A probabilistic hit-and-miss transform for face localization

Authors:
B. Raducanu;M. Graña;X. Albizuri;A. d’Anjou
Affiliations:
Universidad del Pais Vasco, Department of CCIA, Spain;Universidad del Pais Vasco, Department of CCIA, Spain;Universidad del Pais Vasco, Department of CCIA, Spain;Universidad del Pais Vasco, Department of CCIA, Spain
Venue:
Pattern Analysis & Applications
Year:
2004

Citing 0
Cited 2

Using two blinking eyes and one talking mouth for fast face location with complex backgrounds in internet or video

CEA'07 Proceedings of the 2007 annual Conference on International Conference on Computer Engineering and Applications
Face location in non-uniform illumination conditions using dynamic thresholds, lighting normalization and weighting mask function

CEA'07 Proceedings of the 2007 annual Conference on International Conference on Computer Engineering and Applications

Quantified Score

Hi-index	0.00

Visualization

Abstract

Face localization is needed for any face processing procedure whose applications range from biometric identification to content-based image retrieval. It consists in giving the image coordinates of the face. In this paper we propose a probabilistic pattern matching procedure for face localization in greyscale images similar to the morphological hit-and-miss-transform (HMT), which we call probabilistic HMT (PHMT). This procedure is defined on the morphological multiscale fingerprints (MMF), which are image features extracted from the morphological erosion/dilation scale spaces. The face location is estimated as the maximum likelihood image window matching both erosive and dilative MMF models of the object. The MMF models are computed at a discrete set of scales. The MMF models may be built up from a small set of training face images and do not involve numerically sophisticated training algorithms. Training does not use non-face sample images. Therefore resampling is not needed for the construction of the MMF models. The experimental results on the NIST Mugshot Identification Database endorse our claims about the accuracy and robustness of the proposed procedure.