Image dehazing using two‐dimensional canonical correlation analysis
Image dehazing is an important issue that interests both image processing and computer vision. In this study, image dehazing is modelled as an example‐based learning problem, and a novel dehazing algorithm using two‐dimensional (2D) canonical correlation analysis (CCA) is proposed. By assuming that...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2015-12-01
|
| Series: | IET Computer Vision |
| Subjects: | |
| Online Access: | https://doi.org/10.1049/iet-cvi.2014.0324 |
| _version_ | 1827817646707441664 |
|---|---|
| author | Liqian Wang Liang Xiao Zhihui Wei |
| author_facet | Liqian Wang Liang Xiao Zhihui Wei |
| author_sort | Liqian Wang |
| collection | DOAJ |
| description | Image dehazing is an important issue that interests both image processing and computer vision. In this study, image dehazing is modelled as an example‐based learning problem, and a novel dehazing algorithm using two‐dimensional (2D) canonical correlation analysis (CCA) is proposed. By assuming that the hazy‐free image patches are smooth and the pixel intensities in the same patch are approximate to constant, the authors deduce an underlying linear correlation between the observed hazy image patches and corresponding transmission patches. By maximising the correlation between the patch‐pairs of hazy image and corresponding transmission map, 2D CCA is able to learn a subspace to reconstruct the reliable transmission. Thus, given a test hazy image, the transmission map is aggregated by the nearest neighbour patches in the subspace and then globally refined by a local mean adaptive guided filter. The final hazy‐free image is obtained by using the dichromatic atmospheric model. Experimental results demonstrate the efficiency of the proposed method in single image dehazing. |
| first_indexed | 2024-03-12T00:37:12Z |
| format | Article |
| id | doaj.art-79094cd7c8954d018ef5451440778367 |
| institution | Directory Open Access Journal |
| issn | 1751-9632 1751-9640 |
| language | English |
| last_indexed | 2024-03-12T00:37:12Z |
| publishDate | 2015-12-01 |
| publisher | Wiley |
| record_format | Article |
| series | IET Computer Vision |
| spelling | doaj.art-79094cd7c8954d018ef54514407783672023-09-15T09:29:27ZengWileyIET Computer Vision1751-96321751-96402015-12-019690391310.1049/iet-cvi.2014.0324Image dehazing using two‐dimensional canonical correlation analysisLiqian Wang0Liang Xiao1Zhihui Wei2School of Computer Science and EngineeringNanjing University of Science and TechnologyNanjing210094People's Republic of ChinaSchool of Computer Science and EngineeringNanjing University of Science and TechnologyNanjing210094People's Republic of ChinaSchool of Computer Science and EngineeringNanjing University of Science and TechnologyNanjing210094People's Republic of ChinaImage dehazing is an important issue that interests both image processing and computer vision. In this study, image dehazing is modelled as an example‐based learning problem, and a novel dehazing algorithm using two‐dimensional (2D) canonical correlation analysis (CCA) is proposed. By assuming that the hazy‐free image patches are smooth and the pixel intensities in the same patch are approximate to constant, the authors deduce an underlying linear correlation between the observed hazy image patches and corresponding transmission patches. By maximising the correlation between the patch‐pairs of hazy image and corresponding transmission map, 2D CCA is able to learn a subspace to reconstruct the reliable transmission. Thus, given a test hazy image, the transmission map is aggregated by the nearest neighbour patches in the subspace and then globally refined by a local mean adaptive guided filter. The final hazy‐free image is obtained by using the dichromatic atmospheric model. Experimental results demonstrate the efficiency of the proposed method in single image dehazing.https://doi.org/10.1049/iet-cvi.2014.0324image dehazingtwo-dimensional canonical correlation analysisimage processingcomputer visiondehazing algorithmhazy-free image patches |
| spellingShingle | Liqian Wang Liang Xiao Zhihui Wei Image dehazing using two‐dimensional canonical correlation analysis IET Computer Vision image dehazing two-dimensional canonical correlation analysis image processing computer vision dehazing algorithm hazy-free image patches |
| title | Image dehazing using two‐dimensional canonical correlation analysis |
| title_full | Image dehazing using two‐dimensional canonical correlation analysis |
| title_fullStr | Image dehazing using two‐dimensional canonical correlation analysis |
| title_full_unstemmed | Image dehazing using two‐dimensional canonical correlation analysis |
| title_short | Image dehazing using two‐dimensional canonical correlation analysis |
| title_sort | image dehazing using two dimensional canonical correlation analysis |
| topic | image dehazing two-dimensional canonical correlation analysis image processing computer vision dehazing algorithm hazy-free image patches |
| url | https://doi.org/10.1049/iet-cvi.2014.0324 |
| work_keys_str_mv | AT liqianwang imagedehazingusingtwodimensionalcanonicalcorrelationanalysis AT liangxiao imagedehazingusingtwodimensionalcanonicalcorrelationanalysis AT zhihuiwei imagedehazingusingtwodimensionalcanonicalcorrelationanalysis |