Defocus Blur Detection and Estimation from Imaging Sensors
Sparse representation has been proven to be a very effective technique for various image restoration applications. In this paper, an improved sparse representation based method is proposed to detect and estimate defocus blur of imaging sensors. Considering the fact that the patterns usually vary rem...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2018-04-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | http://www.mdpi.com/1424-8220/18/4/1135 |
| _version_ | 1828138142867128320 |
|---|---|
| author | Jinyang Li Zhijing Liu Yong Yao |
| author_facet | Jinyang Li Zhijing Liu Yong Yao |
| author_sort | Jinyang Li |
| collection | DOAJ |
| description | Sparse representation has been proven to be a very effective technique for various image restoration applications. In this paper, an improved sparse representation based method is proposed to detect and estimate defocus blur of imaging sensors. Considering the fact that the patterns usually vary remarkably across different images or different patches in a single image, it is unstable and time-consuming for sparse representation over an over-complete dictionary. We propose an adaptive domain selection scheme to prelearn a set of compact dictionaries and adaptively select the optimal dictionary to each image patch. Then, with nonlocal structure similarity, the proposed method learns nonzero-mean coefficients’ distributions that are much more closer to the real ones. More accurate sparse coefficients can be obtained and further improve the performance of results. Experimental results validate that the proposed method outperforms existing defocus blur estimation approaches, both qualitatively and quantitatively. |
| first_indexed | 2024-04-11T18:31:25Z |
| format | Article |
| id | doaj.art-dcf7e443ac744bf2a382eb8c1b4cf772 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-04-11T18:31:25Z |
| publishDate | 2018-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-dcf7e443ac744bf2a382eb8c1b4cf7722022-12-22T04:09:27ZengMDPI AGSensors1424-82202018-04-01184113510.3390/s18041135s18041135Defocus Blur Detection and Estimation from Imaging SensorsJinyang Li0Zhijing Liu1Yong Yao2School of Computer Science and Technology, Xidian University, Xi’an 710071, Shannxi, ChinaSchool of Computer Science and Technology, Xidian University, Xi’an 710071, Shannxi, ChinaSchool of Computer Science and Technology, Xidian University, Xi’an 710071, Shannxi, ChinaSparse representation has been proven to be a very effective technique for various image restoration applications. In this paper, an improved sparse representation based method is proposed to detect and estimate defocus blur of imaging sensors. Considering the fact that the patterns usually vary remarkably across different images or different patches in a single image, it is unstable and time-consuming for sparse representation over an over-complete dictionary. We propose an adaptive domain selection scheme to prelearn a set of compact dictionaries and adaptively select the optimal dictionary to each image patch. Then, with nonlocal structure similarity, the proposed method learns nonzero-mean coefficients’ distributions that are much more closer to the real ones. More accurate sparse coefficients can be obtained and further improve the performance of results. Experimental results validate that the proposed method outperforms existing defocus blur estimation approaches, both qualitatively and quantitatively.http://www.mdpi.com/1424-8220/18/4/1135sparse representationdefocus bluradaptive domain selectioncompact dictionariesnonlocal structure similaritycoefficients’ distributions |
| spellingShingle | Jinyang Li Zhijing Liu Yong Yao Defocus Blur Detection and Estimation from Imaging Sensors Sensors sparse representation defocus blur adaptive domain selection compact dictionaries nonlocal structure similarity coefficients’ distributions |
| title | Defocus Blur Detection and Estimation from Imaging Sensors |
| title_full | Defocus Blur Detection and Estimation from Imaging Sensors |
| title_fullStr | Defocus Blur Detection and Estimation from Imaging Sensors |
| title_full_unstemmed | Defocus Blur Detection and Estimation from Imaging Sensors |
| title_short | Defocus Blur Detection and Estimation from Imaging Sensors |
| title_sort | defocus blur detection and estimation from imaging sensors |
| topic | sparse representation defocus blur adaptive domain selection compact dictionaries nonlocal structure similarity coefficients’ distributions |
| url | http://www.mdpi.com/1424-8220/18/4/1135 |
| work_keys_str_mv | AT jinyangli defocusblurdetectionandestimationfromimagingsensors AT zhijingliu defocusblurdetectionandestimationfromimagingsensors AT yongyao defocusblurdetectionandestimationfromimagingsensors |