Nonlinear fusion for face recognition using fuzzy integral |
| |
| Affiliation: | 1. Université de Lorraine/ERPI (Equipe de Recherche des processus Innovatifs), 8, rue Bastien Lepage, 54010 Nancy Cedex, France;2. Paris Descartes University, LIPADE, (Laboratoire d''Informatique Paris Descartes), 45 rue des Saints Pères, 75270 Paris Cedex 06, France;1. Department of Economics and Business, University of Catania, Corso Italia 55, 95129 Catania, Italy;2. University of Portsmouth, Portsmouth Business School, Centre of Operations Research and Logistics (CORL), Richmond Building, Portland Street, Portsmouth PO1 3DE, United Kingdom;1. Department of Economics and Business, University of Catania, Corso Italia 55, 95129 Catania, Italy;2. University of Portsmouth, Portsmouth Business School, Centre of Operations Research and Logistics (CORL), Richmond Building, Portland Street, Portsmouth PO1 3DE, United Kingdom;3. Institute of Computing Science, Poznań University of Technology, 60-965 Poznań, Poland;4. Systems Research Institute, Polish Academy of Sciences, 01-447 Warsaw, Poland |
| |
| Abstract: | Face recognition based only on the visual spectrum is not accurate or robust enough to be used in uncontrolled environments. Recently, infrared (IR) imagery of human face is considered as a promising alternative to visible imagery due to its relative insensitive to illumination changes. However, IR has its own limitations. In order to fuse information from the two modalities to achieve better result, we propose a new fusion recognition scheme based on nonlinear decision fusion, using fuzzy integral to fuse the objective evidence supplied by each modality. The scheme also employs independent component analysis (ICA) for feature extraction and support vector machines (SVMs) for classification evidence. Recognition rate is used to evaluate the proposed scheme. Experimental results show the scheme improves recognition performance substantially. |
| |
| Keywords: | |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
