基于多尺度特征融合Hessian稀疏编码的图像分类算法

doi:10.11772/j.issn.1001-9081.2017.12.3517

计算机应用 ›› 2017, Vol. 37 ›› Issue (12): 3517-3522.DOI: 10.11772/j.issn.1001-9081.2017.12.3517

• 计算机视觉与虚拟现实 • 上一篇下一篇

基于多尺度特征融合Hessian稀疏编码的图像分类算法

刘盛清, 孙季丰, 余家林, 宋治国

华南理工大学电子与信息学院, 广州 510641

收稿日期:2017-06-05 修回日期:2017-08-05 出版日期:2017-12-10 发布日期:2017-12-18
通讯作者: 刘盛清
作者简介:刘盛清(1991-),男,江西吉安人,硕士研究生,主要研究方向:机器学习、图像分类;孙季丰(1962-),男,广东广州人,教授,博士,主要研究方向:机器学习、模式识别、计算机视觉;余家林(1989-),男,贵州镇远人,博士研究生,主要研究方向:机器学习、人体姿态估计;宋治国(1988-),男,湖南湘西人,博士研究生,主要研究方向:机器学习、目标跟踪。
基金资助:
国家自然科学基金资助项目（61202292）；广东省自然科学基金资助项目（9151064101000037）。

Image classification algorithm based on multi-scale feature fusion and Hessian sparse coding

LIU Shengqing, SUN Jifeng, YU Jialin, SONG Zhiguo

School of Electronic and Information Engineering, South China University of Technology, Guangzhou Guangdong 510641, China

Received:2017-06-05 Revised:2017-08-05 Online:2017-12-10 Published:2017-12-18
Supported by:
The work is partially supported by the National Natural Science Foundation of China (61202292), the Natural Science Foundation of Guangdong Province (9151064101000037).

摘要/Abstract

摘要： 针对传统稀疏编码图像分类算法提取单一类型特征，忽略图像的空间结构信息，特征编码时无法充分利用特征拓扑结构信息的问题，提出了基于多尺度特征融合Hessian稀疏编码的图像分类算法（HSC）。首先，对图像进行空间金字塔多尺度划分；其次，在各个子空间层将方向梯度直方图（HOG）和尺度不变特征转换（SIFT）进行有效的融合；然后，为了充分利用特征的拓扑结构信息，在传统稀疏编码目标函数中引入二阶Hessian能量函数作为正则项；最后，利用支持向量机（SVM）进行分类。在Scene15数据集上的实验结果表明，HSC的准确率比局部约束线性编码（LLC）高了3~5个百分点，比支持区别性字典学习（SDDL）等对比方法高了1~3个百分点；在Caltech101数据集上的耗时实验结果表明，HSC的用时比多核学习稀疏编码（MKLSC）少40%左右。所提HSC可以有效提高图像分类准确率，算法的效率也优于对比算法。

关键词: 图像分类, 特征融合, 空间金字塔, 稀疏编码, 支持向量机

Abstract: The traditional sparse coding image classification algorithms extract single type features, ignore the spatial structure information of the images, and can not make full use of the feature topological structure information in feature coding. In order to solve the problems, a image classification algorithm based on multi-scale feature fusion and Hessian Sparse Coding (HSC) was proposed. Firstly, the image was divided into sub-regions with multi-scale spatial pyramid. Secondly, the Histogram of Oriented Gradient (HOG) and Scale-Invariant Feature Transform (SIFT) were effectively merged in each subspace layer. Then, in order to make full use of the feature topology information, the second order Hessian energy function was introduced to the traditional sparse coding target function as a regularization term. Finally, Support Vector Machine (SVM) was used to classify the images. The experimental results on dataset Scene15 show that, the accuracy of HSC is 3-5 percentage points higher than that of Locality-constrained Linear Coding (LLC), while it is 1-3 percentage points higher than that of Support Discrimination Dictionary Learning (SDDL) and other comparative methods. Time-consuming experimental results on dataset Caltech101 show that, the time-consuming of HSC is about 40% less than that of the Multiple Kernel Learning Sparse Coding (MKLSC). The proposed HSC can effectively improve the accuracy of image classification, and its efficiency is also better than the contrast algorithms.

