Document Detail


Linear Scale and Rotation Invariant Matching.
MedLine Citation:
PMID:  21135437     Owner:  NLM     Status:  Publisher    
Abstract/OtherAbstract:
Matching visual patterns that appear scaled, rotated and deformed with respect to each other is a challenging problem. We propose a linear formulation that simultaneously matches feature points and estimates global geometrical transformation in a constrained linear space. The linear scheme enables search space reduction based on the lower convex hull property so that the problem size is largely decoupled from the original hard combinatorial problem. Our method therefore can be used to solve large scale problems that involve a very large number of candidate feature points. Without using pre-pruning in the search, this method is more robust in dealing with weak features and clutter. We apply the proposed method to action detection and image matching. Our results on a variety of images and videos demonstrate that our method is accurate, efficient, and robust.
Authors:
Hao Jiang; Stella X Yu; David R Martin
Related Documents :
20423557 - What do people think about when they answer the brief illness perception questionnaire?...
8626157 - Screening for social and environmental problems in a va primary care setting.
19433987 - Crying and feeding problems in infancy and cognitive outcome in preschool children born...
19771757 - Prevalence of occupational voice disorders in teachers.
19379137 - Biodiversity maintenance mechanisms differ between native and novel exotic-dominated co...
18432427 - Sexual responses to living with hiv/aids in lomé, togo.
Publication Detail:
Type:  JOURNAL ARTICLE     Date:  2010-11-30
Journal Detail:
Title:  IEEE transactions on pattern analysis and machine intelligence     Volume:  -     ISSN:  1939-3539     ISO Abbreviation:  -     Publication Date:  2010 Nov 
Date Detail:
Created Date:  2010-12-7     Completed Date:  -     Revised Date:  -    
Medline Journal Info:
Nlm Unique ID:  9885960     Medline TA:  IEEE Trans Pattern Anal Mach Intell     Country:  -    
Other Details:
Languages:  ENG     Pagination:  -     Citation Subset:  -    
Affiliation:
Boston College, Chestnut Hill.
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:  Energy normalization for pose-invariant face recognition based on MRF model image matching.
Next Document:  Modeling Bidirectional Texture Functions with Multivariate Spherical Radial Basis Functions.