Image Classification Method Combining Local Position Feature with Global Contour Feature
LI Ya-qian1, WU Chao2, LI Hai-bin1, LIU Bin2
1. Key Lab of Industrial Computer Control Engineering of Hebei Province, Yanshan University, Qinhuangdao, Hebei 066004, China;
2. Institute of Information Science and Engineering, Yanshan University, Qinhuangdao, Hebei 066004, China
Abstract：Based on Spatial Pyramid Matching method,aiming at the insufficient utilization of spatial information,firstly,local position feature is extracted by computing relative position distribution of each dictionary vector in image.Then,global contour feature is generated through Nonsubsampled Contourlet Transform and Linear Discriminant Analysis.Finally,Spatial information is enhanced by combining local position feature with global contour feature,which consequently improves the accuracy of scene and object classification.Extensive experiments are performed on Caltech 101,MSRC and 15 Scene datasets respectively.The experimental results show that the proposed method further utilizes the spatial information,and thus improves the accuracy of image classification.
李雅倩, 吴超, 李海滨, 刘彬. 局部位置特征与全局轮廓特征相结合的图像分类方法[J]. 电子学报, 2018, 46(7): 1726-1731.
LI Ya-qian, WU Chao, LI Hai-bin, LIU Bin. Image Classification Method Combining Local Position Feature with Global Contour Feature. Acta Electronica Sinica, 2018, 46(7): 1726-1731.
[1] Csurka G,Dance C R,Fan L,et al.Visual categoryzation with bags of keypoints[J].Workshop on Statistical Learning in Computer Vision Eccv,2004,44(247):1-22.
[2] Lazebnik S,Schmid C,Ponce J.Beyond bags of features:spatial pyramid matching for recognizing natural scene categories[A].IEEE Computer Society Conference on Computer Vision and Pattern Recognition[C].New York,USA:IEEE,2006.2169-2178.
[3] Jégou H,Douze M,Schmid C,et al.Aggregating local descriptors into a compact image representation[A].IEEE Conference on Computer Vision and Pattern Recognition[C].San Francisco,USA:IEEE,2010.3304-3311.
[4] Avila S,Thome N,et al.Pooling in image representation:the visual codeword point of view[J].Computer Vision and Image Understanding,2013,117(5):453-465.
[5] Khan R,Barat C,Muselet D,et al.Spatial histograms of soft pairwise similar patches to improve the bag-of-visual-words model[J].Computer Vision & Image Understanding,2014,132:102-112.
[6] Li W S,Dong P,Xiao B,et al.Object recognition based on the region of interest and optimal bag of words model[J].Neurocomputing,2015,172(8):271-280.
[7] Koniusz P,Yan F,Gosselin P,et al.Higher-order occurrence pooling for bags-of-words:visual concept detection[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2017,39(2):313-326.
[8] 艾列富.基于内容的大规模图像索引与检索方法研究[D].湖北武汉:华中科技大学,2014. AI Lie-fu.Research on Content-based Indexing and Retrieval Methods for Large Scale Images[D].Hubei,Wuhan:Huazhong University of Science & Technology,2014.(in Chinese)
[9] Liu L Q,et al.In defense of soft-assignment coding[A].Proceedings of the International Conference on Computer Vision[C].Barcelona,Spain,2011.2486-2493.
[10] Grauman K,Darrell T.Pyramid match kernels:discriminative classification with sets of image features[A].Tenth IEEE International Conference on Computer Vision[C].Beijing,China:IEEE,2005:1458-1465.
[11] Cunha A L D,et al.The nonsubsampled contourlet transform:theory,design,and applications[J].IEEE Transactions on Image Processing,2006,15(10):3089-3101.
[12] 倪伟.基于多尺度几何分析的图像处理技术研究[D].陕西西安:西安电子科技大学,2008. NI Wei.Research on Image Processing Algorithms vi a Multiscale Geometric Analysiss[D].Xi'an,Shaanxi:Xidian University,2008.(in Chinese)
[13] 何国辉,甘俊英.PCA-LDA算法在性别鉴别中的应用[J].计算机工程,2006,32(19):208-210. HE Guo-hui,GAN Jun-ying.Application of PCA andLDA on gender classification[J].Computer Engineering,2006,32(19):208-210.(in Chinese)
[14] 汤鹏.基于LDA的特征提取及其在人脸识别中的应用[D].河北保定:河北大学,2015. TANG Peng.LDA Based Feature Extraction and Its Application To Face Recognition[D].Baoding,Hebei:Hebei University,2015.(in Chinese)
[15] Chang C C,Lin C J.LIBSVM:A library for support vector machines[J].Acm Transactions on Intelligent S ystems & Technology,2011,2(3):389-396.
[16] Microsoft Research Cambridge Object Recognition Image Database[DB].https://www.microsoft.com/en-us/do-wnload/details.aspx?id=52644,218.
[17] Wang J Y,Yang J C,Yu K,et al.Locality-constrained linear coding for image classification[A].IEEE Conference on Computer Vision and Pattern Recognition[C].San Francisco,USA,2010.3360-3367.
[18] 肖文华,包卫东,等.一种用于图像分类的语义增强线性编码方法[J].电子与信息学报,2015,37(4):791-797. XIAO Wen-hua,BAO Wei-dong,et al.A semantic enhanced linear coding for image classification[J].Jounal of Electronics & Information Technology,2015,37(4):791-797.(in Chinese)
2018, Vol. 46 
