浏览全部资源
扫码关注微信
收稿：2020-06-28，
修回：2020-9-22，
录用：2020-9-29，
纸质出版：2021-12-16
移动端阅览
目的
2
现有显著性检测方法大多只关注显著目标的中心信息，使得算法只能得到中心清晰、边缘模糊的显著目标，丢失了一些重要的边界信息，而使用核范数约束进行低秩矩阵恢复，运算过程冗余。为解决以上问题，本文提出一种无监督迭代重加权最小二乘低秩恢复算法，用于图像视觉显著性检测。
方法
2
将图像分为细中粗3种尺度的分割，从细粒度和粗粒度先验的融合中得到分割先验信息；将融合后的分割先验信息通过迭代重加权最小二乘法求解平滑低秩矩阵恢复，生成粗略显著图；使用中粒度分割先验对粗略显著图进行平滑，生成最终的视觉显著图。
结果
2
实验在MSRA10K（Microsoft Research Asia 10K）、SOD（salient object detection dataset）和ECSSD（extended complex scene saliency dataset）数据集上进行测试，并与现有的11种算法进行对比。结果表明，本文算法可生成边界清晰的显著图。在MSRA10K数据集上，本文算法实现了最高的AUC（area under ROC（receiver operating characteristic）curve）和F-measure值，MAE（mean absolute error）值仅次于SMD（structured matrix decomposition）算法和RBD（robust back ground detection）算法，AUC和F-measure值比次优算法RPCA（robust principal component analysis）分别提高了3.9%和12.3%；在SOD数据集上，综合AUC、F-measure和MAE值来看，本文算法优于除SMD算法以外的其他算法，AUC值仅次于SMD算法、SC（smoothness constraint）算法和GBVS（graph-based visual salieney）算法，F-measure值低于最优算法SMD 2.6%；在ECSSD数据集上，本文算法实现了最高的F-measure值75.5%，AUC值略低于最优算法SC 1%，MAE值略低于最优算法HCNs（hierarchical co-salient object detection via color names）2%。
结论
2
实验结果表明，本文算法能从前景复杂或背景复杂的显著图像中更准确地检测出边界清晰的显著目标。
Objective
2
Various existing saliency detection methods have been widely used in saliency images processing. Current saliency detection algorithm can only get the significant target with clear center and blurred edges
losing some important boundary information. The existing saliency detection algorithm based on low-rank matrix recovery has required the use of kernel norms to constrain the low-rank matrix. An unsupervised low-rank matrix restoration iterative re-weighted least squares method has been proposed based on multi-scale segmentation prior information for image saliency detection.
Method
2
First
the input image has been divided into three levels of granularity: fine-grained
medium-granular and coarse-grained. Fine-grained segmentation can divide an image into multiple superpixels. Medium-grain size segmentation can also segment the image but produce fewer regions. Coarse-grain size segmentation can maximize the separation of significant objects from the background but the image may be under-segmented. The segmentation prior information has been obtained from the fusion of fine-grained and coarse-grained priors. Next
the fused segmentation prior information has been obtained. A coarse significant map has been generated based on iterative re-weighted least squares method. At last
the fused significant map has been post-smoothed via using a medium-grained segmentation prior. The final visual saliency map has been acquired.
Result
2
The experiment has used the three datasets of Microsoft Research Asia 10K (MSRA10K)
salient object detection dataset (SOD) and extended complex scene saliency dataset (ECSSD) for testing with comparison of the existing eleven algorithms. The demonstrated algorithm can generate significant target accuracy and clear boundaries of the significant graph. The MSRA10K dataset has contained images of various salient objects of different sizes but only one salient object in each image. The highest area under receiver operating characteristic (ROC) curve value and F-measure value on the MSRA10K dataset have been achieved among them. The mean absolute error (MAE) value has been second only to the structured matrix decomposition (SMD) algorithm and robust back ground detection (RBD) algorithm. The area under ROC curve (AUC) value and F-measure value have been improved by 3.9% and 12.3% respectively compared with the suboptimal algorithm robust principal component analysis (RPCA). A simplified priori functionality and no supervision
and even has implemented the hierarchical fusion of hierarchical co-salient object detection via color names (HCNs) algorithm and the exploiting color name (HCN) algorithm. It is hard to choose the appropriate ratio to suppress the background without the size of the object like the frequency-based frequency-tuned (FT) algorithm. The RPCA algorithm has not considered the spatial structure of the image. The outline of the salient target that can be detected in the MSRA10K dataset with a salient target single. The SOD dataset has contained images of multiple salient objects (independent or adjacent). In the SOD dataset
the algorithm of this paper is superior to other algorithms except SMD algorithm in terms of AUC value
F-measure value and MAE value. The AUC value is second only to the SMD algorithm
