Computer Science ›› 2017, Vol. 44 ›› Issue (12): 298-303.doi: 10.11896/j.issn.1002-137X.2017.12.054

Previous Articles     Next Articles

Research on Image Salient Regions Detection Combing Edge Boxes and Low-rank Background

SHEN Rui-jie, ZHANG Jun-chao and HAO Jing-bin   

  • Online:2018-12-01 Published:2018-12-01

Abstract: Aiming at the problem that traditional saliency detection methods suffer from unclear boundary and bad robust detection performance,an novel image salient regions detection method was proposed,combining two detection stages including edge boxes for rough location and low-rank background model for refining,to enhance the performance of salient regions detection.First,it improves the image salient regions detection method based on edge boxes.It uses OTSU method for adaptively computing the optimal threshold value of edge magnitude,to replace fixed threshold method and reduce boundary detection error.Second,on the basis of suspicious salient regions detected by edge boxes based method,it uses robust principal component analysis method to obtain the low-rank component of the image for building a background model,and eliminates the background regions based on background subtraction method to reduce false detection of salient regions.Experimental results on the PASCAL VOC 2007 dataset show that,this method can significantly improve the precision and recall metrics of salient regions detection,and has higher detection efficiency.

Key words: Salient regions detection,Edge boxes,Robust principal component analysis,Low-rank background,OTSU

[1] CHENG M M,MITRA N J,HUANG X,et al.Global Contrast Based Salient Region Detection[J].IEEE Transactions on Pattern Analysis & Machine Intelligence,2015,7(3):569-582.
[2] ZHAO Q,CAO J L,HU Y L.Computational complexity with multi-scale transform and color Gauss[J].Journal of Saliency Detection Instrument,2013,3(2):405-412.(in Cihese) 赵倩,曹家麟,胡越黎.结合高斯多尺度变换和颜色复杂度计算的显著区域检测[J].仪器仪表学报,2012,3(2):405-412.
[3] YANG X Y,LI X W,ZHANG L B.Visual saliency detection of remote sensing images based on multiscale frequency domain analysis[J].Journal of Optics,2014,4(13):111-115.(in Chinese) 杨绪业,李雪薇,张立保.基于多尺度频域分析的遥感图像视觉显著区域检测[J].光学学报,2014,4(13):111-115.
[4] RANTALANKILA P,KANNALA J,RAHTU E.Generating Object Segmentation Proposals Using Global and Local Search[C]∥IEEE Conference on Computer Vision and Pattern Recognition.2014:2417-2424.
[5] ZHANG L N,KONG Y Q,LI S H,et al.Significance detection method based on commuting distance[J].Journal of Computer Aided Design and Computer Graphics,2016,8(3):395-403.(in Chinese) 张丽娜,孔雨秋,李淑华,等.基于通勤距离的显著性检测方法[J].计算机辅助设计与图形学学报,2016,8(3):395-403.
[6] CARREIRA J,SMINCHISESCU C.Cpmc:Automatic objectsegmentation using constrained parametric min-cuts[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2012,4(7):1312-1328.
[7] ENDRES I,HOIEM D.Category-Independent Object Proposals with Diverse Ranking[J].IEEE Transactions on Pattern Analysis & Machine Intelligence,2014,6(2):222-34.
[8] ALEXE B,DESELAERS T,FERRARI V.Measuring the Objectness of Image Windows[J].IEEE Transactions on Pattern Analysis & Machine Intelligence,2012,4(11):2189-2202.
[9] ZITNICK C L,DOLLR P.Edge boxes:Locating object propo-sals from edges[C]∥European Conference on Computer Vision.Springer International Publishing,2014:391-405.
[10] DOLLR P,ZITNICK C L.Structured forests for fast edge detection[C]∥Proceedings of the IEEE International Conference on Computer Vision.2013:1841-1848.
[11] BHARGAVA D N,KUMAWAT A,BHARGAVA D R.Threshold and binarization for document image analysis using otsu’s Algorithm[J].International Journal of Computer Trends & Technology,2014,7(5):272-275.
[12] ERICHSON N B,DONOVAN C.Randomized low-rank Dyna-mic Mode Decomposition for motion detection[J].Computer Vision and Image Understanding,2016,6:40-50.

No related articles found!
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!