IARS: Image Archival and Retrieval Systems
Exploration of Spatial Similarity Based Indexing Schemes For Symbolic Image Databases
Versandkostenfrei!
Versandfertig in 6-10 Tagen
44,99 €
inkl. MwSt.
PAYBACK Punkte
22 °P sammeln!
In this book, important aspects in creating an efficient and effective image archival and retrieval system are addressed. Various novel algorithmic models are proposed for indexing symbolic images for faster retrieval. The proposed models assume that the symbolic representation of images are made available and they represent images through perception of spatial relationships among the components present in symbolic images. In order to overcome the limitations of existing methodologies in perceiving spatial relationships invariant to image transformations, a novel concept called direction of re...
In this book, important aspects in creating an efficient and effective image archival and retrieval system are addressed. Various novel algorithmic models are proposed for indexing symbolic images for faster retrieval. The proposed models assume that the symbolic representation of images are made available and they represent images through perception of spatial relationships among the components present in symbolic images. In order to overcome the limitations of existing methodologies in perceiving spatial relationships invariant to image transformations, a novel concept called direction of reference is introduced and two algorithmic models, for exact match retrieval are investigated. An alternative model presented preserves triangular spatial relationship among components by the use of quadruples which are mapped onto unique keys. The model stores the mean and standard deviation of the keys for an image as its representatives. Another model based on B-tree, a multilevel indexingstructure, is also proposed for similarity retrieval. A method of classifying the retrieved images based on a query image is also suggested. The extended model has logarithmic retrieval time complexity.
Andere Kunden interessierten sich für
