Direct recognition of motion-blurred faces

The need to recognize motion blurred faces is vital for a wide variety of security applications ranging from maritime surveillance to road traffic policing. While much of the rich theory in the analysis of motion blurred images focuses on restoration of the same, we argue that this is an unnecessary (and expensive) step for face recognition. Instead we adopt a direct approach based on the set-theoretic characterization of the space of all motion blurred images that arise from a single sharp image. This set lacks the nice property of convexity that was exploited in a recent paper to achieve competitive results in real-world datasets of motion blurred faces. Keeping this non-convexity in mind, we propose a Bank-of-Classifiers approach for directly recognizing motion blurred face images. To that end, we divide the parameter space of motion blur into many different bins in such a way that the set of blurred images within each bin is a convex set. In each such bin, we learn SVM classifiers that ’maximally’ separate the convex sets associated with each person in the reference database. Our experiments on synthetic and real datasets provide compelling evidence that this approach is a viable solution for motion blurred face recognition.