Document Detail


Improving object recognition by transforming Gabor filter responses.
MedLine Citation:
PMID:  16754395     Owner:  NLM     Status:  PubMed-not-MEDLINE    
Abstract/OtherAbstract:
Previous work described a biologically motivated object recognition system with Gabor wavelets as basic feature type. These features are robust against slight distortion, rotation and variation in illumination. We here describe extensions of the system that address image variance due to arbitrary in-plane rotation, substantial scale changes and moderate depth rotation of objects, and to background variation, using simple linear transformation of the Gabor filter responses. The performance of the system is enhanced significantly.
Authors:
M Pötzsch; N Krüger; C von der Malsburg
Related Documents :
16685975 - Automatic parameter optimization for de-noising mr data.
9169105 - Digital image processing.
1725485 - Automated selection of the most epithelium-rich areas in gynecologic tumor sections.
18267405 - Annular filters for binary images.
22446075 - The anticommons and the environment.
9855145 - Magnification characteristics of fundus imaging systems.
Publication Detail:
Type:  Journal Article    
Journal Detail:
Title:  Network (Bristol, England)     Volume:  7     ISSN:  0954-898X     ISO Abbreviation:  Network     Publication Date:  1996 May 
Date Detail:
Created Date:  2006-06-06     Completed Date:  2007-07-17     Revised Date:  -    
Medline Journal Info:
Nlm Unique ID:  9431867     Medline TA:  Network     Country:  England    
Other Details:
Languages:  eng     Pagination:  341-7     Citation Subset:  -    
Affiliation:
Ruhr-Universität Bochum, Institut für Neuroinformatik, D-44780, Bochum, Germany.
Export Citation:
APA/MLA Format     Download EndNote     Download BibTex
MeSH Terms
Descriptor/Qualifier:

From MEDLINE®/PubMed®, a database of the U.S. National Library of Medicine


Previous Document:  Natural image statistics and efficient coding.
Next Document:  An auditory cortical theory of primitive auditory grouping.