Abstract

This talk presents methods and applications of multispectral image fusion and night vision colorization organized into three sections (1) image fusion methods, (2) evaluation, and (3) applications. Two primary multiscale fusion approaches, image pyramid and wavelet transform, will be emphasized. Image fusion comparisons include data, metrics, and analytics. Fusion applications presented include off-focal images, night vision, and face recognition. Examples will be discussed of night-vision images rendered using channel-based color fusion, lookup-table color mapping, and segment-based method colorization. These images resemble natural color scenes and thus can improve the observer’s performance. After attending this lecture you will know how to combine multispectral images and how to render the result with colors in order to enhance computer vision and human vision especially at nighttime.

Yufeng Zhengreceived his PhD in optical engineering/image processing from the Tianjin University in Tianjin, China, in 1997. He had his post-doc experience in University of Louisville (Louisville, KY). He is currently a tenured associate professor at Alcorn State University in Lorman, Mississippi. He is the principle investigator of several federal research grants in the areas of night vision enhancement and multispectral face recognition. He holds five utility patents in glaucoma classification, cancer detection and face recognition, and has published three books and 80 peer-reviewed papers. His research interests include pattern recognition, biometrics, information fusion, and computer-aided detection. He is a Cisco Certified Network Professional (CCNP), and a senior member of SPIE, and a senior member of IEEE & Signal Processing. (Preview of this talk by referring to his recently published book, “Multispectral Image Fusion and Colorization”http://spie.org/Publications/Book/2316453)