Human face detection plays an important role in application such as video surveillance, human computer interface, face recognition, and face image database management. In this paper we propose, a novel scheme for human faces detection in color images under unconstrained scene conditions, such as the presence of a complex background and uncontrolled illumination. The proposed method adopts a specialized unsupervised neural network, to extract skin colour regions in the Lab colour space, obtained from the integration of the rough fuzzy set based scale space transform and neural clustering. A correlation-based method is then applied for the detection of ellipse regions. Experiments on three benchmark face databases, namely the IMM [1], CalTech [2] and CMU PIE [3] databases, demonstrate the ability of the proposed algorithm in detecting faces also in difficult conditions.
Titolo: | A Rough Fuzzy Neural Based Approach to Face Detection | |
Autori: | ||
Data di pubblicazione: | 2010 | |
Abstract: | Human face detection plays an important role in application such as video surveillance, human computer interface, face recognition, and face image database management. In this paper we propose, a novel scheme for human faces detection in color images under unconstrained scene conditions, such as the presence of a complex background and uncontrolled illumination. The proposed method adopts a specialized unsupervised neural network, to extract skin colour regions in the Lab colour space, obtained from the integration of the rough fuzzy set based scale space transform and neural clustering. A correlation-based method is then applied for the detection of ellipse regions. Experiments on three benchmark face databases, namely the IMM [1], CalTech [2] and CMU PIE [3] databases, demonstrate the ability of the proposed algorithm in detecting faces also in difficult conditions. | |
Handle: | http://hdl.handle.net/11367/32529 | |
ISBN: | 1-60132-154-6 | |
Appare nelle tipologie: | 4.1 Contributo in Atti di convegno |