计算机科学 ›› 2016, Vol. 43 ›› Issue (5): 308-312.doi: 10.11896/j.issn.1002-137X.2016.05.059
陈光喜,龚震霆,温佩芝,任夏荔
CHEN Guang-xi, GONG Zhen-ting, WEN Pei-zhi and REN Xia-li
摘要： 传统的图像识别方法如ScSPM、LLC都是在SIFT的基础上提取特征,忽略了人工特征的局限性,且单张图像识别耗时略长。考虑到这些不足,提出了一种基于局部抑制线性编码的图像快速识别方法。该方法首先直接利用局部抑制线性编码提取图像局部特征描述子；然后用线性空间金字塔匹配(LSPM)对特征描述子进行计算；最后将计算结果输入到线性支持向量机(LSVM)中进行训练和测试。在3个常用的图像数据集上的实验结果表明,该方法在类别不多的情况下具有很好的识别准确率,同时大大减少了单张图像识别耗时,从而验证了该方法在图像识别上的有效性。
| [1] Xie Zhao,Gao Jun.A novel method for scene categorization with constraint mechanism based on gaussian statistical model[J].Acta Electronica Sinica,2009,37(4):733-738(in Chinese) 谢昭,高隽.基于高斯统计模型的场景分类及约束机制新方法[J].电子学报,2009,37(4):733-738 [2] Sonka M,Hlavac V,Boyle R.Image processing,analysis,andmachine vision[M].Toronto:Thomson,2008 [3] Llwe D G.Distinctive image features from scale-invariant keypoints[J].International Journal of Computer Vision,2004,60(2):91-110 [4] Cox D,Pinto N.Beyond simple features:A large-scale featuresearch approach to unconstrained face recognition[C]∥Procee-dings of the 2011 IEEE International Conference on Automatic Face and Gesture Recognition and Workshops.Piscataway:IEEE,2011:8-15 [5] Yang C,Zhu Y,Chen G.New classifier ensemble method based on rough set attribute reduction[J].Application Research of Computers,2012,29(5):1648-1650 [6] Huang R,Lang F,Shi Z.Log-Gabor and 2D semi-supervised dis-criminant analysis based face image retrieval[J].Application Research of Computers,2012,29(1):393-396 [7] Olshausen B A.Emergence of simple-cell receptive field properties by learning a sparse code for natural images[J].Nature,1996,381(6583):607-609 [8] Zhu Xiao-feng,Huang Zi,Shen Heng-tao,et al.Linear cross-modal hashing for efficient multi-mediasearch[C]∥Proc of the 21st ACM International Conference on Multimedia.2013:143-152 [9] Lee H,Battle A,Raina R,et al.Efficiet sparse coding algorithms[M]∥Advances in Neural Information Processing Systems.Cambridge:MIT Press,2006:801-808 [10] Lazebnik S,Schmid C,Ponce J.Beyond bags of features:Spatial pyramid matching for recognizing natural scene categories[C]∥Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.Washington,DC:IEEE Computer Society,2006:2169-2178 [11] Li Fei-fei,Perona P.A bayesian hierarchical model for learning natural scene categories[C]∥IEEE Computer Society Confe-rence on Computer Vision and Pattern Recognition.San Diego,CA:IEEE Press,2005:524-531 [12] Yang J,Yu K,Gong Y,et al.Linear spatial pyramid matchingusing sparse coding for image classification[C]∥Proceedings of the 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.Washington,DC:IEEE Computer Society,2009:1794-1801 [13] Wang J,Yang J,Yu K,et al.Locality-constrained linear coding for image classification[C]∥Proceedings of the 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.Washington,DC:IEEE Computer Society,2010:3360-3367 [14] Bengio Y.Learning deep architectures for AI[M].Hanover:Now Publishers Inc,2009 [15] Yu K,Zhang T,Gong Y.Nonlinear learning using Local Coordinate Coding[C]∥Proceedings of NIPS.2009:2223-2231 [16] Zhang H,Berg A,Maire M,et al.Svm-knn:Discriminative nearest heighbor classification for visual category recognition[C]∥IEEE Computer Society Conference on Computer Vision and Pattern Recognition.Piscataway,NJ:IEEE Press,2006:2126-2136 [17] Li Fei-fei,Fergus R,Perona P.Learning generative visual mo-dels from few training examples:an incremental bayesian approach tested on 101 object categories [J].Computer Vision and Image Under Standing,2010,6(1):59-70 [18] Holub G G,Perona P A D.Caltech-256 object category dataset:Technical Report 7694[R].California Institute of Technology,2007 [19] Oliva A,Torraba A.Modeling the shape of the scene:A holistic representation of the spatial envelop[C]∥IJCV.2001 [20] Wagner A,Wright J,Ganesh A,et al.Toward a practical facerecognition system:Robust alignment and illumination by sparse representation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2012,34(2):372-386 [21] Grosser,Rainar,Kwongh,et al.Shift-invariant sparse coding for audio classification[EB/OL].[2014-12-01].http://axon.cs.byu.edu/Dan/778/papers/Sparse%20Coding/ng3.pdf [22] Huang Wen-ming,Cai Wen-zheng,Deng Zhen-rong.Cerebrospi-nal fluid images fast recognition model based on sparse coding[J].Journal of Computer Applications,2014,34(7):2040-2043 |
| No related articles found! |
|
||
首页