计算机科学 ›› 2019, Vol. 46 ›› Issue (6): 295-300.doi: 10.11896/j.issn.1002-137X.2019.06.044

• 图形图像与模式识别 • 上一篇    下一篇

基于多尺度下凸包改进的贝叶斯模型显著性检测算法

鲁文超, 段先华, 徐丹, 王万耀   

  1. (江苏科技大学 江苏 镇江212003)
  • 收稿日期:2018-04-12 发布日期:2019-06-24
  • 通讯作者: 段先华(1965-),男,博士,教授,主要研究方向为图像处理、模式识别,E-mail:dxh118@sina.com
  • 作者简介:鲁文超(1991-),男,硕士生,主要研究方向为图像处理,E-mail:luwenchao0309@163.com;徐 丹(1981-),女,博士,副教授,主要研究方向为图像处理;王万耀(1992-),男,硕士生,主要研究方向为图像处理。
  • 基金资助:
    国家自然科学基金项目(6177244),江苏省高校自然科学研究面上项目(16KJB52009),江苏省研究生创新计划项目(KYCX18_2331)资助。

Bayesian Model Saliency Detection Algorithm Based on Multiple Scales and Improved Convex Hull

LU Wen-chao, DUAN Xian-hua, XU Dan, WANG Wan-yao   

  1. (Jiangsu University of Science and Technology,Zhenjiang,Jiangsu 212003,China)
  • Received:2018-04-12 Published:2019-06-24

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。

关键词: 贝叶斯模型, 流形排序算法, 凸包, 显著性检测, 准确率-召回率曲线

Abstract: 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 proposedalgorithm not only achieves good vision effect,but also improves the performance evaluation of precision-recall curves and F-measure value.

Key words: Bayesian model, Convex hull, Manifold Ranking algorithm, precision-recall curves, Saliency detection

中图分类号: 

  • TP391.41
[1]YU G,YUAN J,LIU Z.Propagative Hough Voting for Human Activity Detection and Recognition[J].IEEE Transactions onCircuits & 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 ć I V.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,KRÄHENBÜHL 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.
[1] 刘翔宇, 蹇木伟, 鲁祥伟, 何为凯, 李晓峰, 尹义龙.
基于眼动点视觉先验与边缘优化的显著性检测
Saliency Detection Based on Eye Fixation Prediction and Boundary Optimization
计算机科学, 2021, 48(6A): 107-112. https://doi.org/10.11896/jsjkx.201100116
[2] 王教金, 蹇木伟, 刘翔宇, 林培光, 耿蕾蕾, 崔超然, 尹义龙.
基于3D全时序卷积神经网络的视频显著性检测
Video Saliency Detection Based on 3D Full ConvLSTM Neural Network
计算机科学, 2020, 47(8): 195-201. https://doi.org/10.11896/jsjkx.190600148
[3] 袁野, 和晓歌, 朱定坤, 王富利, 谢浩然, 汪俊, 魏明强, 郭延文.
视觉图像显著性检测综述
Survey of Visual Image Saliency Detection
计算机科学, 2020, 47(7): 84-91. https://doi.org/10.11896/jsjkx.190900006
[4] 吴学林, 朱荣, 郭迎.
基于块稀疏贝叶斯模型的鬼成像重构算法
Ghost Imaging Reconstruction Algorithm Based on Block Sparse Bayesian Model
计算机科学, 2020, 47(11A): 188-191. https://doi.org/10.11896/jsjkx.200200058
[5] 温静, 李雨萌.
基于多尺度反卷积深度学习的显著性检测
Salient Object Detection Based on Multi-scale Deconvolution Deep Learning
计算机科学, 2020, 47(11): 179-185. https://doi.org/10.11896/jsjkx.190900008
[6] 王军, 吴泽民, 杨巍, 胡磊, 张兆丰, 姜青竹.
基于稀疏恢复与优化的显著性目标检测算法
Salient Object Detection Algorithm Based on Sparse Recovery and Optimization
计算机科学, 2018, 45(8): 258-263. https://doi.org/10.11896/j.issn.1002-137X.2018.08.046
[7] 杨陟卓.
基于上下文翻译的有监督词义消歧研究
Supervised WSD Method Based on Context Translation
计算机科学, 2017, 44(4): 252-255. https://doi.org/10.11896/j.issn.1002-137X.2017.04.053
[8] 王燕,李鑫.
基于LDP特征和贝叶斯模型的人脸识别
Face Recognition Based on LDP Feature and Bayesian Model
计算机科学, 2017, 44(12): 283-286. https://doi.org/10.11896/j.issn.1002-137X.2017.12.051
[9] 张兆丰,吴泽民,姜青竹,杜麟,胡磊.
基于超像素匹配的图像协同显著性检测
Co-saliency Detection via Superpixel Matching
计算机科学, 2017, 44(11): 314-319. https://doi.org/10.11896/j.issn.1002-137X.2017.11.048
[10] 许肖,顾磊.
结合显著性检测和中心分割算法的文本检测方法
Saliency Text Detection Combining Graph-based Manifold Ranking with C entral Segmentation
计算机科学, 2016, 43(4): 313-317. https://doi.org/10.11896/j.issn.1002-137X.2016.04.064
[11] 周培云,李静,沈宁敏,庄毅.
BSFCoS:基于分块与稀疏主特征提取的快速协同显著性检测
BSFCoS:Fast Co-saliency Detection Based on Block and Sparse Principal Feature Extraction
计算机科学, 2015, 42(8): 305-309.
[12] 周静波,任永峰,严云洋.
基于视觉显著性的非监督图像分割
Unsupervised Image Segmentation Based on Saliency Detection
计算机科学, 2015, 42(8): 52-55.
[13] 樊强,齐春.
基于全局和局部短期稀疏表示的显著性检测
Saliency Detection Based on Global and Local Short-term Sparse Representation
计算机科学, 2014, 41(10): 80-83. https://doi.org/10.11896/j.issn.1002-137X.2014.10.018
[14] 蒋华荣,郁雪.
应用遗传算法优化子空间的SVM分类算法
GA-based Subspace Classification Algorithm for Support Vector Machines
计算机科学, 2013, 40(11): 255-260.
[15] 周昆,符意德.
WMSN中的一种实时地理路由算法
Real-time Geographic Routing Algorithm in Wireless Multimedia Sensor Networks
计算机科学, 2013, 40(10): 68-71.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!