基于目標緊密性與區(qū)域同質性策略的圖像顯著性檢測
doi: 10.11999/JEIT190101
-
河北工業(yè)大學電子信息工程學院 天津 300401
基金項目: 教育部春暉計劃項目(Z2017015)
Image Saliency Detection Based on Object Compactness and Regional Homogeneity Strategy
-
School of Electronics and Information Engineering, Hebei University of Technology, Tianjin 300401, China
Funds: Chunhui project of the Ministry of Education (Z2017015)
-
摘要: 針對基于圖模型的顯著性檢測算法中節(jié)點間特征差異描述不準確的問題，該文提出一種目標緊密性與區(qū)域同質性策略相結合的圖像顯著性檢測算法。區(qū)別于常用的圖模型，該算法建立更貼近人眼視覺系統(tǒng)的稀疏圖結構與新穎的區(qū)域同質性圖結構，以便描述圖像前景內(nèi)部的關聯(lián)性與前景背景間的差異性，從而摒棄眾多節(jié)點的冗余連接，強化節(jié)點局部空間關系；并且結合聚類簇緊密性采取流形排序的方式形成顯著圖，利用背景區(qū)域簇的相似性，引入背景置信度進行顯著性優(yōu)化，最終得到精細的檢測結果。在4個基準數(shù)據(jù)集上與4種基于圖模型的流行算法對比，該算法能清晰地突出顯著區(qū)域，且在多種綜合指標評估中，具備更優(yōu)越的性能。Abstract: Considering the inaccurate description of feature differences between nodes in the graph-based saliency detection algorithm, an image saliency detection algorithm combining object compactness and regional homogeneity strategy is proposed. Different from the commonly used graph-based model, a sparse graph-based structure closer to the human visual system and a novel regional homogeneity graph-based structure are established. They are used to describe the correlation within the foreground and the difference between foreground and background. Therefore, many redundant connections of nodes are eliminated and the local spatial relationship of nodes is strengthened. Then the clusters are combined to form a saliency map by means of manifold ranking. Finally, the background confidence is introduced for saliency optimization by the similarity of the background region clusters and the final detection result is obtained. Compared with 4 popular graph-based algorithms on the four benchmark datasets, the proposed algorithm can highlight the salient regions clearly and has better performance in the evaluation of multiple comprehensive indicators.
-
Key words:
- Graph-based model /
- Object compactness /
- Regional homogeneity /
- Manifold ranking /
- Saliency detection
-
CONG Runmin, LEI Jianjun, FU Huazhu, et al. Co-saliency detection for RGBD images based on multi-constraint feature matching and cross label propagation[J]. IEEE Transactions on Image Processing, 2018, 27(2): 568–579. doi: 10.1109/TIP.2017.2763819 WANG Songtao, ZHEN Zhou, WEI Jin, et al. Visual saliency detection for RGB-D images under a Bayesian framework[J]. IPSJ Transactions on Computer Vision and Applications, 2018, 10: 1. doi: 10.1186/S41074-017-0037-0 LIU Nian and HAN Junwei. A deep spatial contextual long-term recurrent convolutional network for saliency detection[J]. IEEE Transactions on Image Processing, 2018, 27(7): 3264–3274. doi: 10.1109/TIP.2018.2817047 WU Xiyin, JIN Zhong, ZHOU Jingbo, et al. Saliency propagation with perceptual cues and background-excluded seeds[J]. Journal of Visual Communication and Image Representation, 2018, 54: 51–62. doi: 10.1016/J.JVCIR.2018.04.006 LI Guanbin and YU Yizhou. Contrast-oriented deep neural networks for salient object detection[J]. IEEE Transactions on Neural Networks and Learning Systems, 2018, 29(12): 6038–6051. doi: 10.1109/TNNLS.2018.2817540 TONG Na, LU Huchuan, ZHANG Lihe, et al. Saliency detection with multi-scale superpixels[J]. IEEE Signal Processing Letters, 2014, 21(9): 1035–1039. doi: 10.1109/LSP.2014.2323407 余春艷, 徐小丹, 鐘詩俊. 面向顯著性目標檢測的SSD改進模型[J]. 電子與信息學報, 2018, 40(11): 2554–2561.YU Chunyan, XU Xiaodan, and ZHONG Shijun. An improved SSD model for saliency object detection[J]. Journal of Electronics &Information Technology, 2018, 40(11): 2554–2561. YANG Chuan, ZHANG Lihe, LU Huchuan, et al. Saliency detection via graph-based manifold ranking[C]. 2013 IEEE Conference on Computer Vision and Pattern Recognition, Portland, USA, 2013: 3166–3173. doi: 10.1109/CVPR.2013.407. WEI Yichen, WEN Fang, ZHU Wangjiang, et al. Geodesic saliency using background priors[C]. The 12th European Conference on Computer Vision, Florence, Italy, 2012: 29–42. doi: 10.1007/978-3-642-33712-3_3. ZHANG Lihe, YANG Chuan, LU Huchuan, et al. Ranking saliency[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(9): 1892–1904. doi: 10.1109/TPAMI.2016.2609426 LI Hongyang, LU Huchuan, LIN Zhe, et al. Inner and inter label propagation: salient object detection in the wild[J]. IEEE Transactions on Image Processing, 2015, 24(10): 3176–3186. doi: 10.1109/TIP.2015.2440174 YUAN Yuchen, LI Changyang, KIM J, et al. Reversion correction and regularized random walk ranking for saliency detection[J]. IEEE Transactions on Image Processing, 2018, 27(3): 1311–1322. doi: 10.1109/TIP.2017.2762422 ZHOU Li, YANG Zhaohui, ZHOU Zongtan, et al. Salient region detection using diffusion process on a two-layer sparse graph[J]. IEEE Transactions on Image Processing, 2017, 26(12): 5882–5894. doi: 10.1109/TIP.2017.2738839 ZHANG Zizhao, XING Fuyong, WANG Hanzi, et al. Revisiting graph construction for fast image segmentation[J]. Pattern Recognition, 2018, 78: 344–357. doi: 10.1016/J.PATCOG.2018.01.037 ZHANG Jinxia, FANG Shixiong, EHINGER K A, et al. Hypergraph optimization for salient region detection based on foreground and background queries[J]. IEEE Access, 2018, 6: 26729–26741. doi: 10.1109/ACCESS.2018.2834545 -
下載:
圖(10) / 表(1)
計量
- 文章訪問數(shù): 2426
- HTML全文瀏覽量: 1462
- PDF下載量: 78
- 被引次數(shù): 0
下載:
