Face Detection in Repeated Settings
This addresses face detection for verification in specific, repeated environments, but is incremental as it focuses on controlled settings rather than unconstrained scenarios.
The paper tackles face detection in controlled background and location settings, such as building entrances, by presenting a correlation-based algorithm that is easy and fast to train, outperforms Viola and Jones in accuracy and speed.
Face detection is an important first step before face verification and recognition. In unconstrained settings it is still an open challenge because of the variation in pose, lighting, scale, background and location. However, for the purposes of verification we can have a control on background and location. Images are primarily captured in places such as the entrance to a sensitive building, in front of a door or some location where the background does not change. We present a correlation based face detection algorithm to detect faces in such settings, where we control the location, and leave lighting, pose, and scale uncontrolled. In these scenarios the results indicate that our algorithm is easy and fast to train, outperforms Viola and Jones face detection accuracy and is faster to test.