Content-based multimedia indexing and retrieval

Djeraba, Chabane

doi:10.1109/mmul.2002.998047

Cited by 40 publications

(15 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The adjective blind simply refers to the fact that both the sources and the mixing function are unknown. Thus, observations, as an -dimensional random vector , are assumed to be a linear mixture of mutually statistically independent sources (1) where represents a linear mixture called the mixing matrix. To achieve the separation, one must estimate the separating matrix that verifies:…”

Section: Representation Of Images With Independent Featuresmentioning

confidence: 99%

“…1 This does not take into account the spatial relationships between pixels but makes sense for the global characterization of a scene that is perceived holistically at first sight [43]. However, at a local scale natural images exhibit meaningful spatial structures that 1 This has already been proposed by A. Labbi in an unpublished report [42] also carry important information [41]. To catch this information, we use a sliding window that counts the number of times one filter is the most active within a local area of .…”

Section: A Luminance Signaturementioning

confidence: 99%

“…Nowadays, it is usual to distinguish between low-level and high-level features. The former refer to primitive features such as color, texture, shape and motion that are derived from the raw pixel values but that do not refer to any external knowledge [1]. A major contribution to the definition of these kinds of descriptors was realized during the development of the ISO/MPEG-7 standard.…”

mentioning

confidence: 99%

See 2 more Smart Citations

Learning Midlevel Image Features for Natural Scene and Texture Classification

Borgne

Guérin–Dugué

O’Connor

2007

IEEE Trans. Circuits Syst. Video Technol.

View full text Add to dashboard Cite

Abstract-This paper deals with coding of natural scenes in order to extract semantic information. We present a new scheme to project natural scenes onto a basis in which each dimension encodes statistically independent information. Basis extraction is performed by independent component analysis (ICA) applied to image patches culled from natural scenes. The study of the resulting coding units (coding filters) extracted from well-chosen categories of images shows that they adapt and respond selectively to discriminant features in natural scenes. Given this basis, we define global and local image signatures relying on the maximal activity of filters on the input image. Locally, the construction of the signature takes into account the spatial distribution of the maximal responses within the image. We propose a criterion to reduce the size of the space of representation for faster computation. The proposed approach is tested in the context of texture classification (111 classes), as well as natural scenes classification (11 categories, 2037 images). Using a common protocol, the other commonly used descriptors have at most 47.7% accuracy on average while our method obtains performances of up to 63.8%. We show that this advantage does not depend on the size of the signature and demonstrate the efficiency of the proposed criterion to select ICA filters and reduce the dimension.

show abstract

Section: Representation Of Images With Independent Featuresmentioning

confidence: 99%

Section: A Luminance Signaturementioning

confidence: 99%

mentioning

confidence: 99%

See 1 more Smart Citation

Learning Midlevel Image Features for Natural Scene and Texture Classification

Borgne

Guérin–Dugué

O’Connor

2007

IEEE Trans. Circuits Syst. Video Technol.

View full text Add to dashboard Cite

show abstract

“…Although digitizing and storing large quantities of media files are challenging problems in themselves, browsing and searching these files accurately is an even more complex problem, studied by many research groups in the recent past [10,5,22,20,7]. Given the level of noise and the lack of structure in media documents, content analysis and indexing represent a challenging signal processing, machine learning and information retrieval problem [11]. In the following sections, we first describe the system challenges of large multimedia content analysis systems.…”

Section: Introductionmentioning

confidence: 99%

<title>Multimedia content analysis and indexing: evaluation of a distributed and scalable architecture</title>

et al. 2003

View full text Add to dashboard Cite

multimedia information systems, content-based searching, media indexing, media processing, distributed computing, grid computing, web services Multimedia search engines facilitate the retrieval of documents from large media content archives now available via intranets and the Internet. Over the past several years, many research projects have focused on algorithms for analyzing and indexing media content efficiently. However, special system architectures are required to process large amounts of content from real-time feeds or existing archives. Possible solutions include dedicated distributed architectures for analyzing content rapidly and for making it searchable. The system architecture we propose implements such an approach: a highly distributed and reconfigurable batch media content analyzer that can process media streams and static media repositories. Our distributed media analysis application handles media acquis ition, content processing, and document indexing. This collection of modules is orchestrated by a task flow management component, exploiting data and pipeline parallelism in the application. A scheduler manages load balancing and prioritizes the different tasks. Workers implement application-specific modules that can be deployed on an arbitrary number of nodes running different operating systems. Each application module is exposed as a web service, implemented with industry-standard interoperable middleware components such as Microsoft ASP.NET and Sun J2EE. Our system architecture is the next generation system for the multimedia indexing application demonstrated by www.speechbot.com. It can process large volumes of audio recordings with minimal support and maintenance, while running on low-cost commodity hardware. The system has been evaluated on a server farm running concurrent content analysis processes.

show abstract

“…Not too long ago, we published two special issues [3][8] on the new challenges of multimedia indexing and retrieval. The core idea behind those special issue articles was the gap between primitive and semantics features and how to bridge the two levels for multimedia information retrieval.…”

mentioning

confidence: 99%

Systems and architectures for multimedia information retrieval

2005

View full text Add to dashboard Cite

In this paper, we provide a brief survey on multimedia information retrieval and we introduce some ideas investigated in the special issue. We hope that the contributions of this issue will stimulate the readers to tackle the current challenges and problems in this highly important research direction. Such contributions are the basis of tomorrow's multimedia information systems. Our aims are to clarify some notions raised by this new technology by reviewing its current capabilities and potential usefulness to users in various areas. The research and development issues cover a wide range of fields, many of which are shared with media processing, signal processing, database technologies, and data mining.

show abstract

Content-based multimedia indexing and retrieval

Cited by 40 publications

References 4 publications

Learning Midlevel Image Features for Natural Scene and Texture Classification

Learning Midlevel Image Features for Natural Scene and Texture Classification

<title>Multimedia content analysis and indexing: evaluation of a distributed and scalable architecture</title>

Systems and architectures for multimedia information retrieval

Contact Info

Product

Resources

About