Human faces have two important characteristics: (1) They are similar objectsand the specific variations of each face are similar to each other; (2) They are nearly bilateralsymmetric. Exploiting the two important prop...Human faces have two important characteristics: (1) They are similar objectsand the specific variations of each face are similar to each other; (2) They are nearly bilateralsymmetric. Exploiting the two important properties, we build a unified model in identity subspace(UMIS) as a novel technique for face recognition from only one example image per person. An identitysubspace spanned by bilateral symmetric bases, which compactly encodes identity information, ispresented. The unified model, trained on an obtained training set with multiple samples per classfrom a known people group A, can be generalized well to facial images of unknown individuals, andcan be used to recognize facial images from an unknown people group B with only one sample persubject, Extensive experimental results on two public databases (the Yale database and the Berndatabase) and our own database (the ICT-JDL database) demonstrate that the UMIS approach issignificantly effective and robust for face recognition.展开更多
文摘Human faces have two important characteristics: (1) They are similar objectsand the specific variations of each face are similar to each other; (2) They are nearly bilateralsymmetric. Exploiting the two important properties, we build a unified model in identity subspace(UMIS) as a novel technique for face recognition from only one example image per person. An identitysubspace spanned by bilateral symmetric bases, which compactly encodes identity information, ispresented. The unified model, trained on an obtained training set with multiple samples per classfrom a known people group A, can be generalized well to facial images of unknown individuals, andcan be used to recognize facial images from an unknown people group B with only one sample persubject, Extensive experimental results on two public databases (the Yale database and the Berndatabase) and our own database (the ICT-JDL database) demonstrate that the UMIS approach issignificantly effective and robust for face recognition.
