Salient object detection through over-segmentation
In this paper we present a salient object detection model from an over-segmented image. The input image is initially segmented by the mean-shift segmentation algorithm and then over-segmented by a quad mesh to even smaller segments. Such segmented regions overcome the disadvantage of using patches o...
| Main Authors: | , , , |
|---|---|
| Other Authors: | |
| Format: | Conference Paper |
| Language: | English |
| Published: |
2013
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/99487 http://hdl.handle.net/10220/12929 |
| _version_ | 1811696621562363904 |
|---|---|
| author | Zhang, Xuejie Ren, Zhixiang Rajan, Deepu Hu, Yiqun |
| author2 | School of Computer Engineering |
| author_facet | School of Computer Engineering Zhang, Xuejie Ren, Zhixiang Rajan, Deepu Hu, Yiqun |
| author_sort | Zhang, Xuejie |
| collection | NTU |
| description | In this paper we present a salient object detection model from an over-segmented image. The input image is initially segmented by the mean-shift segmentation algorithm and then over-segmented by a quad mesh to even smaller segments. Such segmented regions overcome the disadvantage of using patches or single pixels to compute saliency. Segments that are similar and spread over the image receive low saliency and a segment which is distinct in the whole image or in a local region receives high saliency. We express this as a color compactness measure which is used to derive saliency level directly. Our method is shown to outperform six existing methods in the literature using a saliency detection database containing images with human-labeled object contour ground truth. The proposed saliency model has been shown to be useful for an image retargeting application. |
| first_indexed | 2024-10-01T07:42:17Z |
| format | Conference Paper |
| id | ntu-10356/99487 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T07:42:17Z |
| publishDate | 2013 |
| record_format | dspace |
| spelling | ntu-10356/994872020-05-28T07:18:57Z Salient object detection through over-segmentation Zhang, Xuejie Ren, Zhixiang Rajan, Deepu Hu, Yiqun School of Computer Engineering IEEE International Conference on Multimedia and Expo (2012 : Melbourne, Australia) DRNTU::Engineering::Computer science and engineering In this paper we present a salient object detection model from an over-segmented image. The input image is initially segmented by the mean-shift segmentation algorithm and then over-segmented by a quad mesh to even smaller segments. Such segmented regions overcome the disadvantage of using patches or single pixels to compute saliency. Segments that are similar and spread over the image receive low saliency and a segment which is distinct in the whole image or in a local region receives high saliency. We express this as a color compactness measure which is used to derive saliency level directly. Our method is shown to outperform six existing methods in the literature using a saliency detection database containing images with human-labeled object contour ground truth. The proposed saliency model has been shown to be useful for an image retargeting application. 2013-08-02T06:47:50Z 2019-12-06T20:08:00Z 2013-08-02T06:47:50Z 2019-12-06T20:08:00Z 2012 2012 Conference Paper https://hdl.handle.net/10356/99487 http://hdl.handle.net/10220/12929 10.1109/ICME.2012.166 en |
| spellingShingle | DRNTU::Engineering::Computer science and engineering Zhang, Xuejie Ren, Zhixiang Rajan, Deepu Hu, Yiqun Salient object detection through over-segmentation |
| title | Salient object detection through over-segmentation |
| title_full | Salient object detection through over-segmentation |
| title_fullStr | Salient object detection through over-segmentation |
| title_full_unstemmed | Salient object detection through over-segmentation |
| title_short | Salient object detection through over-segmentation |
| title_sort | salient object detection through over segmentation |
| topic | DRNTU::Engineering::Computer science and engineering |
| url | https://hdl.handle.net/10356/99487 http://hdl.handle.net/10220/12929 |
| work_keys_str_mv | AT zhangxuejie salientobjectdetectionthroughoversegmentation AT renzhixiang salientobjectdetectionthroughoversegmentation AT rajandeepu salientobjectdetectionthroughoversegmentation AT huyiqun salientobjectdetectionthroughoversegmentation |