Iannarelli's studies demonstrated that ear shape represents a biometric identifier able to authenticate people in the same way as more established biometrics, like face or voice for instance. However, not many researches can be found in literature about ear recognition. In most cases existing algorithms are borrowed from other biometric contexts. An example is PCA (Principal Component Analysis). Eigen-ears only provide high recognition rate in closely controlled conditions, while performances decay even for small changes in environmental conditions. We propose a fractal based technique, namely HERO (Human Ear Recognition against Occlusions) to classify human ears. The feature extraction process has been made local, so that the system gets robust with respect to small changes in pose/illumination and partial occlusions. Experimental results confirm the superiority of this approach over several linear and non linear techniques. © 2010 IEEE.
HERO: Human Ear Recognition against Occlusions / DE MARSICO, Maria; Michele, Nappi; Daniel, Riccio. - (2010), pp. 178-183. (Intervento presentato al convegno 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Workshops, CVPRW 2010 tenutosi a San Francisco, CA nel 13 June 2010 through 18 June 2010) [10.1109/cvprw.2010.5544623].
HERO: Human Ear Recognition against Occlusions
DE MARSICO, Maria;
2010
Abstract
Iannarelli's studies demonstrated that ear shape represents a biometric identifier able to authenticate people in the same way as more established biometrics, like face or voice for instance. However, not many researches can be found in literature about ear recognition. In most cases existing algorithms are borrowed from other biometric contexts. An example is PCA (Principal Component Analysis). Eigen-ears only provide high recognition rate in closely controlled conditions, while performances decay even for small changes in environmental conditions. We propose a fractal based technique, namely HERO (Human Ear Recognition against Occlusions) to classify human ears. The feature extraction process has been made local, so that the system gets robust with respect to small changes in pose/illumination and partial occlusions. Experimental results confirm the superiority of this approach over several linear and non linear techniques. © 2010 IEEE.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