smoothness constraint (SC) algorithm and graph-based visual saliency (GBVS) algorithm. The F-measure value is lower than the best algorithm SMD 2.6%. The algorithm in this paper is superior to other algorithms except SMD algorithm in terms of AUC value
F-measure value and MAE value. The algorithm is effective in the case of multiple salient targets. However
the performance of saliency filters (SF)
segmentation driven low-rank matrix recovery (SLR)
robust back ground detection (RBD) is greatly reduced. Just as the SLR algorithm introduces a segmentation prior first
making it more sensitive to the number of significant targets in the image. As for SF due to its dependence on contrast
its AUC value and F-measure value decrease sharply as the significant target increases. The SF algorithm has divided the salient targets that are not significantly contrasted with the background into the background due to multiple salient targets in the two contrast metrics. The RBD algorithm has relied on the boundary connectivity of the background to segment the image caused poorly performance when detecting multiple salient target images. The ECSSD dataset has contained background complex images as well as significant targets of varying sizes. On the ECSSD dataset
the highest F-measure value of 75.5% has been achieved. The AUC value has been slightly lower than the optimal algorithm SC 1%
while the MAE value is slightly lower than the optimal algorithm HCNs 2%. The highest F-measure values and where the AUC and MAE values have been slightly lower than those of the SC algorithm and the HCNs algorithm. The SC algorithm with deformation smoothness constraint is only slightly inferior to the ECSSD dataset. The SMD algorithm has performed well on the MSRA10K dataset and the SOD dataset and moderated on the ECSSD dataset. The tree structure method of capturing image information is not applicable to images with complex backgrounds. Method such as GBVS
foreground-background segmentation (FBS)
SF
and RBD have relied on methods like visual saliency
foreground enhancement
background enhancement and the use of a tree structure. Cues like suppression
contrast bias and center bias have not maintained good performance.
Conclusion
2
A multi-scale saliency detection algorithm has been demonstrated. First
a coarse saliency map by iterative reweighted least squares method based on the prior of multiscale segmentation has been generated. Second
the coarse saliency map by iterative reweighted least squares has been fused. Finally
the qualified saliency map by smooth fusion of the significant maps with medium granularity has been obtained. The algorithm with the latest methods on three public datasets of MSRA10K
SOD
and ECSSD has been verified. Significant targets have been achieved based on accurate
clear boundary saliency segmentation results. The algorithm has presented more robust.
Achanta R, Hemami S, Estrada F and Susstrunk S. 2009. Frequency-tuned salient region detection//Proceedings of 2009 IEEE Conference on Computer Vision and Pattern Recognition. Miami, USA: IEEE: 1597-1604[ DOI:10.1109/CVPR.2009.5206596 http://dx.doi.org/10.1109/CVPR.2009.5206596 ]
Agustsson E, Tschannen M, Mentzer F, Timofte R and Van Gool L. 2019. Generative adversarial networks for extreme learned image compression//Proceedings of 2019 IEEE/CVF International Conference on Computer Vision. Seoul, Korea (South): IEEE: 221-231[ DOI:10.1109/ICCV.2019.00031 http://dx.doi.org/10.1109/ICCV.2019.00031 ]
Borji A and Itti L. 2012. Exploiting local and global patch rarities for saliency detection//Proceedings of 2012 IEEE Conference on Computer Vision and Pattern Recognition. Providence: USA IEEE: 478-485[ DOI:10.1109/CVPR.2012.6247711 http://dx.doi.org/10.1109/CVPR.2012.6247711 ]
Candès E J, Li X and Ma Y. 2011. Robust principal component analysis? Journal of the ACM, 58(3): 1-37[DOI: 10.1145/1970392.1970395]
Cao C S, Liu X M, Yang Y, Yu Y N, Wang J, Wang Z L, Huang Y Z, Wang L, Huang C, Xu W, Ramanan D and Huang T S. 2015. Look and think twice: capturing top-down visual attention with feedback convolutional neural networks//Proceedings of 2015 IEEE International Conference on Computer Vision. Santiago, Chile: IEEE: 2956-2964[ DOI:10.1109/ICCV.2015.338 http://dx.doi.org/10.1109/ICCV.2015.338 ]
Chen Y W, Song B, Du X J and Guizani M. 2019. Infrared small target detection through multiple feature analysis based on visual saliency. IEEE Access, 7: 38996-39004[DOI: 10.1109/ACCESS.2019.2906076]
