Rapid face detection and annotation with loosely face geometry

Abstract

Recent advancements in research paved way for face can be detection in cluttered background in real time. However, much attention need to be given still in partially occluded face detection with varying degree of face occlusion. This paper presents a strategic approach for rapid detection and annotation of partially occluded face. Partially Occluded Face Detection (POFD) problem is addressed by using a combination of feature-based and part-based face detection methods with the help of face part dictionary. In this approach, the devised algorithm aims to automatically detect face components individually and it starts from mostly un-occluded face component called Nose. Nose is very hard to cover up without drawing suspicion. Keeping nose component as a reference, algorithm search the surrounding area for other main facial features, if any. Once face parts qualify facial geometry, they are normalized (scale and rotational) and tag with annotation about each facial features so that partial face recognition algorithm can be adapted accordingly with the test image.