基于图正则化局部特征编码算法的图像分类方法

doi:10.3969/j.issn.0372-2112.2017.08.011

电子学报 ›› 2017, Vol. 45 ›› Issue (8): 1882-1887.DOI: 10.3969/j.issn.0372-2112.2017.08.011

基于图正则化局部特征编码算法的图像分类方法

杨赛¹, 赵春霞², 胡彬³, 陈峰¹

1. 南通大学电气工程学院, 南通 226019;
2. 南京理工大学计算机科学与工程学院, 江苏南京 210094;
3. 南通大学计算机科学与技术学院, 江苏南通 226019

收稿日期:2016-02-22 修回日期:2016-10-13 出版日期:2017-08-25
- 通讯作者:
- 杨赛
- 作者简介:
- 赵春霞,女,1964年出生,北京人.1985年、1988年和1998年在哈尔滨工业大学分别获得工学学士、工学硕士和工学博士学位,现为南京理工大学教授,博士生导师.主要研究方向为地面智能机器人与复杂环境理解.
- 基金资助:
- 江苏省普通高校自然科学研究面上项目 (No.16KJB520037）; 国家自然科学基金 (No.61602150）; 江苏省自然科学基金 (No.BK20151273）; 南通市科技项目前沿与关键技术 (No.MS22015100）; 江苏省博士后科研资助计划项目 (No.1601013B）

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

Received:2016-02-22 Revised:2016-10-13 Online:2017-08-25 Published:2017-08-25
- Supported by:
- General Program of Natural Science Research in Colleges and Universities of Jiangsu Province (No.16KJB520037); National Natural Science Foundation of China (No.61602150); Natural Science Foundation of Jiangsu Province, China (No.BK20151273); Frotier and Key Technique of Nantong Science and Technology Program (No.MS22015100); Funded by Postgraduate Science Research Program of Jiangsu Province (No.1601013B)

摘要/Abstract

摘要： 为了解决经典局部特征编码方法会产生相似局部特征之间编码系数不一致的问题，本文提出一种图正则化局部特征编码算法.该算法在对初始编码矢量所定义的能量化函数中引入正则化项，保证空间上相邻外观上相似的局部特征之间的编码矢量尽可能一致.MSRcv2、Caltech101、Scene 15以及Indoor 67四个公开数据集上的实验结果表明本文方法能够提高硬分配、软分配、稀疏编码、局部约束线性编码以及局部软分配五种经典编码方法的性能，并且基于本文编码算法的图像分类方法在上述四个公开数据集上的平均分类正确率分别达到了91.13%、76.02%、83.76%、44.78%.

关键词: 词袋模型, 编码算法, 图模型, 图像分类

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.

Key words: bag-of-feature, coding algorithm, graphical model, image classification

中图分类号:

TP391.4

杨赛, 赵春霞, 胡彬, 等. 基于图正则化局部特征编码算法的图像分类方法[J]. 电子学报, 2017, 45(8): 1882-1887.

YANG Sai, ZHAO Chun-xia, HU Bin, et al. An Image Classification Method Using Graphically Regularized Coding Algorithm[J]. Acta Electronica Sinica, 2017, 45(8): 1882-1887.

参考文献

[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.

基于图正则化局部特征编码算法的图像分类方法

An Image Classification Method Using Graphically Regularized Coding Algorithm

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	许新征, 李杉. 基于特征膨胀卷积模块的轻量化技术研究[J]. 电子学报, 2023, 51(2): 355-364.
[2]	王子为, 鲁继文, 周杰. 基于自适应梯度优化的二值神经网络[J]. 电子学报, 2023, 51(2): 257-266.
[3]	李淑慧, 邓志红, 冯肖雪, 潘峰. 强杂波背景下基于变分贝叶斯推理的机载雷达目标跟踪算法[J]. 电子学报, 2022, 50(5): 1089-1097.
[4]	宋鑫, 程乃平, 廖育荣, 倪淑燕, 雷拓峰. 具有逆向边增长结构LT码的设计与分析[J]. 电子学报, 2022, 50(5): 1201-1210.
[5]	王雪松, 张翰林, 程玉虎. 基于自编码器和超图的半监督宽度学习系统[J]. 电子学报, 2022, 50(3): 533-539.
[6]	赵旭东, 陶然, 李伟, 张蒙蒙. 高光谱图像分数域信息提取理论与方法进展[J]. 电子学报, 2022, 50(12): 2874-2883.
[7]	王相海, 宋若曦, 曲思洁, 穆振华, 宋传鸣. 图像多尺度几何分析域隐马尔可夫树模型研究进展[J]. 电子学报, 2022, 50(1): 238-249.
[8]	刘芳, 韩笑. 基于小波变换和深度网络的着陆地貌图像分类[J]. 电子学报, 2021, 49(11): 2171-2176.
[9]	江泽涛, 秦嘉奇, 张少钦. 参数池化卷积神经网络图像分类方法[J]. 电子学报, 2020, 48(9): 1729-1734.
[10]	黄鸿, 徐科杰, 石光耀. 联合多尺度多特征的高分遥感图像场景分类[J]. 电子学报, 2020, 48(9): 1824-1833.
[11]	祁志卫, 王笳辉, 岳昆, 乔少杰, 李劲. 图嵌入方法与应用:研究综述[J]. 电子学报, 2020, 48(4): 808-818.
[12]	邵航, 黄海亮, 郭雨晨, 戴琼海. 一种基于可信度估计单元的图像分类噪声抑制深度学习策略[J]. 电子学报, 2020, 48(10): 1969-1975.
[13]	魏志强, 毕海霞, 刘霞. 基于深度卷积神经网络的图上半监督极化SAR图像分类算法[J]. 电子学报, 2020, 48(1): 66-74.
[14]	曹晔. 一种基于局部排序的约束稀疏编码的图像分类方法[J]. 电子学报, 2019, 47(4): 832-836.
[15]	葛疏雨, 高子淋, 张冰冰, 李培华. 基于核化双线性卷积网络的细粒度图像分类[J]. 电子学报, 2019, 47(10): 2134-2141.