Cheng M M, Mitra N J, Huang X L, Torr P H S and Hu S M. 2015. Global contrast based salient region detection. IEEE Transactions on Pattern Analysis and Machine Intelligence, 37(3): 569-582[DOI: 10.1109/TPAMI.2014.2345401]
Cho M, Kwak S, Schmid C and Ponce J. 2015. Unsupervised object discovery and localization in the wild: part-based matching with bottom-up region proposals//Proceedings of 2015 IEEE Conference on Computer Vision and Pattern Recognition. Boston, USA: IEEE: 1201-1210[ DOI:10.1109/CVPR.2015.7298724 http://dx.doi.org/10.1109/CVPR.2015.7298724 ]
Fornasier M, Rauhut H and Ward R. 2011. Low-rank matrix recovery via iteratively reweighted least squares minimization. SIAM Journal on Optimization, 21(4): 1614-1640[DOI: 10.1137/100811404]
Harel J, Koch C and Perona P. 2006. Graph-based visual saliency//Proceedings of the 19th International Conference on Neural Information Processing Systems. Canada: MIT Press: 545-552
Koch C and Ullman S. 1987. Shifts in selective visual attention: towards the underlying neural circuitry//Vaina L M, ed. Matters of Intelligence. Dordrecht: Springer: 115-141[ DOI:10.1007/978-94-009-3833-5_5 http://dx.doi.org/10.1007/978-94-009-3833-5_5 ]
Li C W, Zhang Z L and Yang W P. 2020. Salient object detection method by combining Boolean map and grayscale rarity. Journal of Image and Graphics, 25(2): 267-281
李楚为, 张志龙, 杨卫平. 2020. 结合布尔图和灰度稀缺性的小目标显著性检测. 中国图象图形学报, 25(2): 267-281[DOI: 10.11834/jig.190228]
Lin J X, Zhou T K and Chen Z B. 2019. DeepIR: a deep semantics driven framework for image retargeting//Proceedings of 2019 IEEE International Conference on Multimedia and Expo Workshops. Shanghai, China: IEEE: 54-59[ DOI:10.1109/ICMEW.2019.0-111 http://dx.doi.org/10.1109/ICMEW.2019.0-111 ]
Lou J, Wang H, Chen L T, Xu F L, Xia Q Y, Zhu W and Ren M W. 2020. Exploiting color name space for salient object detection. Multimedia Tools and Applications, 79(15): 10873-10897[DOI: 10.1007/s11042-019-07970-x]
Lou J, Xu F L, Xia Q Y, Yang W K and Ren M W. 2017. Hierarchical co-salient object detection via color names//Proceedings of the 4th IAPR Asian Conference on Pattern Recognition. Nanjing, China: IEEE: 718-724[ DOI:10.1109/ACPR.2017.91 http://dx.doi.org/10.1109/ACPR.2017.91 ]
Papale P, Leo A, Cecchetti L, Handjaras G, Kay K N, Pietrini P and Ricciardi E. 2018. Foreground-background segmentation revealed during natural image viewing. eNeuro, 5(3): ENEURO. 0075-18.2018[DOI: 10.1523/ENEURO.0075-18.2018]
Peng H W, Li B, Ling H B, Hu W M, Xiong W H and Maybank S J. 2017. Salient object detection via structured matrix decomposition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 39(4): 818-832[DOI: 10.1109/TPAMI.2016.2562626]
Perazzi F, Krähenbühl, Pritch Y and Hornung A. 2012. Saliency filters: contrast based filtering for salient region detection//Proceedings of 2012 IEEE Conference on Computer Vision and Pattern Recognition. Providence, USA: IEEE: 733-740[ DOI:10.1109/CVPR.2012.6247743 http://dx.doi.org/10.1109/CVPR.2012.6247743 ]
Shen X H and Wu Y. 2012. A unified approach to salient object detection via low rank matrix recovery//Proceedings of 2012 IEEE Conference on Computer Vision and Pattern Recognition. Providence, USA: IEEE: 853-860[ DOI:10.1109/CVPR.2012.6247758 http://dx.doi.org/10.1109/CVPR.2012.6247758 ]
Sun F D and Li W H. 2019. Saliency guided deep network for weakly-supervised image segmentation. Pattern Recognition Letters, 120: 62-68[DOI: 10.1016/j.patrec.2019.01.009]
Wu X Y, Ma X D, Zhang J X, Wang A D and Jin Z. 2018. Salient object detection via deformed smoothness constraint//Proceedings of the 25th IEEE International Conference on Image Processing. Athens, Greece: IEEE: 2815-2819[ DOI:10.1109/ICIP.2018.8451169 http://dx.doi.org/10.1109/ICIP.2018.8451169 ]
Zhu W J, Liang S, Wei Y C and Sun J. 2014. Saliency optimization from robust background detection//Proceedings of 2014 IEEE Conference on Computer Vision and Pattern Recognition. Columbus, USA: IEEE: 2814-2821[ DOI:10.1109/CVPR.2014.360 http://dx.doi.org/10.1109/CVPR.2014.360 ]
Zou W B, Kpalma K, Liu Z and Ronsin J. 2013. Segmentation driven low-rank matrix recovery for saliency detection//Proceedings of the British Machine Vision Conference. Bristol, UK: BMVA Press: 1-13[ DOI: 10.5244/C.27.78 http://dx.doi.org/10.5244/C.27.78 ]
相关作者
相关机构
京公网安备11010802024621
