计算机科学 ›› 2017, Vol. 44 ›› Issue (12): 298-303.doi: 10.11896/j.issn.1002-137X.2017.12.054
申瑞杰,张军朝,郝敬滨
SHEN Rui-jie, ZHANG Jun-chao and HAO Jing-bin
摘要: 针对现有显著性区域边界不明确和检测效果鲁棒性较差等问题,提出了一种新颖的图像显著区域检测方法,该方法结合了边缘盒粗定位和低秩背景模型细筛选来提高显著区域的检测性能。首先,对基于边缘盒的图像显著区域检测方法进行改进,采用OTSU方法自适应计算边缘模值的最佳分割阈值,以替代固定分割阈值,降低边界点检测误差;其次,在基于边缘盒检测到的可疑显著区域上,采用鲁棒主成分分析方法获取图像的低秩分量,构建背景模型,并基于背景差分方法剔除背景区域,减少显著区域的虚检现象。在PASCAL VOC 2007数据集上的实验结果表明,提出的方法明显提高了显著区域检测的精确度和召回率,同时具有较高的检测效率。
[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,DOLLR P.Edge boxes:Locating object propo-sals from edges[C]∥European Conference on Computer Vision.Springer International Publishing,2014:391-405. [10] DOLLR 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! |
|