Exploring face recognition under complex lighting conditions with HDR imaging

Abstract

Applying image processing applications under complex or harsh lighting conditions can be a difficult challenge. In particular, face recognition can be prone to such limitations due to the uncontrolled nature of the applications to which it is applied. One of the conventional ways used to resolve this concern is by capturing images under controlled light or pre-processing the affected images, which can change the perception of the resultant images. One of the primary issues with this is the lack of information present in the original images due to over-exposed and under-exposed pixels. High Dynamic Range (HDR) imaging offers an alternative due to its capability of handling natural lighting. This paper explores the use HDR imaging for face recognition. A training and testing set of HDR images under different harsh lighting conditions was created. Traditional low dynamic range methods were compared with using the full range and applying HDR methods to a traditional face recognition method. Results demonstrate that adapting HDR captured images for use with traditional face recognition methods via a tone mapping provides sufficient improvement and enables traditional algorithms to cope well with harsh lighting scenarios.