基于多尺度下凸包改进的贝叶斯模型显著性检测算法
|
摘要
针对传统基于贝叶斯的显著性检测算法存在的准确率不理想的问题,提出了一种基于多尺度凸包改进贝叶斯模型的显著性检测算法。该算法首先通过流行排序算法(MR)在CIELab颜色空间上对图像的前景进行提取,并将其作为先验图;其次通过高斯金字塔算法对图像进行降采样,得到3种不同尺度的图像(包括原图),结合经典的Harris算子检测不同尺度图像的角点,求三者的交集,得到更合理的凸包;然后利用颜色直方图结合凸包来计算观察似然概率;最后根据已有的先验图和似然概率,利用贝叶斯模型计算显著图,并进行优化处理得到最终的显著图。为了验证该算法的正确性和有效性,在公开数据集MSRA1000和ECSSD上进行仿真实验。结果表明,该算法不仅能够得到较好的视觉效果,而且召回率、准确率和F-measure等评价指标比传统算法有明显提升。
Traditional Bayesian model saliency detection algorithm may have a poor performance in terms of precision.Therefore,this paper proposed a novel algorithm based on the multi-scaled convex hull.Firstly,the manifold ranking(MR) algorithm is used to extract the foreground of the images in the CIELab color space,which is considered as the prior probability map.Secondly,the image is down sampled by Gaussian Pyramid algorithm,and three scaled images are obtained.The improved convex hull is derived by using the intersection about convex hull of Harris corners of the three scaled images.Thirdly,the color histogram and convex hull are combined to calculate the observation likelihood probability.Finally,according to the existing prior probability map and observation likelihood probability,the Bayesian model is used to compute the saliency map.Moreover,the optimization is carried out for better performance.The experiment results on public datasets MSRA1000 and ECSSD show that the proposed algorithm not only achieves good vision effect,but also improves the performance evaluation of precision-recall curves and F-measure value.
Traditional Bayesian model saliency detection algorithm may have a poor performance in terms of precision.Therefore,this paper proposed a novel algorithm based on the multi-scaled convex hull.Firstly,the manifold ranking(MR) algorithm is used to extract the foreground of the images in the CIELab color space,which is considered as the prior probability map.Secondly,the image is down sampled by Gaussian Pyramid algorithm,and three scaled images are obtained.The improved convex hull is derived by using the intersection about convex hull of Harris corners of the three scaled images.Thirdly,the color histogram and convex hull are combined to calculate the observation likelihood probability.Finally,according to the existing prior probability map and observation likelihood probability,the Bayesian model is used to compute the saliency map.Moreover,the optimization is carried out for better performance.The experiment results on public datasets MSRA1000 and ECSSD show that the proposed algorithm not only achieves good vision effect,but also improves the performance evaluation of precision-recall curves and F-measure value.
引文
[1] YU G,YUAN J,LIU Z.Propagative Hough Voting for Human Activity Detection and Recognition[J].IEEE Transactions on Circuits & Systems for Video Technology,2015,25(1):87-98.
[2] HORBERT E,GARCíA G M,FRINTROP S,et al.Sequence- level object candidates based on saliency for generic object re-cognition on mobile systems[C]//IEEE International Confe-rence on Robotics and Automation.IEEE,2015:127-134.
[3] HADIZADEH H,BAJI■.Saliency-aware video compression[J].IEEE Transactions on Image Processing A Publication of the IEEE Signal Processing Society,2014,23(1):19-33.
[4] JIAN M W,DONG J Y,MA J.Image retrieval using wavelet-based salient regions[J].Journal of Photographic Science,2014,59(4):219-231.
[5] LEI B,TAN E L,CHEN S,et al.Saliency-driven image classification method based on histogram mining and image score[J].Pattern Recognition,2015,48(8):2567-2580.
[6] ITTI L,KOCH C,NIEBUR E.A model of saliency-based visual attention for rapid scene analysis[J].IEEE Transactions on Pattern Analysis & Machine Intelligence,1998,20(11):1254-1259.
[7] ACHANTA R,HEMAMI S,ESTRADA F,et al.Frequency- tuned salient region detection[C]//IEEE Comference on Computer Vision and Pattern Recognition.2009:1597-1604.
[8] LU H,LI X,ZHANG L,et al.Dense and Sparse Reconstruction Error Based Saliency Descriptor[J].IEEE Transactions on Image Processing,2016,25(4):1592-1603.
[9] CHENG M M,MITRA N J,HUANG X,et al.Global Contrast Based Salient Region Detection[J].IEEE Transactions on Pattern Analysis &Machine Intelligence,2015,37(3):569.
[10] CHEN D,JIA T,WU C.Visual saliency detection:From space to frequency[J].Signal Processing Image Communication,2016,44:57-68.
