Published June 1995
| Version Published
Book Section - Chapter
Open
Finding Faces in Cluttered Scenes using Random Labeled Graph Matching
Abstract
An algorithm for locating quasi-frontal views of human faces in cluttered scenes is presented. The algorithm works by coupling a set of local feature detectors with a statistical model of the mutual distances between facial features it is invariant with respect to translation, rotation (in the plane), and scale and can handle partial occlusions of the face. On a challenging database with complicated and varied backgrounds, the algorithm achieved a correct localization rate of 95% in images where the face appeared quasi-frontally.
Additional Information
© 1995 IEEE. Date of Current Version: 06 August 2002. This work was supported by the Center for Neuromorphic Systems Engineering as a part of the National Science Foundation (NSF) Engineering Research Center Program, and by the California Trade and Commerce Agency, Office of Strategic Technology. Additional funding was provided by ONR grant n. N00014-93-1-0990, an NSF National Young Investigator award, a grant from Intel, and a grant from Caltech. We are also very grateful to Jitendra Malik for useful discussions.Attached Files
Published - LEUiccv95.pdf
Files
LEUiccv95.pdf
Additional details
Identifiers
- Eprint ID
- 29351
- Resolver ID
- CaltechAUTHORS:20120217-090230623
Funding
- NSF Center for Neuromorphic Systems Engineering (CNSE)
- Engineering Research Center Program
- California Trade and Commerce Agency
- Office of Naval Research (ONR)
- N00014-93-1-0990
- NSF National Young Investigator Award
- Intel
- Caltech
Dates
- Created
-
2012-02-17Created from EPrint's datestamp field
- Updated
-
2021-11-09Created from EPrint's last_modified field
Caltech Custom Metadata
- Other Numbering System Name
- INSPEC Accession Number
- Other Numbering System Identifier
- 5028073