Document Detail

Active testing for face detection and localization.
MedLine Citation:
PMID:  20479494     Owner:  NLM     Status:  MEDLINE    
We provide a novel search technique which uses a hierarchical model and a mutual information gain heuristic to efficiently prune the search space when localizing faces in images. We show exponential gains in computation over traditional sliding window approaches, while keeping similar performance levels.
Raphael Sznitman; Bruno Jedynak
Related Documents :
2759524 - Application of 3-d computer graphics for facial reconstruction and comparison with scul...
24453194 - The utilization of fluorescence to identify the components of lipofuscin by imaging mas...
20203214 - Internal and external features of the face are represented holistically in face-selecti...
19716424 - Selectivity for low-level features of objects in the human ventral stream.
24799044 - In vivo lung morphometry with accelerated hyperpolarized (3) he diffusion mri: a prelim...
3840734 - Computerized data retrieval system for colon surgery.
Publication Detail:
Type:  Journal Article; Research Support, N.I.H., Extramural; Research Support, Non-U.S. Gov't    
Journal Detail:
Title:  IEEE transactions on pattern analysis and machine intelligence     Volume:  32     ISSN:  1939-3539     ISO Abbreviation:  IEEE Trans Pattern Anal Mach Intell     Publication Date:  2010 Oct 
Date Detail:
Created Date:  2010-08-30     Completed Date:  2010-11-29     Revised Date:  -    
Medline Journal Info:
Nlm Unique ID:  9885960     Medline TA:  IEEE Trans Pattern Anal Mach Intell     Country:  United States    
Other Details:
Languages:  eng     Pagination:  1914-20     Citation Subset:  IM    
Department of Computer Science, The Johns Hopkins University, CSEB Room 136, 3400 North Charles Street, Baltimore, MD 21218, USA.
Export Citation:
APA/MLA Format     Download EndNote     Download BibTex
MeSH Terms
Artificial Intelligence*
Face / anatomy & histology*
Image Processing, Computer-Assisted / methods*
Pattern Recognition, Automated / methods*
Grant Support
1 R01 EB 007969-01/EB/NIBIB NIH HHS

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

Previous Document:  MRF energy minimization and beyond via dual decomposition.
Next Document:  MPML3D: Scripting Agents for the 3D Internet.