[11] YANG C,ZHANG L,LU H,et al.Saliency Detection via Graph-Based Manifold Ranking[C]//Computer Vision and Pattern Recognition.IEEE,2013:3166-3173.
[12] WEI Y,WEN F,ZHU W,et al.Geodesic Saliency Using Background Priors[M]//Computer Vision-ECCV 2012.Springer Berlin Heidelberg,2012:29-42.
[13] JIANG Y W,TAN L Y,WANG S J.Saliency detected model based on selective edges prior[J].Journal of Electronics & Information Technology,2015,37(1):130-136.
[14] TONG N,LU H,RUAN X,et al.Salient object detection via bootstrap learning[C]//Computer Vision and Pattern Recognition.2015:1884-1892.
[15] XIE Y,LU H.Visual saliency detection based on Bayesian mo- del[C]//IEEE International Conference on Image Processing.IEEE,2011:645-648.
[16] XIE Y,LU H,YANG M H.Bayesian saliency via low and mid levelcues[J].IEEE Transactions on Image Processing,2013,22(5):1689-1698.
[17] ZHANG L,TONG M H,MARKS T K,et al.SUN:A Bayesian framework for saliency using natural statistics[J].Journal of Vision,2008,8(7):32-32.
[18] QIN Y,LU H,XU Y,et al.Saliency detection via Cellular Automata[C]//Computer Vision and Pattern Recognition.2015:110-119.
[19] MAHADEVAN V,VASCONCELOS N.Spatiotemporal salie- ncy in dynamic scenes[J].IEEE Transactions on pattern Analysis and Machine Intelligence,2010,32(1):171-177.
[20] LIN X,WANG Y L,ZHU H L,et al.Saliency Detection Based on the Bayesian Model of Improved Convex Hull[J].Journal of Computer-Aided Design & Computer Graphics,2017,29(2):221-228.(in Chinese)林晓,王燕玲,朱恒亮,等.改进凸包的贝叶斯模型显著性检测算法[J].计算机辅助设计与图形学学报,2017,29(2):221-228.
[21] RAHTU E,KANNALA J,SALO M,et al.Segmenting Salient Objects from Images and Videos[M]//Computer Vision-ECCV 2010.Springer Berlin Heidelberg,2010:366-379.
[22] WANG W Y,DUAN X H,XU D,et al.Grabcut Image Segmentation Method Based on Saliency[J].Computer Engineering,2018,44(7):230-236,243.(in Chinese)王万耀,段先华,徐丹,等.基于显著性的Grabcut图像分割方法[J].计算机工程,2018,44(7):230-236,243.
[23] PERAZZI F,KR?HENBüHL P,PRITCH Y,et al.Saliency filters:Contrast based filtering for salient region detection[C]//Computer Vision and Pattern Recognition.IEEE,2012:733-740.
[24] ACHANTA R,ESTRADA F,WILS P,et al.Salient Region Detection and Segmentation[M]//Computer Vision Systems.Springer Berlin Heidelberg,2008:66-75.
[25] HOU X,ZHANG L.Saliency Detection:A Spectral Residual Approach[C]//IEEE Comference on Computer Vision and Pattern Recognition.2007:1-8.
[26] KIM J,HAN D,TAI Y W,et al.Salient Region Detection via High-Dimensional Color Transform[C]//Computer Vision and Pattern Recognition.IEEE,2014:883-890.
[27] RAN M,TAL A,ZELNIK-MANOR L.What Makes a Patch Distinct?[C]//IEEE Conference on Computer Vision and Pattern Recognition.IEEE Computer Society,2013:1139-1146.
[28] WEI Y,WEN F,ZHU W,et al.Geodesic Saliency Using Background Priors[M]//Computer Vision-ECCV 2012.Springer Berlin Heidelberg,2012:29-42.
[2] HORBERT E,GARCíA G M,FRINTROP S,et al.Sequence- level object candidates based on saliency for generic object re-cognition on mobile systems[C]//IEEE International Confe-rence on Robotics and Automation.IEEE,2015:127-134.
[3] HADIZADEH H,BAJI■.Saliency-aware video compression[J].IEEE Transactions on Image Processing A Publication of the IEEE Signal Processing Society,2014,23(1):19-33.
[4] JIAN M W,DONG J Y,MA J.Image retrieval using wavelet-based salient regions[J].Journal of Photographic Science,2014,59(4):219-231.
[5] LEI B,TAN E L,CHEN S,et al.Saliency-driven image classification method based on histogram mining and image score[J].Pattern Recognition,2015,48(8):2567-2580.
