The authors proposed site adaptation for a generic face recognizers based on a small adaptation data set capture.
Although the state-of-the-art face recognition algorithms are designed to reliably recognize faces under uncontrolled imaging conditions, the performance of these face recognizers varies in the real-world applications, depending on how much the face appearance statistics in the testing data match with those in the training data. Based on an OSFV face recognizer with Gabor features selected by Adaboost algorithm, the authors propose several site adaptation methods at the feature level and at the model level. The experiment results show that the proposed site adaptation approaches can boost the performance of the authors’ generic face recognition algorithm based on a small adaptation dataset acquired from the site with a different imaging condition. (Publisher abstract provided)
Downloads
Similar Publications
- Using Citizen Notification To Interrupt Near-Repeat Residential Burglary Patterns: the Micro-Level Near-Repeat Experiment
- Development of a Probabilistic Multi-Class Model Selection Algorithm for High-Dimensional and Complex Data
- Analysis and Characterization of Smokeless Powders and Smokeless Powder Residues