1st Edition

Super-Resolution Imaging

Edited By Peyman Milanfar Copyright 2011
    496 Pages 163 B/W Illustrations
    by CRC Press

    With the exponential increase in computing power and broad proliferation of digital cameras, super-resolution imaging is poised to become the next "killer app." The growing interest in this technology has manifested itself in an explosion of literature on the subject. Super-Resolution Imaging consolidates key recent research contributions from eminent scholars and practitioners in this area and serves as a starting point for exploration into the state of the art in the field. It describes the latest in both theoretical and practical aspects of direct relevance to academia and industry, providing a base of understanding for future progress.

    Features downloadable tools to supplement material found in the book

    Recent advances in camera sensor technology have led to an increasingly larger number of pixels being crammed into ever-smaller spaces. This has resulted in an overall decline in the visual quality of recorded content, necessitating improvement of images through the use of post-processing. Providing a snapshot of the cutting edge in super-resolution imaging, this book focuses on methods and techniques to improve images and video beyond the capabilities of the sensors that acquired them. It covers:

    • History and future directions of super-resolution imaging
    • Locally adaptive processing methods versus globally optimal methods
    • Modern techniques for motion estimation
    • How to integrate robustness
    • Bayesian statistical approaches
    • Learning-based methods
    • Applications in remote sensing and medicine
    • Practical implementations and commercial products based on super-resolution

    The book concludes by concentrating on multidisciplinary applications of super-resolution for a variety of fields. It covers a wide range of super-resolution imaging implementation techniques, including variational, feature-based, multi-channel, learning-based, locally adaptive, and nonparametric methods. This versatile book can be used as the basis for short courses for engineers and scientists, or as part of graduate-level courses in image processing.

    Image Super-Resolution: Historical Overview and Future Challenges, J. Yang and T. Huang

    Introduction to Super-Resolution

    Notations

    Techniques for Super-Resolution

    Challenge issues for Super-Resolution

    Super-Resolution Using Adaptive Wiener Filters, R.C. Hardie

    Introduction

    Observation Model

    AWF SR Algorithms

    Experimental Results

    Conclusions

    Acknowledgments

    Locally Adaptive Kernel Regression for Space-Time Super-Resolution, H. Takeda and P. Milanfar

    Introduction

    Adaptive Kernel Regression

    Examples

    Conclusion

    AppendiX

    Super-Resolution With Probabilistic Motion Estimation, M. Protter and M. Elad

    Introduction

    Classic Super-Resolution: Background

    The Proposed Algorithm

    Experimental Validation

    Summary

    Spatially Adaptive Filtering as Regularization in Inverse Imaging, A. Danielyan, A. Foi, V. Katkovnik, and K. Egiazarian

    Introduction

    Iterative filtering as regularization

    Compressed sensing

    Super-resolution

    Conclusions

    Registration for Super-Resolution, P. Vandewalle, L. Sbaiz, and M. Vetterli

    Camera Model

    What Is Resolution?

    Super-Resolution as a Multichannel Sampling Problem

    Registration of Totally Aliased Signals

    Registration of Partially Aliased Signals

    Conclusions

    Towards Super-Resolution in the Presence of Spatially Varying Blur, M. Sorel, F. Sroubek and J. Flusser

    Introduction

    Defocus and Optical Aberrations

    Camera Motion Blur

    Scene Motion

    Algorithms

    Conclusion

    Acknowledgments

    Toward Robust Reconstruction-Based Super-Resolution, M. Tanaka and M. Okutomi

    Introduction

    Overviews

    Robust SR Reconstruction with Pixel Selection

    Robust Super-Resolution Using MPEG Motion Vectors

    Robust Registration for Super-Resolution

    Conclusions

    Multi-Frame Super-Resolution from a Bayesian Perspective, L. Pickup, S. Roberts, A. Zisserman and D. Capel

    The Generative Model

    Where Super-Resolution Algorithms Go Wrong

    Simultaneous Super-Resolution

    Bayesian Marginalization

    Concluding Remarks

    Variational Bayesian Super Resolution Reconstruction, S. Derin Babacan, R. Molina, and A.K. Katsaggelos

    Introduction

    Problem Formulation

    Bayesian Framework for Super Resolution

    Bayesian Inference

    Variational Bayesian Inference Using TV Image Priors

    Experiments

    Estimation of Motion and Blur

    Conclusions

    Acknowledgements

    Pattern Recognition Techniques for Image Super-Resolution, K. Ni and T.Q. Nguyen

    Introduction

    Nearest Neighbor Super-Resolution

    Markov Random Fields and Approximations

    Kernel Machines for Image Super-Resolution

    Multiple Learners and Multiple Regressions

    Design Considerations and Examples

    Remarks

    Glossary

    Super-Resolution Reconstruction of Multi-Channel Images, O.G. Sezer and Y. Altunbasak

    Introduction

    Notation

    Image Acquisition Model

    Subspace Representation

    Reconstruction Algorithm

    Experiments & Discussions

    Conclusion

    New Applications of Super-Resolution in Medical Imaging, M.D.Robinson, S.J. Chiu, C.A. Toth, J.A. Izatt, J.Y. Lo, and S. Farsiu

    Introduction

    The Super-Resolution Framework

    New Medical Imaging Applications

    Conclusion

    Acknowledgment

    Practicing Super-Resolution: What Have We Learned? N. Bozinovic

    Abstract

    Introduction

    MotionDSP: History and Concepts

    Markets and Applications

    Technology

    Results

    Lessons Learned

    Conclusions

    Biography

    Peyman Milanfar is Professor of Electrical Engineering at the University of California, Santa Cruz. He received a B.S. degree in Electrical Engineering/Mathematics from the University of California, Berkeley, and the Ph.D. degree in Electrical Engineering from the Massachusetts Institute of Technology. Prior to coming to UCSC, he was at SRI (formerly Stanford Research Institute) and served as a Consulting Professor of computer science at Stanford. In 2005 he founded MotionDSP, Inc., to bring state-of-art video enhancement technology to consumer and forensic markets. He is a Fellow of the IEEE for contributions to Inverse Problems and Super-resolution in Imaging.