A Review on Single Image Super Resolution

Bhavana Girdharilal Lachhwani

Bhavana Girdharilal Lachhwani Bhavana Girdharilal Lachhwani, Department of Electronics and Telecommunication Matoshri College of Engineering Nashik, India

Abstract

An important vision application is rebuilding single low-Resolution (LR)
image from High-Resolution (HR) image. Many algorithms successfully planned in recent years shows efficient and robust single-image
Super-Resolution (SR) rebuilding but it still seemsinspiring by several
factors, such ascomputational load, necessary huge exemplar images,
inherent ambiguous mapping between the HR-LR images, etc. Inspired
by simple mapping functions method, a mapping matrix table of HR-LR
feature patches is calculated in the training phase. The objective of SR is
to enhance the resolution of a given LR image, which is an unremitting
ongoing process in image technology, using up-sampling, de-blurring,
de-noising, etc. To rebuild an image into a HR image correctly, it is necessary to inject high frequency components of a low-resolution image.
In requests like, medical diagnosis, satellite imaging, video surveillance,
face recognition, forensic investigation and pattern recognition, it develops essential to extract the important information from the images.
During such process, zooming the image after a certain limit results
in a blurred image with no useful information. Hardware limitations
of sensors is one of the main causes behind this problem. Also, main
objective behind achieving HR images is not to hamper the observable
quality of the image.

How to cite this article:
Lachhwani BG, Dighe D. A Review on Single Image
Super Resolution. J Adv Res Image Proc Appl
2020; 3(1): 1-3

References

1. Shang X, YangW, Zhou F et al. Anchored Neighborhood
Regression Based Single Image Super- Resolution From
Self Examples. ICIP 2016(pp:2827-2831).
2. Liu D, Wang Z, Wen B et al. Robust Single Image Super-Resolution via Deep Networks WithSparse Prior.
IEEE Transactions on image processing 2016; 25(7):
3194-3207.
3. Dong C, Loy CC, He K et al. Learning a Deep Convolutional Network for Image SuperResolution. Research
Gate Conference Paper, Sep 2014; 1-16.
4. Jiang J, Ma X, Chen C et al. Single Image Super-Resolution via Locally Regularized Anchored Neighborhood
Regression and Nonlocal Means. IEEE Transactions on
Multimedia 2016; 1-11.
5. Nezhad ZH, Karami A, Heylen R et al. Fusion of hyperspectral and multispectral images using spectral
unmixing and sparse coding. ResearchGate July 2016.
6. Kang LW, Hsu C, Zhuang B et al. Learning-Based Joint Super-Resolution and Deblocking for a Highly Compressed
Image. IEEE Transactions on Multimedia 2015; 1-13.
7. kang LW, Zhuang B, Hsu C et al. Learning-Based joint
Super-Resolution and Deblocking for a Highly Compressed Image. IEEE Transactions on multimedia 2015;
17(7): 921-933.
8. Dong W, Fu F, Shi G et al. Hyper spectral image super-resolution via non-negative structured sparse representation. IEEE Transactions on image processing
2016; 25(5).