期刊文献+

基于构造空间金字塔度量矩阵的图像分类算法

An image classification algorithm based on construction space pyramid metric matrix
下载PDF
导出
摘要 传统的空间金字塔匹配方法时间复杂度较高,其所采用的SIFT底层特征缺少颜色信息,从而导致图像分类性能不佳。该文提出了一种融合颜色和尺度不变特征的CSIFT算子,通过建立CSIFT词典的有向图邻接矩阵,对词典中单词的距离进行度量,构建了n阶距离度量矩阵,对图像进行相似性度量并分类。实验结果表明,该方法在优化图像词典构造方面有明显效果,提高了图像分类精度。 The traditional SPM(Spatial pyramid matching)method suffers from the high computation problem,and meanwhile the SIFT adopted by SPM lost sufficient color information which leads to the poor performance on image classification.In this paper,a novel CSIFT descriptor based on color and SIFT is proposed,which construct directed graph adjacency matrix to measure the distance of visual words,and construct n-order distant matrix to measure the image by similarity and classify the images.The experimental results show that this method has obvious effect in optimizing the construction of image dictionary and improves the accuracy of image classification.
作者 李青彦 彭进业 李展 LI Qingyan;PENG Jinye;LI Zhan(School of Electronics and Information,Northwestern Ploytechnical University,Xi′an 710072,China;School of Information Science and Technology,Northwest University,Xi′an 710127,China)
出处 《西北大学学报(自然科学版)》 CAS CSCD 北大核心 2018年第1期50-56,共7页 Journal of Northwest University(Natural Science Edition)
基金 中国博士后科学基金资助项目(2014M552478)
关键词 图像分类 邻接矩阵 CSIFT 空间金字塔匹配 image classification adjacency matrix CSIFT SPM
  • 相关文献

参考文献6

二级参考文献77

  • 1Sivic J,Zisserman A.Video Google:A text retrievalapproach to object matching in videos[C]//Proc 9thInternational Conference on Computer Vision.2003:1470-1477. 被引量:1
  • 2Lazebnik S,Schmid C,Ponce J.Beyond bags of features:Spatial pyramid matching for recognizing natural scenecategories[C]//Proc 19th International Conference onComputer Vision and Pattern recognition.2006:2169-2178. 被引量:1
  • 3van Gemert J,Veenman C,Smeulders A,et al.Visual wordambiguity[J]IEEE Transactions on Pattern Analysis andMachine Intelligence.2010,32(7):1271-1283. 被引量:1
  • 4Wu J,Rehg J.Beyond the Euclidean distance:Creatingeffective visual codebooks using the histogram intersectionkernel[C]//Proc 12th International Conference onComputer Vision.2009:630-637. 被引量:1
  • 5Wang J,Yang J,Yu K,et al.Locality-constrained linearcoding for image classification[C]//Proc 23rd InternationalConference on Computer Vision and Pattern Recognition.2010:3360-3367. 被引量:1
  • 6Yang J,Yu K,Gong Y,et al.Linear spatial pyramidmatching using sparse coding for image classification[C]//Proc 22nd International Conference on Computer Vision andPattern Recognition.2009:1794-1801. 被引量:1
  • 7Boureau Y,Bach F,LeCun Y,et al.Learning mid-levelfeatures for recognition[C]//Proc 23rd InternationalConference on Computer Vision and Pattern Recognition.2010:2559-2566. 被引量:1
  • 8Goldberg A,Zhu X,Singh A,et al.Multi-manifoldsemi-supervised learning[C]//Proc 12th InternationalConference on Artificial Intelligence and Statistics.2009. 被引量:1
  • 9Lee H,Battle A,Raina R,et al.Efficient sparse codingalgorithms[C]//Advances in Neural Information ProcessingSystems.2007:801-808. 被引量:1
  • 10Li F,Fergus R,Perona P.Learning generative visual modelsfrom few training examples:An incremental Bayesianapproach tested on 101object categories[C]//Workshop of17th International Conference on Computer Vision andPattern Recognition.2004:178. 被引量:1

共引文献53

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部