Open Access Open Access  Restricted Access Subscription Access

Reconstruction Techniques for Super Resolution Using Low Resolution Images

Devidas Dighe, Gajanan K. Kharate, Varsha H. Patil

Abstract


The aim of Super Resolution (SR) reconstruction is to restore High Resolution (HR) image using information obtained from many degraded and aliased Low Resolution (LR) images. SR is signal processing for bandwidth expansion beyond the pass band of the imaging hardware system by using spatio-temporal information available from LR images. Over last three-decade various researchers contributed in the field of SR, but all are intuitive SR mechanisms. This paper employs Kerens algorithm for registration, which is an iterative algorithm and more accurate than other. Algorithm find the rotation angle by using a 3-parameter affine transformation generated using Gaussian pyramid. Thereafter various reconstruction techniques are applied and analyzed for quality of reconstruction in objective and subjective way revel that execution time for convolution approach is highest but subjective quality is better than the others and interpolation is the fastest approach, butresult is blurred.


Keywords


Super resolution, registration, reconstruction, blurring, interpolation, convolution

Full Text:

PDF

References


Andrey Krokhin, Super-Resolution in Image Sequences, A Thesis at Department of Electrical and Computer Engineering Northeastern University Boston, Massachusetts September 2005.

Park S, Park M, Kang M. Super-Resolution Image Reconstruction: A Technical Overview, IEEE Signal Process Mag. Mar. 2003; 20(3): 21–36p.

Devidas D. Dighe, Ingole DT, Gajanan K.Kharate. 18th and 19th August 2017. Registration of multiple low resolution images for motion using hybrid approach, International Conference on Contents, Computing and Communication, Organized by Matoshri College of Engineering and Research Center in Association with Savitribai Phule University of Pune (former University of Pune).

Devidas D. Dighe, Gajanan K. Kharate, Varsha H. Patil. Enhancing the Still Image Using Super Resolution Techniques: A Review, J Multimedia Technology Recent Advancements. 2(2).

Sean Borman, Robert Stevenson, Spatial Resolution Enhancement of Low-Resolution Image Sequences A Comprehensive Review with Directions for Future Research, University of Notre Dame, Notre, July 8, 1998, IN 46556-

Tsai RY, Huang TS. Multiform Image Registration and Restoration, Adv Comput Vis Image Process. 1984; I.

Anil K. Jain, Fundamentals of Digital Image Processing, Prentice-Hall of India Private Limited, New Delhi, 2007.

Peter N. Crabtree, Collin Seanor, Jeremy Murray-Krezan, Patrick J. McNicholl, Robust global image registration based on a hybrid algorithm combining Fourier and spatial domain techniques.

Luca Lucchese, Guido Maria Cortelazzo, A Noise-Robust Frequency Domain Technique for Estimating Planar Roto-Translations, IEEE Trans Signal Process. 48(6): 1769–1786p.

Tuan Q. Pham, Lucas J. van Vliet, Klamer Schutte, Robust Fusion of Irregularly Sampled Data Using Adaptive Normalized Convolution, Hindawi Publishing Corporation EURASIP J Appl Signal Process. 2006, Article ID 83268, 1–12p.

Mohamed SA, Helmi AK, Fkirin MA, Badwai SM. Subpixel Accuracy Analysis of Phase Correlation Shift Measurement Methods Applied to Satellite Imagery, (IJACSA) Int J Adv Comput Sci Appl. 2012; 3(12).

Priyam Chatterjee, Sujata Mukherjee, Subhasis Chaudhuri, Guna Seetharaman, Application of Papoulis-Gerchberg Method in Image Super-resolution and Inpainting, The Author 2005. Published by Oxford University Press on behalf of The British Computer Society. Comput J. 2007; 00(0).

Tekalp AM, Ozkan MK, Sezan MI. High-Resolution Image Reconstruction from Lower-Resolution Image Sequences and Space-Varying Image Restoration, Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing, San Francisco, CA, 1992; II: 169–172p.

Ali Ajdar Rad, Laurence Meylan, Patrick Vandewalle, Sabine Susstrunk Ecole Polytechnique 1015 Lausanne, Switzerland, Multidimensional Image Enhancement from a Set of Unregistered and Dierently Exposed Images.

Jianchao Yang, Thomas Huang, A book on Image super-resolution: Historical overview and future challenges, chapter one, University of Illinois at Urbana-Champaign.

Luca Lucchese, Gianfranco Doretto, Guido Maria Cortelazzo, A Frequency Domain Technique for Range Data Registration, IEEE Trans Pattern Anal Mach Intell. November 2002; 24(11).

Michel Irani, Shmuel Peleg, Improving Resolution by Image Registration, CVGIP Graphics Model Image Process. 53(3): 231-239p.

Assaf Zomet, Alex Rav-Acha, Shmuel Peleg, Robust Image Super Resolution,

Sina Farsiu, Dirk Robinson Michael Elad M, Peyman Milanfar, Fast and Robust Multiframe Super Resolution, IEEE Trans Image Process. October 2004; 13(10).

Patrick Vandewalle, Super-Resolution from Unregistered Aliased Images, Thèse No 3591 École Polytechnique Fédérale De Lausanne Présentée Le 21 Juillet, 2006.

Budi Setiyono, Mochamad Hariadi, Mauridhi Hery Purnomo, Super resolution Using Papoulis-Gerchberg Algorithm Based Phase Based Image Matching, J Ilmiah KURSOR. January 2012; 6(3): hlm.159–166.

Patrick Vandewalle, Luciano Sbaiz, Joos Vandewalle, Martin Vetterli, Super-Resolution from Unregistered and Totally Aliased Signals Using Subspace Methods, IEEE Trans Signal Process. July 2007; 55,(7).




DOI: https://doi.org/10.37591/rrjoesa.v9i2.834

Refbacks

  • There are currently no refbacks.


Copyright (c) 2021 Research & Reviews: A Journal of Embedded System & Applications