Opportunistic activity and context recognition systems do not presume a static sensor infrastructure that is defined at the design time of a system. They also do not have a fixed ...
A good training dataset, representative of the test images expected in a given application, is critical for ensuring good performance of a visual categorization system. Obtaining ...
Aniruddha Kembhavi, Behjat Siddiquie, Roland Miezi...
We present a novel expert-model of Query-Driven Locally Adaptive (QDLA) Fisher faces for robust face recognition. For each query face, the proposed method first fits local Fisher ...
Yun Fu, Junsong Yuan, Zhu Li, Thomas S. Huang, Yin...
Recognition under illumination variations is a challenging problem. The key is to successfully separate the illumination source from the observed appearance. Once separated, what ...
In this work we evaluate a recently published vector quantization scheme, which has been developed to handle binary features like the pressure feature occurring in on-line handwri...