A dynamic counterpropagation network based on the forward only counterpropagation network (CPN) is applied to face detection in this paper. The network, called the dynamic supervised forward-propagation network (DSFPN) trains using a supervised algorithm and can grow dynamically during training allowing subclasses in the training data to be learnt. The network is trained using the categorized wavelet coefficients of the image as features of the image. The results suggests a 98% correct detection rate can be achieved with 4% false positives by increasing network complexity.
|Title of host publication||Proceedings - 2007 International Conference on Computational Intelligence and Security, CIS 2007|
|Number of pages||5|
|Publication status||Published - 01 Dec 2007|
|Event||2007 International Conference on Computational Intelligence and Security, CIS'07 - Harbin, Heilongjiang, China|
Duration: 15 Dec 2007 → 19 Dec 2007
|Conference||2007 International Conference on Computational Intelligence and Security, CIS'07|
|Period||15/12/07 → 19/12/07|