학술논문

Face localization based on the morphological multi-scale fingerprint
Document Type
Conference
Source
Proceedings 15th International Conference on Pattern Recognition. ICPR-2000 Pattern recognition Pattern Recognition, 2000. Proceedings. 15th International Conference on. 2:925-928 vol.2 2000
Subject
Signal Processing and Analysis
Computing and Processing
Fingerprint recognition
Face detection
Principal component analysis
Feature extraction
Robustness
Independent component analysis
Lighting
Face recognition
Image processing
Neural networks
Language
ISSN
1051-4651
Abstract
We propose the use of morphological multi-scale fingerprints (MMF) for face localization. The MMF is computed as the local maxima and minima preserved up to a certain scale in a multi-scale analysis based on morphological erosion and dilation. This approach belongs to a class of global image feature extraction approaches, that can be combined with others to ensure robust face localization. No structural relationships between face elements is taken into account. We compare this approach to the eigenface approach to face detection with clear superior results.