27 February 2007 A real-time hierarchical rule-based approach for scale independent human face detection
Author Affiliations +
Abstract
In this paper, we present a scale independent automatic face location technique which can detect the locations of frontal human faces from images. Our hierarchical approach of knowledge-based face detection composed of three levels. Level 1 consists of a simple but effective eyes model that generates a set of rules to judge whether or not there exists a human face candidate in the current search area in a scale-independent manner and in a single scan of the image. To utilize this model, we define a new operator - extended projection and define two new concepts: single projection line and pair projection line. At level 2, an improved model of Yang's mosaic image model is applied to check the consistency of visual features with respect to the human face within each 3x3 blocks of a candidate face image. At the third level, we apply a SVM based face model, to eliminate the false positives obtained from level 2. Experimental results show the combined rule-based and statistical approach works well in detecting frontal human faces in uncluttered scenes.
© (2007) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Jun Jiang, Jun Jiang, Horace H. S. Ip, Horace H. S. Ip, } "A real-time hierarchical rule-based approach for scale independent human face detection", Proc. SPIE 6496, Real-Time Image Processing 2007, 64960P (27 February 2007); doi: 10.1117/12.704657; https://doi.org/10.1117/12.704657
PROCEEDINGS
11 PAGES


SHARE
RELATED CONTENT

Cornea shape measurement
Proceedings of SPIE (August 01 1990)
Refinement of a model for predicting perceived brightness
Proceedings of SPIE (December 28 2001)
Face detection based on a new nonlinear color space
Proceedings of SPIE (September 25 2003)
Geometric image processing of stereo pairs
Proceedings of SPIE (June 22 2001)

Back to Top