Key words: image classification, feature fusion, spatial pyramid, sparse coding, Support Vector Machine (SVM)

中图分类号:

TP391.4

刘盛清, 孙季丰, 余家林, 宋治国. 基于多尺度特征融合Hessian稀疏编码的图像分类算法[J]. 计算机应用, 2017, 37(12): 3517-3522.

LIU Shengqing, SUN Jifeng, YU Jialin, SONG Zhiguo. Image classification algorithm based on multi-scale feature fusion and Hessian sparse coding[J]. Journal of Computer Applications, 2017, 37(12): 3517-3522.

参考文献

[1] 李博,曹鹏,栗伟,等.基于尺度空间中多特征融合的医学影像分类[J].计算机应用,2013,33(4):1108-1111,1114.(LI B, CAO P, LI W, et al. Medical image classification based on scale space multi-feature fusion[J]. Journal of Computer Applications, 2013, 33(4):1108-1111, 1114.)
[2] 王澍,吕学强,张凯,等.基于快速鲁棒特征集合统计特征的图像分类方法[J].计算机应用,2015,35(1):224-230.(WANG P, LYU X Q, ZHANG K, et al. Image classification approach based on statistical features of speed up robust feature set[J]. Journal of Computer Applications, 2015, 35(1):224-230.)
[3] LAZEBNIK S, SCHMID C, PONCE J. Beyond bags of features:spatial pyramid matching for recognizing natural scene categories[C]//CVPR 2006:Proceeding of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Piscataway, NJ:IEEE, 2006:2169-2178.
[4] LEE H, BATTLE H, RAINA R, et al. Efficient sparse coding algorithms[C]//Proceedings of the 2006 Annual Conference on Neural Information Processing Systems. Cambridge, MA:MIT Press, 2006:801-808.
[5] YANG J C, YU K, GONG Y H, et al. Linear spatial pyramid matching using sparse coding for image classification[C]//CVPR 2009:Proceedings of the 2009 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway, NJ:IEEE, 2009:1794-1801.
[6] WANG J J, YANG J C, YU K, et al. Locality-constrained linear coding for image classification[C]//CVPR 2010:Proceedings of the 2010 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway, NJ:IEEE, 2010:3360-3367.
[7] 刘培娜,刘国军,郭茂祖,等.非负局部约束线性编码图像分类算法[J].自动化学报,2015,41(7):1235-1243.(LIU P N, LIU G J, GUO M Z, et al, Image classification based on non-negative locality-constrained linear coding[J]. Acta Automatica Sinica, 2015, 41(7):1235-1243.)
[8] YANG M, ZHANG L, FENG X C, et al. Sparse representation based Fisher discrimination dictionary learning for image classification[J]. International Journal of Computer Vision, 2014, 109(3):209-232.
[9] LIU Y, CHEN W, CHEN Q C, et al. Support discrimination dictionary learning for image classification[C]//ECCV 2016:Proceedings of the 2016 European Conference on Computer Vision, LNCS 9906. Berlin:Springer, 2016:375-390.
[10] WANG L P, CHEN S C. Joint representation classification for collective face recognition[J]. Pattern Recognition, 2017, 63(5):182-192.
[11] SHRIVASTAVA A, PATEL V M, CHELLAPPA R. Multiple kernel learning for sparse representation-based classification[J]. IEEE Transactions on Image Processing, 2014, 23(7):3013-3024.
[12] FANG L Y, LI S T. Face recognition by exploiting local Gabor features with multitask adaptive sparse representation[J]. IEEE Transactions on Instrumentation and Measurement, 2015, 64(10):2605-2615.
[13] GAO S H, TSANG I W H, CHIA L T, et al. Local features are not lonely-Laplacian sparse coding for image classification[C]//CVPR 2010:Proceeding of the 2010 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway, NJ:IEEE, 2010:3555-3561.
[14] KIM K I, STEINKE F, HEIN M. Semi-supervised regression using Hessian energy with an application to semi-supervised dimensionality reduction[C]//Proceedings of the 2009 Annual Conference on Neural Information Processing Systems. Cambridge, MA:MIT Press, 2009:979-987.
[15] 史彩娟,阮秋琦,刘健,等.基于Hessian半监督特征选择的网络图像标注[J].计算机应用研究,2015,32(2):606-608,618.(SHI C J, RUAN Q Q, LIU J, et al, Web image annotation based on Hessian semi-supervised feature selection[J]. Application Research of Computers, 2015, 32(2):606-608, 618.)

