Appearance-based face detection with artificial neural networks

Article type: Research Article

Authors: Stathopoulou, Ioanna-Ourania | Tsihrintzis, George A.^{; *}

Affiliations: University of Piraeus, Department of Informatics, Piraeus 185 34, Greece

Correspondence: [*] Corresponding author. E-mail: [email protected]

Abstract: The rapid and successful detection of a face in an image is a prerequisite to a fully automated face recognition system. A new neural network-based face detection system is presented, which is the outcome of a comparative study of two neural network models of different architecture and complexity. The fundamental difference in the construction of the two models is the need to address the problem either by using a general solution based on the full-face image or by composing the solution through the resolution of specific characteristics of the face. The algorithm is based on the assumption that there exists contrast in brightness between specific regions of the human face. The proposed neural network system is reliable and of reduced error rate. Specifically, we show that the second approach, even though more complicated, exhibits better performance in terms of detection and false – positive rates. Moreover, it can detect successfully faces that are slightly rotated out of the image plane.

Keywords: Face detection, neural networks

DOI: 10.3233/IDT-2011-0100

Journal: Intelligent Decision Technologies, vol. 5, no. 2, pp. 101-111, 2011