- 期刊
- OpenAccess
Salient Region Detection with Hierarchical Image Abstraction
並列摘要
Salient region detection is important for many high-level computer vision tasks. The majority of previous works exploit element contrast to detect image saliency region. In this paper, we propose a novel approach to analyze saliency cues from multiple scales of image structure, using a multi-scale image abstraction. In each image layer global color contrast cue and color spatial distribution cue are integrated to generate a single-layer saliency map, and then the final saliency map can be obtained by across-scale adding several single-layer saliency maps. The proposed saliency estimation method abstracts unnecessary image detail, obtaining high quality saliency detection results. We have evaluated the results of our method on the two publicly available datasets MSRA-1000 and SED. The experimental results on these datasets demonstrate the effectiveness of the approaches against the other approaches to analyze image saliency.
被引用紀錄
延伸閱讀
- Dong, Z. W. (2005). CONTENT-BASED IMAGE RETRIEVAL USING HIERARCHICAL MATCH [master's thesis, Tatung University]. Airiti Library. https://www.airitilibrary.com/Article/Detail?DocID=U0081-0607200917233623
- 林宗瀚、王宗銘（2010）。Data Hiding Using Image Interpolation and Distortion Estimation Schemes。興大工程學刊，21(1)，26-45。https://doi.org/10.6287/JENCHU.2010.2101.03
- 林承憲（2021）。An Efficient Data Augmentation Network for Out-of-Distribution Image Detection〔碩士論文，國立臺灣師範大學〕。華藝線上圖書館。https://doi.org/10.6345/NTNU202100209
- Wu, S. Y. (2018). Real-time Salient Object Detection with Two-Stage Algorithm and Heterogeneous Hardware Architecture [master's thesis, National Taiwan University]. Airiti Library. https://doi.org/10.6342/NTU201802450
- Huang, T. H. (2007). A Benchmark for Region-of-Interest Detection in Images [master's thesis, National Taiwan University]. Airiti Library. https://doi.org/10.6342/NTU.2007.02401