrons ainsi que notre approche rend des éléments accessibles et augmente la flexibilité d'interrogation en autorisant une connaissance imparfaite de la structure des documents.
45
Kurz, Thomas [Verfasser], Harald [Akademischer Betreuer] Kosch, and Sören [Akademischer Betreuer] Auer. "Adapting Semantic Web Information Retrieval to Multimedia / Thomas Kurz ; Harald Kosch, Sören Auer." Passau : Universität Passau, 2020. http://d-nb.info/1215337574/34.
Full text
46
Zhu, Bin, and Hsinchun Chen. "Validating a Geographic Image Retrieval System." Wiley Periodicals, Inc, 2000. http://hdl.handle.net/10150/105934.
Full textAbstract:
Artificial Intelligence Lab, Department of MIS, University of Arizona<br>This paper summarizes a prototype geographical image
retrieval system that demonstrates how to integrate image
processing and information analysis techniques to
support large-scale content-based image retrieval. By
using an image as its interface, the prototype system
addresses a troublesome aspect of traditional retrieval
models, which require users to have complete knowledge
of the low-level features of an image. In addition
we describe an experiment to validate the performance
of this image retrieval system against that of human
subjects in an effort to address the scarcity of research
evaluating performance of an algorithm against that of
human beings. The results of the experiment indicate
that the system could do as well as human subjects in
accomplishing the tasks of similarity analysis and image
categorization. We also found that under some circumstances
texture features of an image are insufficient to
represent a geographic image. We believe, however,
that our image retrieval system provides a promising
approach to integrating image processing techniques
and information retrieval algorithms.
47
Chen, Hsinchun, Terrence R. Smith, Mary L. Larsgaard, Linda L. Hill, and Marshall C. Ramsey. "A Geographical Knowledge Representation System (GKRS)for Multimedia Geospatial Retrieval and Analysis." Springer-Verlag, 1997. http://hdl.handle.net/10150/105551.
Full textAbstract:
Artificial Intelligence Lab, Department of MIS, University of Arizona<br>Digital libraries serving multimedia information
that may be accessed in terms of geographic content
and relationships are creating special challenges and
opportunities for networked information systems. An
especially challenging research issue concerning collections
of geo-referenced information relates to the development
of techniques supporting geographic information
retrieval (GIR) that is both fuzzy and concept-based.
Viewing the meta-information environment of a digital
library as a heterogeneous set of services that support
users in terms of GIR, we define a geographic knowledge
representation system (GKRS) in terms of a core set of
services of the meta-information environment that is
required in supporting concept-based access to collections
of geospatial information. In this paper, we describe
an architecture for a GKRS and its implementation in
terms of a prototype system. Our GKRS architecture
loosely couples a variety of multimedia knowledge
sources that are in part represented in terms of the
semantic network and neural network representations
developed in artificial intelligence research. Both textual
analysis and image processing techniques are employed
in creating these textual and iconic geographcal knowledge
structures. The GKRS also employs spreading
activation algorithms in support of concept-based knowledge
retrieval. The- paper describes implementational
details of several of the components of the GKRS as well
as discussing both the lessons learned from, and future
directions of, our research.
48
Hu, You-Heng Surveying & Spatial Information Systems Faculty of Engineering UNSW. "Development, evaluation and application of a geographic information retrieval system." Publisher:University of New South Wales. Surveying & Spatial Information Systems, 2007. http://handle.unsw.edu.au/1959.4/41754.
Full textAbstract:
Geographic Information Retrieval (GIR) systems provide users with functionalities of representation, storage, organisation of and access to various types of electronic information resources based on their textual and geographic context. This thesis explores various aspects of the development, evaluation and application of GIR systems. The first study focuses upon the extraction and grounding of geographic information entities. My approach for this study consists of a hierarchical structure-based geographic relationship model that is used to describe connections between geographic information entities, and a supervised machine learning algorithm that is used to resolve ambiguities. The proposed approach has been evaluated on a toponym disambiguation task using a large collection of news articles. The second study details the development and validation of a GIR ranking mechanism. The proposed approach takes advantage of the power of the Genetic Programming (GP) paradigm with the aim of finding an optimal functional form that integrates both textual and geographic similarities between retrieved documents and a given user query. My approach has been validated by applying it to a large collection of geographic metadata documents. The third study addresses the problem of modelling the GIR retrieval process that takes into account both thematic and geographic criteria. Based on the Spreading Activation Network (SAN), the proposed model consists a two-layer associative network that is used to construct a structured search space; a constrained spreading activation algorithm that is used to retrieve and to rank relevant documents; and a geographic knowledge base that is used to provide necessary domain knowledge for network. The retrieval performance of my model has been evaluated using the GeoCLEF 2006 tasks. The fourth study discusses the publishing, browsing and navigation of geographic information on the World Wide Web. Key challenges in designing and implementing of a GIR user interface through which online content can be systematically organised based on their geospatial characteristics, and can be efficiently accessed and interrelated, are addressed. The effectiveness and the usefulness of the system are shown by applying it to a large collection of geo-tagged web pages.
49
Tsai, Chieh-Yuan. "A flexible feature-based design retrieval system /." free to MU campus, to others for purchase, 1999. http://wwwlib.umi.com/cr/mo/fullcit?p9946307.
Full text
50
Weaver, Marybeth Therese. "Implementing an intelligent information retrieval system: the CODER system, version 1.0." Thesis, Virginia Tech, 1988. http://hdl.handle.net/10919/44097.
Full textAbstract:
For individuals requiring interactive access to online text, information storage and retrieval systems
provide a way to retrieve desired documents and/or text passages. The CODER (COmposite
Document Expert/effective/extended Retrieval) system is a testbed for determining how useful various
artificial intelligence techniques are for increasing the effectiveness of information storage and
retrieval systems. The system, designed previously, has three components: an analysis subsystem
for analyzing and storing document contents, a central spine for manipulation and storage of world
and domain knowledge, and a retrieval subsystem for matching user queries to relevant documents.
This thesis discusses the implementation of the retrieval subsystem and portions of the spine and
analysis subsystem. It illustrates that logic programming, specifically with the Prolog language, is
suitable for development of an intelligent information retrieval system. Furthermore, it shows that
system modularity provides a flexible research testbed, allowing many individuals to work on different
parts of the system which may later be quickly integrated.
The retrieval subsystem has been implemented in a modular fashion so that new approaches to
information retrieval can be easily compared to more traditional ones. A powerful knowledge
representation language, a comprehensive lexicon and individually tailored experts using standardized
blackboard modules for communication and control allowed rapid prototyping, incremental
development and ready adaptability to change. The system executes on a DEC VAX ll/785 running
ULTRIXâ ¢, a variant of 4.2 BSD UNIX. It has been implemented as a set of MU-Prolog
and C modules communicating through TCP/IP sockets.<br>Master of Science