Multi‐scale contrast‐based saliency enhancement for salient object detection
To achieve more complete and more uniformly highlighted salient object regions, this study presents a computational saliency enhancement model that incorporates the properties of multi‐scale and logarithmic response into the local and global contrasts. A distinct feature of the authors model is a no...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2014-06-01
|
| Series: | IET Computer Vision |
| Subjects: | |
| Online Access: | https://doi.org/10.1049/iet-cvi.2013.0118 |
| _version_ | 1797685200122019840 |
|---|---|
| author | Wenhui Zhou Teng Song Lili Lin Andrew Lumsdaine |
| author_facet | Wenhui Zhou Teng Song Lili Lin Andrew Lumsdaine |
| author_sort | Wenhui Zhou |
| collection | DOAJ |
| description | To achieve more complete and more uniformly highlighted salient object regions, this study presents a computational saliency enhancement model that incorporates the properties of multi‐scale and logarithmic response into the local and global contrasts. A distinct feature of the authors model is a novel saliency enhancement operator. This operator can effectively enhance the saliency of object interior regions while simultaneously reducing blur on object boundaries caused by multiple scales. Their model is a general one that can make flexible tradeoffs between precision and recall. Detailed comparisons with 12 state‐of‐the‐art methods show that their method can obtain satisfactory salient object regions that are closer to the human‐labelled results. In addition, their method provides superior results in precision–recall, F‐measure and mean absolute error. |
| first_indexed | 2024-03-12T00:41:41Z |
| format | Article |
| id | doaj.art-df56f867453c4690934e5aec697ff02e |
| institution | Directory Open Access Journal |
| issn | 1751-9632 1751-9640 |
| language | English |
| last_indexed | 2024-03-12T00:41:41Z |
| publishDate | 2014-06-01 |
| publisher | Wiley |
| record_format | Article |
| series | IET Computer Vision |
| spelling | doaj.art-df56f867453c4690934e5aec697ff02e2023-09-15T07:15:52ZengWileyIET Computer Vision1751-96321751-96402014-06-018320721510.1049/iet-cvi.2013.0118Multi‐scale contrast‐based saliency enhancement for salient object detectionWenhui Zhou0Teng Song1Lili Lin2Andrew Lumsdaine3School of Computer Science and TechnologyHangzhou Dianzi UniversityHangZhou310018People's Republic of ChinaSchool of Computer Science and TechnologyHangzhou Dianzi UniversityHangZhou310018People's Republic of ChinaSchool of Information and Electronic EngineeringZhejiang Gongshang UniversityHangZhou310018People's Republic of ChinaComputer Science DepartmentIndianav UniversityBloomingtonIN47405USATo achieve more complete and more uniformly highlighted salient object regions, this study presents a computational saliency enhancement model that incorporates the properties of multi‐scale and logarithmic response into the local and global contrasts. A distinct feature of the authors model is a novel saliency enhancement operator. This operator can effectively enhance the saliency of object interior regions while simultaneously reducing blur on object boundaries caused by multiple scales. Their model is a general one that can make flexible tradeoffs between precision and recall. Detailed comparisons with 12 state‐of‐the‐art methods show that their method can obtain satisfactory salient object regions that are closer to the human‐labelled results. In addition, their method provides superior results in precision–recall, F‐measure and mean absolute error.https://doi.org/10.1049/iet-cvi.2013.0118multiscale contrast-based saliency enhancement operatorsalient object detectioncomputational saliency enhancement modellogarithmic response propertyobject interior regionblur reduction |
| spellingShingle | Wenhui Zhou Teng Song Lili Lin Andrew Lumsdaine Multi‐scale contrast‐based saliency enhancement for salient object detection IET Computer Vision multiscale contrast-based saliency enhancement operator salient object detection computational saliency enhancement model logarithmic response property object interior region blur reduction |
| title | Multi‐scale contrast‐based saliency enhancement for salient object detection |
| title_full | Multi‐scale contrast‐based saliency enhancement for salient object detection |
| title_fullStr | Multi‐scale contrast‐based saliency enhancement for salient object detection |
| title_full_unstemmed | Multi‐scale contrast‐based saliency enhancement for salient object detection |
| title_short | Multi‐scale contrast‐based saliency enhancement for salient object detection |
| title_sort | multi scale contrast based saliency enhancement for salient object detection |
| topic | multiscale contrast-based saliency enhancement operator salient object detection computational saliency enhancement model logarithmic response property object interior region blur reduction |
| url | https://doi.org/10.1049/iet-cvi.2013.0118 |
| work_keys_str_mv | AT wenhuizhou multiscalecontrastbasedsaliencyenhancementforsalientobjectdetection AT tengsong multiscalecontrastbasedsaliencyenhancementforsalientobjectdetection AT lililin multiscalecontrastbasedsaliencyenhancementforsalientobjectdetection AT andrewlumsdaine multiscalecontrastbasedsaliencyenhancementforsalientobjectdetection |