摘要: 图像检索过程中往往会提取大量的局部特征,这将加大图像检索的计算量和复杂度,影响其应用。针对这一问题,提出了一种应用综合视觉注意模型的显著性分析提取局部特征的方法:在图像尺度空间中提取关键点,利用模糊增长技术查找原始图像的显著性区域,计算其综合视觉显著性权值并分类,提取SIFT描述因子,保留最突出的局部特征以提高检索性能。相比于传统的局部特征提取算法,本方法在图像检索精度和检索速度方面都具有明显优势。
[1] Ma Y F,Zhang H J.Contrast-based Image Attention Analysis by Using Fuzzy Growing[C]∥ACM MM.2003:374-381 [2] Itti L,et al.Visual Attention and Target Detection in Cluttered Natural Scenes[J].Optical Engineering,2001,40(9):1784-1793 [3] Ke Y,et al.PCA-SIFT:A More Distinctive Representation for Local Image Descriptors[C]∥CVPR.2004:506-513 [4] Lowe D.Distinctive Image Features from Scale-Invariant Key-points[J].Int’l J.Computer Vision,2004,2(60):91-110 [5] Tuytelaars T.Matching Widely Separated Views Based on Af-fine Invariant Regions[J].Int’l J.Computer Vision,2004,1(59):61-85 [6] Mikolajczyk K,Schmid C.Performance Evaluation of Local Descriptors[J].IEEE Trans.of PAMI,2005,27(10):1615-1630 [7] Hakim A.CSIFT:A SIFT Descriptor with Color Invariant Cha-racteristics[C]∥CVPR.2006:1978-1983 [8] Hou X.Saliency detection:A spectral residual approach[C]∥CVPR.2007:1-8 [9] Cheng M M,et al.Global Contrast based Salient Region Detection [C]∥CVPR.2011:456-463 [10] 陈硕,吴成东,陈东岳.基于视觉显著性特征的快速场景配准方法[J].中国图象图形学报,2011(7):1241-1247 [11] 程仁贵,刘书炘.基于边缘检测的影像多线自动测量算法[J].重庆理工大学学报:自然科学版,2013,27(2):89-92 |
No related articles found! |
|