An Image Classification Method Using Graphically Regularized Coding Algorithm
YANG Sai1, ZHAO Chun-xia2, HU Bin3, CHEN Feng1
1. School of Electrical Engineering, Natong University, Nantong, Jiangsu 226019, China;
2. School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, Jiangsu 210094, China;
3. School of Computer Science and Technology, Nantong University, Nantong, Jiangsu 226019, China
Abstract：In order to solve the problem that current coding schemes lost consistence between similar local features,this paper proposes a new graphically regularized coding algorithm.This algorithm used any current coding scheme to get the initial coding coefficients,and utilized a regularized term to preserve locality constrains both in the feature space and the spatial domain of the image.Experimental results on popular benchmark datasets show that our method improves the performances of the current coding algorithms,and the average classification accuracies of our proposed method in MSRcv2,Caltech101,Scene15,Indoor 67 and UIUC-sport has reached 91.13%,76.02%,83.76%,44.78% and 89.05% respectively.
[1] Csurka G,Dance C R,Fan L X,et al.Visual categorization with bags of keypoints[A].Proceedings of the 8th European Conference on Computer Vision[C].Prague,CZE:Springer-Verlag,2004.1-22.
[2] Van Gemert J C,Veenman C J,Smeulders A W M,et al.Visual word ambiguity[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2010,32(7):1271-1284.
[3] Yang J C,Yu K,Gong Y H,Huang T.Linear spatial pyramid matching using sparse coding for image classification[A].Proceedings of the 22nd International Conference on Computer Vision and Pattern Recognition[C].Miami,USA:IEEE Computer Society,2009.1794-1801.
[4] Wang J J,Yang J C,Yu K,et al.Locality-constrained linear coding for image classification[A].Proceedings of the 23rd International Conference on Computer Vision and Pattern Recognition[C].San Francisco,USA:IEEE Computer Society,2010.3360-3367.
[5] Liu L Q,Wang L,Liu X W.In defense of soft-assignment coding[A].Proceedings of the 13th International Conference on Computer Vision[C].Barcelona,Spain:IEEE Computer Society,2011.2486-2493.
[6] Gao S,Tsang I,Huang T,Chia L.Laplacian sparse coding,hypergraph laplacian sparse coding,and application[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2013,35(1):92-104.
[7] Zhang Y,Chen T.Efficient kernels for identifying unbounded-order spatial features[A].Proceedings of the 22nd International Conference on Computer Vision and Pattern Recognition[C].Miami,USA:IEEE Computer Society,2009.1762-1769.
[8] Sawaree S,Winn J,Criminisi A.Discriminative object class models of appearance and shape by correlations[A].In:Proceedings of the 19th International Conference on Computer Vision and Pattern Recognition[C].New York,USA:IEEE Computer Society,2006.2033-2040.
[9] Su Y,Jurie F.Visual word disambiguation by semantic contexts[A].Proceedings of the 13th IEEE International Conference on Computer Vision[C].Barcelona,Spain:IEEE Computer Society,2011.311-318.
[10] Li F F,Fergus R,Perona P.Learning generative visual models from few training examples:an incremental Bayesian approach tested on 101 object categories[J].Computer Vision and Image Understanding,2007,106(1):59-70.
[11] Griffin G,Holub A.Perona.Caltech256 object category dataset[R].Pasadena:CIT,2007.1-20.
[12] Boureau Y L,Boch F,LeCun Y,Ponce J.Learning mid-level features for recognition[A].In:Proceedings of the 23rd International Conference on Computer Vision and Pattern Recognition[C].San Francisco,USA:IEEE Computer Society,2010.1-8.
[13] Zhang C J,Liu J,Tian Q,et al.Image classification by non-negative sparse coding,Low-Rank and sparse decomposition[A].Proceedings of the 24th International Conference on Computer Vision and Pattern Recognition[C].Colorado Springs,USA:IEEE Computer Society,2011.1673-1680.
[14] Wang Z,Feng J,Yan S,et al.Linear distance coding for image classification[J].IEEE Transaction on Image Processing,2013,22(2):537-548.
[15] Shabou A,Le Borgne H.Locality-constrained and spatially regularized coding for scene categorization[A].Proceedings of the 25th International Conference on Computer Vision and Pattern Recognition[C].Providence,USA:IEEE Computer Society,2012.3618-3625.
[16] Zhang T Z,Ghanem B,Liu S.Xu C S,et al.Low-rank sparse coding for image classification[A].Proceedings of the 14th International Conference on Computer Vision[C].Sydney,Australia:IEEE Computer Society,2013.281-288.
[17] Jia Y Q,Huang C,Darrell T.Beyond spatial pyramids:receptive field learning for pooled image features[A].Proceedings of the 25th International Conference on Computer Vision and Pattern Recognition[C].Providence,USA:IEEE Computer Society,2012.3370-3377.
[18] Wu Z F,Huang Y Z,Wang L,Tan T N.Group encoding of local features in image classification[A].Proceedings of the 19th International Conference on Image Processing[C].Orlando,USA:IEEE Computer Society,2012.1505-1508.
[19] Lazebnik S,Schmid C,Ponce J.Beyond bags of features:spatial pyramid matching for recognizing natural scene categories[A].Proceedings of the 19th International Conference on Computer Vision and Pattern Recognition[C].New York,USA:IEEE Computer Society,2006.2169-2178.
[20] Yang Y,Newsam S.Spatial pyramid co-occurrence for image classification[A].Proceedings of the 13th IEEE International Conference on Computer Vision[C].Barcelona,Spain:IEEE Computer Society,2011.1465-1472.
[21] Theriault C,Thome N,Cord M.Extended coding and pooling in the HMAX model[J].IEEE Transaction on Image Processing,2013,22(2):764-777.
[22] Quattoni A,Torralba A.Recognizing indoor scenes[A].Proceedings of the 22nd International Conference on Computer Vision and Pattern Recognition[C].Miami,USA:IEEE Computer Society,2009.413-420.
[23] Li L,Su H,Xing E,Li F F.Object bank:a high-level image representation for scene classification and semantic feature sparsification[A].Proceedings of the 24th Annual Conference on Neural Information Processing Systems[C].Vancouver B.C.,Canada:MIT Press,2010.1378-1386.
[24] Bo L,Ren X,Fox D.Hierarchical matching pursuit for image classification:architecture and fast algorithm[A].Proceedings of the 25th Annual Conference on Neural Information Processing Systems[C].Vancouver B.C.,Canada:MIT Press,2011.2115-2123.
2017, Vol. 45 
