The MPEG-7 Multimedia Database System (MPEG-7 MMDB)

Döller, Mario; Kosch, Harald

doi:10.1016/j.jss.2006.03.051

Cited by 33 publications

(10 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The low-level FEMs are widely employed to compare and to filter data, based purely on content. These FEMs are meaningful in the context of various applications according to several studies (Doeller and Kosch, 2008;Tjondronegoro and Chen, 2002). They are also supposed to define objects by including color patches, shapes or textures.…”

Section: Mpeg-7 Feature Extraction Methodsmentioning

confidence: 97%

“…On the other hand, the feature extraction methods available in the MPEG-7 Standard have been used for image representation in fast-response systems that deal with large amounts of data (Doeller and Kosch, 2008;Ojala et al, 2002;Tjondronegoro and Chen, 2002). However, to the best of our knowledge, there is no study employing those extractors for fire detection.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Techniques for Effective and Efficient Fire Detection from Social Media Images

Bedo

Blanco

Oliveira

et al. 2015

Proceedings of the 17th International Conference on Enterprise Information Systems

View full text Add to dashboard Cite

Abstract:Social media could provide valuable information to support decision making in crisis management, such as in accidents, explosions and fires. However, much of the data from social media are images, which are uploaded in a rate that makes it impossible for human beings to analyze them. Despite the many works on image analysis, there are no fire detection studies on social media. To fill this gap, we propose the use and evaluation of a broad set of content-based image retrieval and classification techniques for fire detection. Our main contributions are: (i) the development of the Fast-Fire Detection method (FFireDt), which combines feature extractor and evaluation functions to support instance-based learning; (ii) the construction of an annotated set of images with ground-truth depicting fire occurrences -the Flickr-Fire dataset; and (iii) the evaluation of 36 efficient image descriptors for fire detection. Using real data from Flickr, our results showed that FFireDt was able to achieve a precision for fire detection comparable to that of human annotators. Therefore, our work shall provide a solid basis for further developments on monitoring images from social media.

show abstract

Section: Mpeg-7 Feature Extraction Methodsmentioning

confidence: 97%

Section: Related Workmentioning

confidence: 99%

Techniques for Effective and Efficient Fire Detection from Social Media Images

Bedo

Blanco

Oliveira

et al. 2015

Proceedings of the 17th International Conference on Enterprise Information Systems

View full text Add to dashboard Cite

show abstract

“…Euclidean Distanceis the distance which is used to calculate the distance between two points (p,q) in any dimension of space and it is one of the most commonly used distance measures (Iker et al, 2008), (Mario et al, 2008). Distance between features of the query image and the image within the closest clusters is determined.…”

Section: Algorithm For Rule Generationmentioning

confidence: 99%

CBIR: Primary Collection of Relevant Image Selection using Rule Based Boolean Query

2016

Rev. Téc. Ing. Univ. Zulia

View full text Add to dashboard Cite

Content Based Image Retrieval is an active way of searching, browsing, or retrieving images from a large image repository. Researchers are intensely competing for developing efficient and precise image retrieval tool which can be applied to various image searching devices that run on different platforms. By applying static clustering, similarity between query image and each cluster is determined to find the closest cluster which has greater likelihood. To obtain more relevant images, it searches not only a single cluster but also the nearby clusters and when the database size increases, all the clusters get updated to reflect the changes in the database. To overcome this problem the proposed method develops an efficient CBIR system that uses rule based Boolean query. It does not generate clusters, instead a dynamic rule has been derived using query image features to retrieve the primary collection of relevant images which has higher semantics. Instead of using dissimilarity distances directly this system determines the subset of images and then it is refined to yield the topmost closest images by finding the shortest distance using Euclidean distance. Gray-level co-occurrence matrix is used to determine texture features such as energy, entropy, contrast and homogeneity. Region based method is used for shape features such as area, perimeter, solidity and circularity of a largest connected component. Dominant color descriptors in RGB space are used for extracting the color feature. Performance can be compared to an existing system by evaluating the time, retrieval precision and recall. The experiment is performed on Corel dataset and it shows superior performance than the previous system.

show abstract

“…Karpouzis et al build a system based on MPEG-21 framework [14] to handle both binary information and structured representations of digital items. Another study of Döller and Kosch [15] introduces a metadata model for multimedia content relying on XML-based MPEG-7 standard. This model, however, has the limitations in inference capability.…”

Section: Semantic Web Application and Musical Information Domainmentioning

confidence: 99%