A Short Survey of Image Super Resolution Algorithms

Authors

  • Dongdong Huang School of Computer Science and Technology, Anhui University of Technology
  • Heng Liu School of Computer Science and Technology, Anhui University of Technology

Keywords:

Image super resolution, Interpolation based super resolution, Reconstruction based super resolution, Learning based super resolution

Abstract

Image super resolution is to estimate a high resolution image from a low resolution image or a sequence of low resolution images using image processing and machine learning technology. So far, there have emerged lots of super resolution algorithms. According to the input number of image, these algorithms can usually be divided as single image based algorithm and multiple images based algorithm. And according to technique principle, these algorithms can also be divided into three categories - interpolation based algorithm, reconstruction based algorithm and learning based one. This work mainly addresses the basic principle and different strategy of super resolution algorithms in detail. Then, the evaluation criteria and its application issues of super resolution are also discussed in the end.

Downloads

Published

2015-12-30

Issue

Vol. 2 No. 2 (2015)

Section

Articles

License

Policy for Journals/Articles with Open Access

Authors who publish with this journal agree to the following terms:
    1. Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.

  1. Authors are permitted and encouraged to post links to their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work

Policy for Journals / Manuscript with Paid Access

Authors who publish with this journal agree to the following terms:
    1. Publisher retain copyright .

  1. Authors are permitted and encouraged to post links to their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work .