Advertising Image Saliency Prediction Method Based on Score Level Fusion
At present, visual saliency prediction algorithms have been developed more and more mature, but most of the current saliency prediction algorithms are aimed at natural images. Due to the inconsistency of elements and features between natural images and advertising images, the existing saliency predi...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2023-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10016709/ |
| _version_ | 1797938836426194944 |
|---|---|
| author | Qiqi Kou Ruihang Liu Chen Lv He Jiang Deqiang Cheng |
| author_facet | Qiqi Kou Ruihang Liu Chen Lv He Jiang Deqiang Cheng |
| author_sort | Qiqi Kou |
| collection | DOAJ |
| description | At present, visual saliency prediction algorithms have been developed more and more mature, but most of the current saliency prediction algorithms are aimed at natural images. Due to the inconsistency of elements and features between natural images and advertising images, the existing saliency prediction algorithms show poor robustness and low inference speed to advertising images, which severely limits its commercial application in advertising design and evaluation. In view of this, a saliency prediction algorithm for advertisement images is proposed in this paper. In the feature extraction stage, two text candidate regions based on intensity feature and improved MESR algorithm are first obtained and further integrated to produce a two-dimensional text confidence score. Meanwhile, a saliency confidence score is also obtained by an improved natural image saliency prediction network. Then, the score level fusion strategy was adopted to fuse the two confidence scores to get the final saliency prediction map. The experimental results show that the proposed model has good accuracy and robustness in advertising images, as well as the most remarkable inference speed, which can meet the demand for real-time performance of advertising image saliency prediction, leading to great practical and commercial value. |
| first_indexed | 2024-04-10T19:07:06Z |
| format | Article |
| id | doaj.art-c34c97820dc7460e9fff1d07fb6b50b8 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-04-10T19:07:06Z |
| publishDate | 2023-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-c34c97820dc7460e9fff1d07fb6b50b82023-01-31T00:00:18ZengIEEEIEEE Access2169-35362023-01-01118455846610.1109/ACCESS.2023.323680710016709Advertising Image Saliency Prediction Method Based on Score Level FusionQiqi Kou0https://orcid.org/0000-0003-2873-2636Ruihang Liu1Chen Lv2https://orcid.org/0000-0002-2079-9417He Jiang3https://orcid.org/0000-0002-3345-9665Deqiang Cheng4https://orcid.org/0000-0001-8831-1994School of Computer Science and Technology, China University of Mining and Technology, Xuzhou, ChinaSchool of Information and Control Engineering, China University of Mining and Technology, Xuzhou, ChinaSchool of Information and Control Engineering, China University of Mining and Technology, Xuzhou, ChinaSchool of Information and Control Engineering, China University of Mining and Technology, Xuzhou, ChinaSchool of Information and Control Engineering, China University of Mining and Technology, Xuzhou, ChinaAt present, visual saliency prediction algorithms have been developed more and more mature, but most of the current saliency prediction algorithms are aimed at natural images. Due to the inconsistency of elements and features between natural images and advertising images, the existing saliency prediction algorithms show poor robustness and low inference speed to advertising images, which severely limits its commercial application in advertising design and evaluation. In view of this, a saliency prediction algorithm for advertisement images is proposed in this paper. In the feature extraction stage, two text candidate regions based on intensity feature and improved MESR algorithm are first obtained and further integrated to produce a two-dimensional text confidence score. Meanwhile, a saliency confidence score is also obtained by an improved natural image saliency prediction network. Then, the score level fusion strategy was adopted to fuse the two confidence scores to get the final saliency prediction map. The experimental results show that the proposed model has good accuracy and robustness in advertising images, as well as the most remarkable inference speed, which can meet the demand for real-time performance of advertising image saliency prediction, leading to great practical and commercial value.https://ieeexplore.ieee.org/document/10016709/Saliency predictioneye-gaze assessmentadvertising imagescore level fusion |
| spellingShingle | Qiqi Kou Ruihang Liu Chen Lv He Jiang Deqiang Cheng Advertising Image Saliency Prediction Method Based on Score Level Fusion IEEE Access Saliency prediction eye-gaze assessment advertising image score level fusion |
| title | Advertising Image Saliency Prediction Method Based on Score Level Fusion |
| title_full | Advertising Image Saliency Prediction Method Based on Score Level Fusion |
| title_fullStr | Advertising Image Saliency Prediction Method Based on Score Level Fusion |
| title_full_unstemmed | Advertising Image Saliency Prediction Method Based on Score Level Fusion |
| title_short | Advertising Image Saliency Prediction Method Based on Score Level Fusion |
| title_sort | advertising image saliency prediction method based on score level fusion |
| topic | Saliency prediction eye-gaze assessment advertising image score level fusion |
| url | https://ieeexplore.ieee.org/document/10016709/ |
| work_keys_str_mv | AT qiqikou advertisingimagesaliencypredictionmethodbasedonscorelevelfusion AT ruihangliu advertisingimagesaliencypredictionmethodbasedonscorelevelfusion AT chenlv advertisingimagesaliencypredictionmethodbasedonscorelevelfusion AT hejiang advertisingimagesaliencypredictionmethodbasedonscorelevelfusion AT deqiangcheng advertisingimagesaliencypredictionmethodbasedonscorelevelfusion |