Salient Region Guided Blind Image Sharpness Assessment
Salient regions provide important cues for scene understanding to the human vision system. However, whether the detected salient regions are helpful in image blur estimation is unknown. In this study, a salient region guided blind image sharpness assessment (BISA) framework is proposed, and the effe...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-06-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/21/12/3963 |
| _version_ | 1797530844472016896 |
|---|---|
| author | Siqi Liu Shaode Yu Yanming Zhao Zhulin Tao Hang Yu Libiao Jin |
| author_facet | Siqi Liu Shaode Yu Yanming Zhao Zhulin Tao Hang Yu Libiao Jin |
| author_sort | Siqi Liu |
| collection | DOAJ |
| description | Salient regions provide important cues for scene understanding to the human vision system. However, whether the detected salient regions are helpful in image blur estimation is unknown. In this study, a salient region guided blind image sharpness assessment (BISA) framework is proposed, and the effect of the detected salient regions on the BISA performance is investigated. Specifically, three salient region detection (SRD) methods and ten BISA models are jointly explored, during which the output saliency maps from SRD methods are re-organized as the input of BISA models. Consequently, the change in BISA metric values can be quantified and then directly related to the difference in BISA model inputs. Finally, experiments are conducted on three Gaussian blurring image databases, and the BISA prediction performance is evaluated. The comparison results indicate that salient region input can help achieve a close and sometimes superior performance to a BISA model over the whole image input. When using the center region input as the baseline, the detected salient regions from the saliency optimization from robust background detection (SORBD) method lead to consistently better score prediction, regardless of the BISA model. Based on the proposed hybrid framework, this study reveals that saliency detection benefits image blur estimation, while how to properly incorporate SRD methods and BISA models to improve the score prediction will be explored in our future work. |
| first_indexed | 2024-03-10T10:35:47Z |
| format | Article |
| id | doaj.art-100c8d7d355d41a584f018d9f959dba4 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T10:35:47Z |
| publishDate | 2021-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-100c8d7d355d41a584f018d9f959dba42023-11-21T23:19:19ZengMDPI AGSensors1424-82202021-06-012112396310.3390/s21123963Salient Region Guided Blind Image Sharpness AssessmentSiqi Liu0Shaode Yu1Yanming Zhao2Zhulin Tao3Hang Yu4Libiao Jin5Key Laboratory of Convergent Media and Intelligent Technology (Communication University of China), Ministry of Education, Beijing 100024, ChinaKey Laboratory of Convergent Media and Intelligent Technology (Communication University of China), Ministry of Education, Beijing 100024, ChinaKey Laboratory of Convergent Media and Intelligent Technology (Communication University of China), Ministry of Education, Beijing 100024, ChinaKey Laboratory of Convergent Media and Intelligent Technology (Communication University of China), Ministry of Education, Beijing 100024, ChinaSchool of Aerospace Science and Technology, Xidian University, Xi’an 710126, ChinaKey Laboratory of Convergent Media and Intelligent Technology (Communication University of China), Ministry of Education, Beijing 100024, ChinaSalient regions provide important cues for scene understanding to the human vision system. However, whether the detected salient regions are helpful in image blur estimation is unknown. In this study, a salient region guided blind image sharpness assessment (BISA) framework is proposed, and the effect of the detected salient regions on the BISA performance is investigated. Specifically, three salient region detection (SRD) methods and ten BISA models are jointly explored, during which the output saliency maps from SRD methods are re-organized as the input of BISA models. Consequently, the change in BISA metric values can be quantified and then directly related to the difference in BISA model inputs. Finally, experiments are conducted on three Gaussian blurring image databases, and the BISA prediction performance is evaluated. The comparison results indicate that salient region input can help achieve a close and sometimes superior performance to a BISA model over the whole image input. When using the center region input as the baseline, the detected salient regions from the saliency optimization from robust background detection (SORBD) method lead to consistently better score prediction, regardless of the BISA model. Based on the proposed hybrid framework, this study reveals that saliency detection benefits image blur estimation, while how to properly incorporate SRD methods and BISA models to improve the score prediction will be explored in our future work.https://www.mdpi.com/1424-8220/21/12/3963saliency detectionimage sharpnessimage qualityGaussian blurringhuman vision system |
| spellingShingle | Siqi Liu Shaode Yu Yanming Zhao Zhulin Tao Hang Yu Libiao Jin Salient Region Guided Blind Image Sharpness Assessment Sensors saliency detection image sharpness image quality Gaussian blurring human vision system |
| title | Salient Region Guided Blind Image Sharpness Assessment |
| title_full | Salient Region Guided Blind Image Sharpness Assessment |
| title_fullStr | Salient Region Guided Blind Image Sharpness Assessment |
| title_full_unstemmed | Salient Region Guided Blind Image Sharpness Assessment |
| title_short | Salient Region Guided Blind Image Sharpness Assessment |
| title_sort | salient region guided blind image sharpness assessment |
| topic | saliency detection image sharpness image quality Gaussian blurring human vision system |
| url | https://www.mdpi.com/1424-8220/21/12/3963 |
| work_keys_str_mv | AT siqiliu salientregionguidedblindimagesharpnessassessment AT shaodeyu salientregionguidedblindimagesharpnessassessment AT yanmingzhao salientregionguidedblindimagesharpnessassessment AT zhulintao salientregionguidedblindimagesharpnessassessment AT hangyu salientregionguidedblindimagesharpnessassessment AT libiaojin salientregionguidedblindimagesharpnessassessment |