Improvements of Memory Efficiency and Discrimination Power for Real-Time Document Image Retrieval on a Large-Scale Database

Kazutaka TAKEDA  Koichi KISE  Masakazu IWAMURA 

Publication
D - Abstracts of IEICE TRANSACTIONS on Information and Systems (Japanese Edition)  Vol.J95-D  No.7  pp.1491-1494
Publication Date: 2012/07/01
Online ISSN: 1881-0225
Print ISSN: 1880-4535
Type of Manuscript: LETTER
Category: 
Keyword: 
document image retrievalreal-time processingmemory reductionfeature selectionLLAH

Full Text(in Japanese): PDF(695KB)


Summary: 
In order to realize a document image retrieval method for a large-scale database, we propose a method of memory reduction which is based on both sampling feature points and improvement of discrimination power of features by increasing the number of dimension and reducing redundancy.