Document Detail


A multiscale representation including opponent color features for texture recognition.
MedLine Citation:
PMID:  18267387     Owner:  NLM     Status:  PubMed-not-MEDLINE    
Abstract/OtherAbstract:
We introduce a representation for color texture using unichrome and opponent features computed from Gabor filter outputs. The unichrome features are computed from the spectral bands independently while the opponent features combine information across different spectral bands at different scales. Opponent features are motivated by color opponent mechanisms in human vision. We present a method for efficiently implementing these filters, which is of particular interest for processing the additional information present in color images. Using a data base of 2560 image regions, we show that the multiscale approach using opponent features provides better recognition accuracy than other approaches.
Authors:
A Jain; G Healey
Related Documents :
2564057 - Patent foramen ovale and decompression sickness in divers.
17029517 - Comparison of doppler sonography to magnetic resonance imaging and clinical examination...
7678467 - Prostate: techniques, results, and potential applications of color doppler us scanning.
19768607 - High-throughput snp detection based on pcr amplification on magnetic nanoparticles usin...
1631287 - Computed tomography of gynecologic neoplasms.
2916047 - Do radiologists control imaging studies? survey results from 198 academic institutions.
Publication Detail:
Type:  Letter    
Journal Detail:
Title:  IEEE transactions on image processing : a publication of the IEEE Signal Processing Society     Volume:  7     ISSN:  1057-7149     ISO Abbreviation:  IEEE Trans Image Process     Publication Date:  1998  
Date Detail:
Created Date:  2008-02-12     Completed Date:  2009-12-15     Revised Date:  -    
Medline Journal Info:
Nlm Unique ID:  9886191     Medline TA:  IEEE Trans Image Process     Country:  United States    
Other Details:
Languages:  eng     Pagination:  124-8     Citation Subset:  -    
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:  A vector quantizer for image restoration.
Next Document:  Optimal nonnegative color scanning filters.