Attributes in Multiple Facial Images
This addresses a practical issue in face recognition systems for applications like security or biometrics, but it is incremental as it builds on existing deep learning methods for attribute prediction.
The paper tackles the problem of inconsistent facial attribute recognition across multiple images of the same subject, which can negatively impact face recognition, by developing two methods to compute attributes per subject rather than per image, showing effectiveness on multiple still images or video frames and correcting incorrectly annotated labels.
Facial attribute recognition is conventionally computed from a single image. In practice, each subject may have multiple face images. Taking the eye size as an example, it should not change, but it may have different estimation in multiple images, which would make a negative impact on face recognition. Thus, how to compute these attributes corresponding to each subject rather than each single image is a profound work. To address this question, we deploy deep training for facial attributes prediction, and we explore the inconsistency issue among the attributes computed from each single image. Then, we develop two approaches to address the inconsistency issue. Experimental results show that the proposed methods can handle facial attribute estimation on either multiple still images or video frames, and can correct the incorrectly annotated labels. The experiments are conducted on two large public databases with annotations of facial attributes.