Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

A Survey of Blur Detection and Sharpness Assessment MethodsSummary and Future Directions

A Survey of Blur Detection and Sharpness Assessment Methods: Summary and Future Directions CH AP TE R 5 SummaryandFuture Directions 5.1 SUMMARY Blur is an almost omnipresent effect on imageand video.It can representa challengein several applications ranging from applications in microscopy imaging to images acquired with tele- scopes.Imageprocessingandcomputervisionalgorithmsusuallypresentunexpectedbehaviors when the analyzed image is partially or totally blurred. One alternative can be to define a blur map of an image or a video frame, and based on it the image processing or computer vision algorithmscan workonly overthe non-blurredpartoftheimage,or basedontheblurmap the image can be selectively improved by using blind deconvolution algorithms. The phenomenon of the main sources of image blurring; i.e, defocus, motion, and atmo- spheric,werepresented.Out-of-focusandmotionblurarethemostcommonsourcesofblurring; therefore, in Chapter 2 a survey of the approaches used to estimate blur maps is presented. Al- gorithms using gradients, kurtosis, local autocorrelation congruency, transforms, singular value decomposition, the rank of local patches, sparse representation, reblurring, and multi-feature are explained in detail. Additionally, a novel method proposed by the author is presented and compared with state-of-the art algorithms. The dataset of Shi et al. [ 38], which provides 704 testingimageswiththeircorrespondinggroundtruthblurringmaps,wereusedinthequantita- tive comparison. Sometimesasinglevalueindicatingthedegreeofblurrinessofthewholeimageisneces- sary. This type of methods falls within the image quality assessment area. Image quality assess- ment methods can be categorized as full-reference, reduced-reference, and no-reference http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png

A Survey of Blur Detection and Sharpness Assessment MethodsSummary and Future Directions

Part of the Synthesis Lectures on Algorithms and Software in Engineering Book Series
Andrade, Juan
Springer Journals — Jan 1, 2021
Download PDF
1 page

Loading next page...
 
/lp/springer-journals/a-survey-of-blur-detection-and-sharpness-assessment-methods-summary-FQlLciBcsI
Publisher
Springer International Publishing
Copyright
© Springer Nature Switzerland AG 2021
ISBN
978-3-031-00401-8
Pages
73 –74
DOI
10.1007/978-3-031-01529-8_5
Publisher site
See Chapter on Publisher Site

Abstract

CH AP TE R 5 SummaryandFuture Directions 5.1 SUMMARY Blur is an almost omnipresent effect on imageand video.It can representa challengein several applications ranging from applications in microscopy imaging to images acquired with tele- scopes.Imageprocessingandcomputervisionalgorithmsusuallypresentunexpectedbehaviors when the analyzed image is partially or totally blurred. One alternative can be to define a blur map of an image or a video frame, and based on it the image processing or computer vision algorithmscan workonly overthe non-blurredpartoftheimage,or basedontheblurmap the image can be selectively improved by using blind deconvolution algorithms. The phenomenon of the main sources of image blurring; i.e, defocus, motion, and atmo- spheric,werepresented.Out-of-focusandmotionblurarethemostcommonsourcesofblurring; therefore, in Chapter 2 a survey of the approaches used to estimate blur maps is presented. Al- gorithms using gradients, kurtosis, local autocorrelation congruency, transforms, singular value decomposition, the rank of local patches, sparse representation, reblurring, and multi-feature are explained in detail. Additionally, a novel method proposed by the author is presented and compared with state-of-the art algorithms. The dataset of Shi et al. [ 38], which provides 704 testingimageswiththeircorrespondinggroundtruthblurringmaps,wereusedinthequantita- tive comparison. Sometimesasinglevalueindicatingthedegreeofblurrinessofthewholeimageisneces- sary. This type of methods falls within the image quality assessment area. Image quality assess- ment methods can be categorized as full-reference, reduced-reference, and no-reference

Published: Jan 1, 2021

There are no references for this article.