CONF fasel02a-conf/IDIAP Robust Face Analysis using Convolutional Neural Networks Fasel, B. EXTERNAL http://publications.idiap.ch/attachments/reports/2001/rr01-48.pdf PUBLIC http://publications.idiap.ch/index.php/publications/showcite/fasel-rr-01-48 Related documents Proceedings of the International Conference on Pattern Recognition (ICPR 02) 2 40-43 2002 Quebec, Canada August 2002 IDIAP-RR 01-48 Automatic face analysis has to cope with pose and lighting variations. Especially pose variations are difficult to tackle and many face analysis methods require the use of sophisticated normalization procedures. We propose a data-driven face analysis approach that is not only capable of extracting features relevant to a given face analysis task, but is also robust with regard to face location changes and scale variations. This is achieved by deploying convolutional neural networks, which are either trained for facial expression recognition or face identity recognition. Combining the outputs of these networks allows us to obtain a subject dependent or personalized recognition of facial expressions. REPORT fasel-RR-01-48/IDIAP Robust Face Analysis using Convolutional Neural Networks Fasel, B. EXTERNAL http://publications.idiap.ch/attachments/reports/2001/rr01-48.pdf PUBLIC Idiap-RR-48-2001 2001 IDIAP Published in the Proceedings of the International Conference on Pattern Recognition (ICPR 2002,',','), Quebec, Canada, 2002 Automatic face analysis has to cope with pose and lighting variations. Especially pose variations are difficult to tackle and many face analysis methods require the use of sophisticated normalization procedures. We propose a data-driven face analysis approach that is not only capable of extracting features relevant to a given face analysis task, but is also robust with regard to face location changes and scale variations. This is achieved by deploying convolutional neural networks, which are either trained for facial expression recognition or face identity recognition. Combining the outputs of these networks allows us to obtain a subject dependent or personalized recognition of facial expressions.