Open-Set Face Verification Algorithm Using Competitive Negative Samples

A novel face verification algorithm using competitive negative samples is proposed.In the algorithm,the tested face matches not only with the claimed client face but also with competitive negative samples,and all the matching scores are combined to make a final decision.Based on the algorithm,three schemes,including closestnegative-sample scheme,all-negative-sample scheme,and closest-few-negative-sample scheme,are designed.They are tested and compared with the traditional similaritybased verification approach on several databases with different features and classifiers.Experiments demonstrate that the three schemes reduce the verification error rate by 25.15%,30.24%,and 30.97%,on average,respectively.

Coordinate-wise monotonic transformations enable privacy-preserving age estimation with 3D face point cloud

The human face is a valuable biomarker of aging,but the collection and use of its image raise significant privacy concerns.Here we present an approach for facial data masking that preserves age-related features using coordinate-wise monotonic transformations.We first develop a deep learning model that estimates age directly from non-registered face point clouds with high accuracy and generalizability.We show that the model learns a highly indistinguishable mapping using faces treated with coordinate-wise monotonic transformations,indicating that the relative positioning of facial information is a low-level biomarker of facial aging.Through visual perception tests and computational3D face verification experiments,we demonstrate that transformed faces are significantly more difficult to perceive for human but not for machines,except when only the face shape information is accessible.Our study leads to a facial data protection guideline that has the potential to broaden public access to face datasets with minimized privacy risks.

Discriminative Histogram Intersection Metric Learning and Its Applications

In this paper, a novel method called discriminative histogram intersection metric learning （DHIML） is proposed for pair matching and classification. Specifically, we introduce a discrimination term for learning a metric from binary infor-mation such as same/not-same or similar/dissimilar, and then combine it with the classification error for the discrimination in classifier construction. Compared with conventional approaches, the proposed method has several advantages. 1） The histogram intersection strategy is adopted into metric learning to deal with the widely used histogram features effectively. 2） By introducing discriminative term and classification error term into metric learning, a more discriminative distance metric and a classifier can be learned together. 3） The objective function is robust to outliers and noises for both features and labels in the training. The performance of the proposed method is tested on four applications： face verification, face-track identification, face-track clustering, and image classification. Evaluations on the challenging restricted protocol of Labeled Faces in the Wild （LFW） benchmark, a dataset with more than 7000 face-tracks, and Caltech-101 dataset validate the robustness and discriminability of the proposed metric learning, compared with the recent state-of-the-art approaches.