53 Enhanced Hyperspectral Face Recognition

Face recognition is an attractive biometric approach due to the ease in which photographs of the human face can be acquired and processed. The non-intrusive ability of surveillance equipment permits face recognition applications to be used in a myriad of environments. Despite decades of impressive research, face recognition still struggles with variations in illumination, pose and expression as well as spoofing challenges. In order to improve effectiveness, face recognition is often combined with other biometric modalities. An alternative to multimodal biometrics may lie in the exploitation of the hyperspectral imagery and the processing of contextual layers of information contained within these images. The use of context in a hierarchal and fused manner can lead to a more selective gallery. This approach is novel for hyperspectral face recognition and is expected to show improved efficiency, performance and robustness over classical recognition methodologies.