“…Moreover, the process of identifying an authentic correlation shape can be used to refine the correlation outputs after the initial matching for improved discrimination. There are a large number of CFs that have been developed [1,2,3,4,5] for image matching problems and have been previously shown to perform well in biometric recognition scenarios like face [6], iris [7], periocular [8], fingerprint [9], and palm print [10]. However, the matching challenge is noticeably more difficult when only a single image is available for the gallery template, e.g., as in real-world applications (such as when matching crime-scene face images to face images in surveillance videos) and in several NIST biometric competitions [11,12,13] designed to mimic such real world scenarios.…”