Similarity Searching in Large Image Databases

dc.contributor.authorPetrakis, Euripides G.M.en_US
dc.contributor.authorFaloutsos, Christosen_US
dc.date.accessioned2004-05-31T22:29:19Z
dc.date.available2004-05-31T22:29:19Z
dc.date.created1994-12en_US
dc.date.issued1998-10-15en_US
dc.description.abstractWe propose a method to handle approximate searching by image content in large image databases. Image content is represented by attributed relational graphs holding features of objects and relationships between objects. The method relies on the assumption that a fixed number of ``labeled'' or ``expected'' objects (e.g., ``heart'', ``lungs'' etc.) are common in all images of a given application domain in addition to a variable number of ``unexpected'' or ``unlabeled'' objects (e.g., ``tumor'', ``hematoma'' etc.). The method can answer queries by example such as ``{\em find all X-rays that are similar to Smith's X-ray}''. The stored images are mapped to points in a multidimensional space and are indexed using state-of-the-art database methods (R-trees). The proposed method has several desirable properties: (a) Database search is approximate so that all images up to a pre-specified degree of similarity (tolerance) are retrieved, (b) it has no ``false dismissals'' (i.e., all images qualifying query selection criteria are retrieved) and (c) it scales-up well as the database grows. We implemented the method and ran experiments on a database of synthetic (but realistic) medical images. The experiments showed that our method significantly outperforms sequential scanning by up to an order of magnitude. (Also cross-referenced as UMIACS-TR-94-134)en_US
dc.format.extent495766 bytes
dc.format.mimetypeapplication/postscript
dc.identifier.urihttp://hdl.handle.net/1903/682
dc.language.isoen_US
dc.relation.isAvailableAtDigital Repository at the University of Marylanden_US
dc.relation.isAvailableAtUniversity of Maryland (College Park, Md.)en_US
dc.relation.isAvailableAtTech Reports in Computer Science and Engineeringen_US
dc.relation.isAvailableAtUMIACS Technical Reportsen_US
dc.relation.ispartofseriesUM Computer Science Department; CS-TR-3388en_US
dc.relation.ispartofseriesUMIACS; UMIACS-TR-94-134en_US
dc.titleSimilarity Searching in Large Image Databasesen_US
dc.typeTechnical Reporten_US

Files

Original bundle
Now showing 1 - 2 of 2
No Thumbnail Available
Name:
CS-TR-3388.ps
Size:
484.15 KB
Format:
Postscript Files
Loading...
Thumbnail Image
Name:
CS-TR-3388.pdf
Size:
386.64 KB
Format:
Adobe Portable Document Format
Description:
Auto-generated copy of CS-TR-3388.ps