[6] ITTI L,KOCH C,NIEBUR E.A model of saliency-based visual attention for rapid scene analysis[J].IEEE Transactions on Pattern Analysis & Machine Intelligence,1998,20(11):1254-1259.
[7] ACHANTA R,HEMAMI S,ESTRADA F,et al.Frequency- tuned salient region detection[C]//IEEE Comference on Computer Vision and Pattern Recognition.2009:1597-1604.
[8] LU H,LI X,ZHANG L,et al.Dense and Sparse Reconstruction Error Based Saliency Descriptor[J].IEEE Transactions on Image Processing,2016,25(4):1592-1603.
[9] CHENG M M,MITRA N J,HUANG X,et al.Global Contrast Based Salient Region Detection[J].IEEE Transactions on Pattern Analysis &Machine Intelligence,2015,37(3):569.
[10] CHEN D,JIA T,WU C.Visual saliency detection:From space to frequency[J].Signal Processing Image Communication,2016,44:57-68.
[11] YANG C,ZHANG L,LU H,et al.Saliency Detection via Graph-Based Manifold Ranking[C]//Computer Vision and Pattern Recognition.IEEE,2013:3166-3173.
[12] WEI Y,WEN F,ZHU W,et al.Geodesic Saliency Using Background Priors[M]//Computer Vision-ECCV 2012.Springer Berlin Heidelberg,2012:29-42.
[13] JIANG Y W,TAN L Y,WANG S J.Saliency detected model based on selective edges prior[J].Journal of Electronics & Information Technology,2015,37(1):130-136.
[14] TONG N,LU H,RUAN X,et al.Salient object detection via bootstrap learning[C]//Computer Vision and Pattern Recognition.2015:1884-1892.
[15] XIE Y,LU H.Visual saliency detection based on Bayesian mo- del[C]//IEEE International Conference on Image Processing.IEEE,2011:645-648.
[16] XIE Y,LU H,YANG M H.Bayesian saliency via low and mid levelcues[J].IEEE Transactions on Image Processing,2013,22(5):1689-1698.
[17] ZHANG L,TONG M H,MARKS T K,et al.SUN:A Bayesian framework for saliency using natural statistics[J].Journal of Vision,2008,8(7):32-32.
[18] QIN Y,LU H,XU Y,et al.Saliency detection via Cellular Automata[C]//Computer Vision and Pattern Recognition.2015:110-119.
[19] MAHADEVAN V,VASCONCELOS N.Spatiotemporal salie- ncy in dynamic scenes[J].IEEE Transactions on pattern Analysis and Machine Intelligence,2010,32(1):171-177.
[20] LIN X,WANG Y L,ZHU H L,et al.Saliency Detection Based on the Bayesian Model of Improved Convex Hull[J].Journal of Computer-Aided Design & Computer Graphics,2017,29(2):221-228.(in Chinese)林晓,王燕玲,朱恒亮,等.改进凸包的贝叶斯模型显著性检测算法[J].计算机辅助设计与图形学学报,2017,29(2):221-228.
[21] RAHTU E,KANNALA J,SALO M,et al.Segmenting Salient Objects from Images and Videos[M]//Computer Vision-ECCV 2010.Springer Berlin Heidelberg,2010:366-379.
[22] WANG W Y,DUAN X H,XU D,et al.Grabcut Image Segmentation Method Based on Saliency[J].Computer Engineering,2018,44(7):230-236,243.(in Chinese)王万耀,段先华,徐丹,等.基于显著性的Grabcut图像分割方法[J].计算机工程,2018,44(7):230-236,243.
[23] PERAZZI F,KR?HENBüHL P,PRITCH Y,et al.Saliency filters:Contrast based filtering for salient region detection[C]//Computer Vision and Pattern Recognition.IEEE,2012:733-740.
[24] ACHANTA R,ESTRADA F,WILS P,et al.Salient Region Detection and Segmentation[M]//Computer Vision Systems.Springer Berlin Heidelberg,2008:66-75.
[25] HOU X,ZHANG L.Saliency Detection:A Spectral Residual Approach[C]//IEEE Comference on Computer Vision and Pattern Recognition.2007:1-8.
[26] KIM J,HAN D,TAI Y W,et al.Salient Region Detection via High-Dimensional Color Transform[C]//Computer Vision and Pattern Recognition.IEEE,2014:883-890.
[27] RAN M,TAL A,ZELNIK-MANOR L.What Makes a Patch Distinct?[C]//IEEE Conference on Computer Vision and Pattern Recognition.IEEE Computer Society,2013:1139-1146.
[28] WEI Y,WEN F,ZHU W,et al.Geodesic Saliency Using Background Priors[M]//Computer Vision-ECCV 2012.Springer Berlin Heidelberg,2012:29-42.