Attribute-Centered Loss for Soft-Biometrics Guided Face Sketch-Photo Recognition
This addresses the challenge of matching forensic sketches to photos for law enforcement, though it appears incremental by building on existing deep learning approaches with a new loss function.
The paper tackled the problem of face sketch-photo recognition by incorporating facial attributes, proposing an attribute-centered loss to train a Deep Coupled Convolutional Neural Network, which significantly outperformed state-of-the-art methods on composite and semi-forensic databases.
Face sketches are able to capture the spatial topology of a face while lacking some facial attributes such as race, skin, or hair color. Existing sketch-photo recognition approaches have mostly ignored the importance of facial attributes. In this paper, we propose a new loss function, called attribute-centered loss, to train a Deep Coupled Convolutional Neural Network (DCCNN) for the facial attribute guided sketch to photo matching. Specifically, an attribute-centered loss is proposed which learns several distinct centers, in a shared embedding space, for photos and sketches with different combinations of attributes. The DCCNN simultaneously is trained to map photos and pairs of testified attributes and corresponding forensic sketches around their associated centers, while preserving the spatial topology information. Importantly, the centers learn to keep a relative distance from each other, related to their number of contradictory attributes. Extensive experiments are performed on composite (E-PRIP) and semi-forensic (IIIT-D Semi-forensic) databases. The proposed method significantly outperforms the state-of-the-art.