基于多尺度特征融合Hessian稀疏编码的图像分类算法

Image classification algorithm based on multi-scale feature fusion and Hessian sparse coding

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]	周险兵, 樊小超, 任鸽, 杨勇. 基于多层次语义特征的英文作文自动评分方法[J]. 计算机应用, 2021, 41(8): 2205-2211.
[2]	王伟, 赵尔平, 崔志远, 孙浩. 基于HowNet义原和Word2vec词向量表示的多特征融合消歧方法[J]. 计算机应用, 2021, 41(8): 2193-2198.
[3]	吴丽丹, 薛雨阳, 童同, 杜民, 高钦泉. 基于前景语义信息的图像着色算法[J]. 计算机应用, 2021, 41(7): 2048-2053.
[4]	杜炎, 吕良福, 焦一辰. 基于模糊推理的模糊原型网络[J]. 计算机应用, 2021, 41(7): 1885-1890.
[5]	冯兴杰, 张天泽. 基于分组卷积进行特征融合的全景分割算法[J]. 计算机应用, 2021, 41(7): 2054-2061.
[6]	章荪, 尹春勇. 基于多任务学习的时序多模态情感分析模型[J]. 计算机应用, 2021, 41(6): 1631-1639.
[7]	贾鹤鸣, 郎春博, 姜子超. 基于轻量级卷积神经网络的植物叶片病害识别方法[J]. 计算机应用, 2021, 41(6): 1812-1819.
[8]	赖雪梅, 唐宏, 陈虹羽, 李珊珊. 基于注意力机制的特征融合-双向门控循环单元多模态情感分析[J]. 计算机应用, 2021, 41(5): 1268-1274.
[9]	贾鹤鸣, 姜子超, 李瑶, 孙康健. 基于改进斑点鬣狗优化算法的同步优化特征选择[J]. 计算机应用, 2021, 41(5): 1290-1298.
[10]	曹建芳, 田晓东, 贾一鸣, 闫敏敏. 改进DeepLabV3+模型在壁画分割中的应用[J]. 计算机应用, 2021, 41(5): 1471-1476.
[11]	卞鹏程, 郑忠龙, 李明禄, 何依然, 王天翔, 张大伟, 陈丽媛. 基于注意力融合网络的视频超分辨率重建[J]. 计算机应用, 2021, 41(4): 1012-1019.
[12]	胡屹杉, 秦品乐, 曾建潮, 柴锐, 王丽芳. 基于特征融合和动态多尺度空洞卷积的超声甲状腺分割网络[J]. 计算机应用, 2021, 41(3): 891-897.
[13]	姜倩玉, 王凤英, 贾立鹏. 基于感知哈希算法和特征融合的恶意代码检测方法[J]. 计算机应用, 2021, 41(3): 780-785.
[14]	后云龙, 朱磊, 陈琴, 吕燧栋. 基于高斯差分特征网络的显著目标检测[J]. 计算机应用, 2021, 41(3): 706-713.
[15]	邱宁佳, 王晓霞, 王鹏, 王艳春. 融合语法规则的双通道中文情感模型分析[J]. 计算机应用, 2021, 41(2): 318-323.