A Unified Approach to Iconic Indexing, Retrieval, and Maintenance of Spatial Relationships in Image Databases
✍ Scribed by Qing-Long Zhang; Shi-Kuo Chang; Stephen S.-T. Yau
- Publisher
- Elsevier Science
- Year
- 1996
- Tongue
- English
- Weight
- 495 KB
- Volume
- 7
- Category
- Article
- ISSN
- 1047-3203
No coin nor oath required. For personal study only.
✦ Synopsis
portant problems in the design of image database systems is how images are stored in the image databases [12, 13, In this paper we propose a unified iconic indexing, the generalized combined 2D string representation, for images in image 4,5,9,26]. Because of the large amount of storage required databases. Each 2D image is modelled as a generalized extended for images, the problem of efficient, economic storage and pseudo-symbolic picture, which has the GEP-2D string repreflexible retrieval and the manipulation of vast amounts of sentation. We present an efficient algorithm to generate the image information has become more and more important GEP-2D string representation for each 2D image. We also show and requires careful consideration. While the use of inhow to maintain the complete information about the absolute dexing to allow database accessing has been well estabspatial relationships in the image. Our proposed iconic indexing lished in traditional database systems, content-based piccombines both the GEP-2D string representation and the usual ture indexing techniques need to be developed for 2D string representation to capture absolute and relative spatial facilitating pictorial information retrieval from a pictorial relationships in the image. The result is better representation database. With the recent interest in multimedia systems, of spatial relationships in image databases. These results extend content-based image retrieval has attracted the attention our earlier work on a large class of 2D scenes, the extended of researchers across several disciplines [18]. Flickner et al. pseudo-symbolic pictures. Picture retrieval by generalized com- [17] have developed a prototype image and video database bined 2D strings is discussed. Our approach can also be easily system, QBIC, to explore content-based image retrieval formulated for 3D images.