Dynamic selection of exemplar-svms forwatch-list screening through domain adaptation
Dynamic selection of exemplar-svms forwatch-list screening through domain adaptation
Bashbaghi, Saman and Granger, Eric and Sabourin, Robert and Bilodeau, Guillaume Alexandre
ICPRAM 2017 – Proceedings of the 6th International Conference on Pattern Recognition Applications and Methods 2017
Abstract : Still-to-video face recognition (FR) plays an important role in video surveillance, allowing to recognize individuals of interest over a network of video cameras. Watch-list screening is a challenging video surveillance application, because faces captured during enrollment (with still camera) may differ significantly from those captured during operations (with surveillance cameras) under uncontrolled capture conditions (with variations in, e.g., pose, scale, illumination, occlusion, and blur). Moreover, the facial models used for matching are typically designed a priori with a limited number of reference stills. In this paper, a multi-classifier system is proposed that exploits domain adaptation and multiple representations of face captures. An individualspecific ensemble of exemplar-SVM (e-SVM) classifiers is designed to model the single reference still of each target individual, where different random subspaces, patches, and face descriptors are employed to generate a diverse pool of classifiers. To improve robustness of face models, e-SVMs are trained using the limited number of labeled faces in reference stills from the enrollment domain, and an abundance of unlabeled faces in calibration videos from the operational domain. Given the availability of a single reference target still, a specialized distance-based criteria is proposed based on properties of e-SVMs for dynamic selection of the most competent classifiers per probe face. The proposed approach has been compared to reference systems for still-to-video FR on videos from the COX-S2V dataset. Results indicate that ensemble of e-SVMs designed using calibration videos for domain adaptation and dynamic ensemble selection yields a high level of FR accuracy and computational efficiency.
