Computational Modeling of Face Recognition Based on Psychophysical Experiments

@article{citeulike:2388016, abstract = {Recent results from psychophysical studies are discussed which clearly show that face processing is not only holistic. Humans do encode face parts (component information) in addition to information about the spatial interrelationship of facial features (global configural information). Based on these findings we propose a computational architecture of face recognition, which implements a component and configural route for encoding and recognizing faces. Modeling results showed a striking similarity between human psychophysical data and the computational model. In addition, we could show that our framework is able to achieve good recognition performance even under large view rotations. Thus, our study is an example of how an interdisciplinary approach can provide a deeper understanding of cognitive processes and lead to further insights in human psychophysics as well as computer vision.}, author = {Schwaninger, Adrian and Wallraven, Christian and Bulthoff, Heinrich H. }, citeulike-article-id = {2388016}, doi = {10.1024/1421-0185.63.3.207}, journal = {Swiss Journal of Psychology}, keywords = {08-009, computation, face}, month = {September}, number = {3}, pages = {207--215}, posted-at = {2008-02-16 05:53:45}, priority = {2}, title = {Computational Modeling of Face Recognition Based on Psychophysical Experiments}, url = {http://dx.doi.org/10.1024/1421-0185.63.3.207}, volume = {63}, year = {2004} }

TY - JOUR ID - citeulike:2388016 L3 - citeulike-article-id:2388016 TI - Computational Modeling of Face Recognition Based on Psychophysical Experiments JF - Swiss Journal of Psychology VL - 63 IS - 3 SP - 207 EP - 215 N2 - Recent results from psychophysical studies are discussed which clearly show that face processing is not only holistic. Humans do encode face parts (component information) in addition to information about the spatial interrelationship of facial features (global configural information). Based on these findings we propose a computational architecture of face recognition, which implements a component and configural route for encoding and recognizing faces. Modeling results showed a striking similarity between human psychophysical data and the computational model. In addition, we could show that our framework is able to achieve good recognition performance even under large view rotations. Thus, our study is an example of how an interdisciplinary approach can provide a deeper understanding of cognitive processes and lead to further insights in human psychophysics as well as computer vision. KW - 08-009 KW - computation KW - face AU - Schwaninger, Adrian AU - Wallraven, Christian AU - Bulthoff, Heinrich PY - 2004/09// UR - http://dx.doi.org/10.1024/1421-0185.63.3.207 ER -