Improved salient object detection via boundary components affinity
Referring to the existing model that considers the image boundary as the image background, the model is still not able to produce an optimum detection. This paper is introducing the combination features at the boundary known as boundary components affinity that is capable to produce an optimum measu...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Universiti Putra Malaysia Press
2019
|
| Online Access: | http://psasir.upm.edu.my/id/eprint/76320/ http://psasir.upm.edu.my/id/eprint/76320/1/17%20JST-1475-2018.pdf |
| _version_ | 1848857934413430784 |
|---|---|
| author | Nadzri, Nur Zulaikhah Marhaban, Mohammad Hamiruce Ahmad, Siti Anom Ishak, Asnor Juraiza Mohd Zin, Zalhan |
| author_facet | Nadzri, Nur Zulaikhah Marhaban, Mohammad Hamiruce Ahmad, Siti Anom Ishak, Asnor Juraiza Mohd Zin, Zalhan |
| author_sort | Nadzri, Nur Zulaikhah |
| building | UPM Institutional Repository |
| collection | Online Access |
| description | Referring to the existing model that considers the image boundary as the image background, the model is still not able to produce an optimum detection. This paper is introducing the combination features at the boundary known as boundary components affinity that is capable to produce an optimum measure on the image background. It consists of contrast, spatial location, force interaction and boundary ratio that contribute to a novel boundary connectivity measure. The integrated features are capable to produce clearer background with minimum unwanted foreground patches compared to the ground truth. The extracted boundary features are integrated as the boundary components affinity. These features were used for measuring the image background through its boundary connectivity to obtain the final salient object detection. Using the verified datasets, the performance of the proposed model was measured and compared with the 4 state-of-art models. In addition, the model performance was tested on the close contrast images. The detection performance was compared and analysed based on the precision, recall, true positive rate, false positive rate, F Measure and Mean Absolute Error (MAE). The model had successfully reduced the MAE by maximum of 9.4%. |
| first_indexed | 2025-11-15T12:05:26Z |
| format | Article |
| id | upm-76320 |
| institution | Universiti Putra Malaysia |
| institution_category | Local University |
| language | English |
| last_indexed | 2025-11-15T12:05:26Z |
| publishDate | 2019 |
| publisher | Universiti Putra Malaysia Press |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | upm-763202020-02-04T03:50:27Z http://psasir.upm.edu.my/id/eprint/76320/ Improved salient object detection via boundary components affinity Nadzri, Nur Zulaikhah Marhaban, Mohammad Hamiruce Ahmad, Siti Anom Ishak, Asnor Juraiza Mohd Zin, Zalhan Referring to the existing model that considers the image boundary as the image background, the model is still not able to produce an optimum detection. This paper is introducing the combination features at the boundary known as boundary components affinity that is capable to produce an optimum measure on the image background. It consists of contrast, spatial location, force interaction and boundary ratio that contribute to a novel boundary connectivity measure. The integrated features are capable to produce clearer background with minimum unwanted foreground patches compared to the ground truth. The extracted boundary features are integrated as the boundary components affinity. These features were used for measuring the image background through its boundary connectivity to obtain the final salient object detection. Using the verified datasets, the performance of the proposed model was measured and compared with the 4 state-of-art models. In addition, the model performance was tested on the close contrast images. The detection performance was compared and analysed based on the precision, recall, true positive rate, false positive rate, F Measure and Mean Absolute Error (MAE). The model had successfully reduced the MAE by maximum of 9.4%. Universiti Putra Malaysia Press 2019 Article PeerReviewed text en http://psasir.upm.edu.my/id/eprint/76320/1/17%20JST-1475-2018.pdf Nadzri, Nur Zulaikhah and Marhaban, Mohammad Hamiruce and Ahmad, Siti Anom and Ishak, Asnor Juraiza and Mohd Zin, Zalhan (2019) Improved salient object detection via boundary components affinity. Pertanika Journal of Science & Technology, 27 (4). pp. 1735-1758. ISSN 0128-7680; ESSN: 2231-8526 http://www.pertanika.upm.edu.my/Pertanika%20PAPERS/JST%20Vol.%2027%20(4)%20Oct.%202019/17%20JST-1475-2018.pdf |
| spellingShingle | Nadzri, Nur Zulaikhah Marhaban, Mohammad Hamiruce Ahmad, Siti Anom Ishak, Asnor Juraiza Mohd Zin, Zalhan Improved salient object detection via boundary components affinity |
| title | Improved salient object detection via boundary components affinity |
| title_full | Improved salient object detection via boundary components affinity |
| title_fullStr | Improved salient object detection via boundary components affinity |
| title_full_unstemmed | Improved salient object detection via boundary components affinity |
| title_short | Improved salient object detection via boundary components affinity |
| title_sort | improved salient object detection via boundary components affinity |
| url | http://psasir.upm.edu.my/id/eprint/76320/ http://psasir.upm.edu.my/id/eprint/76320/ http://psasir.upm.edu.my/id/eprint/76320/1/17%20JST-1475-2018.pdf |