基于稀疏自动编码机的场景识别算法

doi:10.16180/j.cnki.issn1007-7820.2019.01.008

电子科技 ›› 2019, Vol. 32 ›› Issue (1): 38-41.doi: 10.16180/j.cnki.issn1007-7820.2019.01.008

基于稀疏自动编码机的场景识别算法

谢林,李菲菲,陈虬

上海理工大学光电信息与计算机工程学院,上海 200093

收稿日期:2018-12-28 出版日期:2019-01-15 发布日期:2018-12-29
作者简介:谢林(1992-),男,硕士研究生。研究方向:计算机视觉与模式识别。|李菲菲(1970-),女,博士,教授。研究方向:多媒体信息处理、图像处理与模式识别、信息检索等。|陈虬(1972-),男,博士,教授,博士生导师。研究方向:图像处理与模式识别、计算机视觉、信息检索等。
基金资助:
上海市高校特聘教授(东方学者)岗位计划(ES2012XX);上海市高校特聘教授(东方学者)岗位计划(ES2014XX)

Scene Recognition Algorithm Based on Sparse Autoencoder

XIE Lin,LI Feifei,CHEN Qiu

School of Optical-Electrical and Computer Engineering,University of Shanghai for Science and Technology,Shanghai 200093,China

Received:2018-12-28 Online:2019-01-15 Published:2018-12-29
Supported by:
The Program for Professor of Special Appointment (Eastern Scholar) at Shanghai Institutions of Higher Learning(ES2012XX);The Program for Professor of Special Appointment (Eastern Scholar) at Shanghai Institutions of Higher Learning(ES2014XX)

摘要/Abstract

摘要：

针对场景识别中低级特征与高级概念之间的语义鸿沟问题,提出了一种基于稀疏自动编码机的场景识别方法。采用了稀疏自动编码机和空间金字塔池化相结合的特征编码技术。首先对场景图像提取局部的HOG特征,然后利用改进的稀疏自动编码机对HOG特征进行编码,得到稀疏特征,通过空间金字塔池化和局部归一化得到整张场景图像的表示,最后利用线性SVM实现分类。在标准的场景图像数据集Scene-15上进行的实验表明,该算法可以将识别的准确率提升至81.97%。

关键词: 场景识别, 稀疏自动编码机, 空间金字塔池化, 局部归一化, HOG特征, SVM

Abstract:

To narrow the gap between low-level features and high-level concepts in scene recognition, a new algorithm based on the sparse autoencoder was proposed. This algorithm adopted the feature encoding technique that combined the sparse autoencoder and spatial pyramid pooling. First of all, the local HOG descriptors were extracted from scene images, then they were encoded into sparse features by the modified sparse autoencoder. After spatial pyramid pooling and local normalization on these sparse features, the image representation can be obtained. Finally, linear SVM was utilized to implement scene recognition. The experimental results on Scene-15 dataset indicated that the recognition accuracy of this algorithm can be increased up to 81.97%.

Key words: scene recognition, sparse autoencoder, spatial pyramid pooling, local normalization, HOG, SVM

中图分类号:

TP391

谢林,李菲菲,陈虬. 基于稀疏自动编码机的场景识别算法[J]. 电子科技, 2019, 32(1): 38-41.

XIE Lin,LI Feifei,CHEN Qiu. Scene Recognition Algorithm Based on Sparse Autoencoder[J]. Electronic Science and Technology, 2019, 32(1): 38-41.

图/表 6

图1

图2

图3

图4

表1

表2

参考文献 16

[1]	G Lowe D . Distinctive image features from scale-invariant keypoints[J]. International Journal of Computer Vision, 2004,60(2):91-110. doi: 10.1023/B:VISI.0000029664.99615.94
[2]	Bay H, Tuytelaars T, Van Gool L. Surf: speeded up robust features [C].Graz:European Conference on Computer Vision, 2006.
[3]	Ojala T, Pietikainen M, Maenpaa T . Multiresolution gray-scale and rotation invariant texture classification with local binary patterns[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2002,24(7):971-987. doi: 10.1007/3-540-45054-8_27
[4]	Sivic J, Zisserman A. Video google: a text retrieval approach to object matching in videos [C].Nice: IEEE International Conference on Computer Vision, 2003.
[5]	Wang J, Yang J, Yu K, et al. Locality-constrained linear coding for image classification [C].San Francisco: IEEE International Conference on Computer Vision and Pattern Recognition, 2010.
[6]	Gao S, Tsang I, Chia L, et al. Local features are not lonely-Laplacian sparse coding for image classification [C].San Francisco:IEEE International Conference on Computer Vision and Pattern Recognition, 2010.
[7]	Dalal N, Triggs B. Histograms of oriented gradients for human detection [C].San Diego:IEEE International Conference on Computer Vision and Pattern Recognition, 2005.
[8]	Japkowicz N, Hanson S, Gluck M . Nonlinear autoassociation is not equivalent to PCA[J]. Neural Computation, 2000,12(3):531-545. doi: 10.1162/089976600300015691
[9]	Glorot X, Bordes A, Bengio Y. Deep sparse rectifier neural networks [C].Ft. Lauderdale:International Conference on Artificial Intelligence and Statistics, 2011.
[10]	Li F, Perona P. A Bayesian hierarchical model for learning natural scene categories [C].San Diego:IEEE International Conference on Computer Vision and Pattern Recognition, 2005.
[11]	Lazebnik S, Schmid C, Ponce J. Beyond bags of features: spatial pyramid matching for recognizing natural scene categories [C].New York:IEEE International Conference on Computer Vision and Pattern Recognition, 2006.
[12]	Fan R, Chang K, Hsieh C , et al. Liblinear: a library for large linear classification[J].Journal of Machine Learning Research, 2008(9):1871-1874. doi: 10.1145/1390681.1442794
[13]	Parizi S, Oberlin J, Felzenszwalb P. Reconfigurable models for scene recognition [C].Providence:IEEE International Conference on Computer Vision and Pattern Recognition, 2012.
[14]	Yang J, Yu K, Gong Y, et al. Linear spatial pyramid matching using sparse coding for image classification [C]. Miami:IEEE International Conference on Computer Vision and Pattern Recognition, 2009.
[15]	Li L, Su H, Xing E, et al. Object bank:a high-level image representation for scene classification & semantic feature sparsification [C].Hyatt Regency:International Conference on Neural Information Processing Systems, 2010.
[16]	Harada T, Ushiku Y, Yamashita Y, et al. Discriminative spatial pyramid [C].Colorado Springs:IEEE International Conference on Computer Vision and Pattern Recognition, 2011.

方法	隐含层中节点的个数	识别率/%
传统的稀疏自动编码机(SAE)	1024	78.58
传统的稀疏自动编码机(SAE)	2048	79.36
改进的稀疏自动编码机(MSAE)	1024	80.85
改进的稀疏自动编码机(MSAE)	2048	81.97

方法	识别率/%
MSAE	81.97
RBoW ^[13]	78.60
ScSPM ^[14]	80.28
Object Bank ^[15]	80.90
SPM ^[11]	81.40
DSPM ^[16]	81.81

基于稀疏自动编码机的场景识别算法

Scene Recognition Algorithm Based on Sparse Autoencoder

RichHTML

PDF (PC)

赞

可视化

摘要/Abstract

引用本文

使用本文

图/表 6

参考文献 16

相关文章 10

Metrics

本文评价

推荐阅读 0

[1]	张泽晨,巨志勇. 基于BoF模型的多特征融合果蔬图像分类方法[J]. 电子科技, 2020, 33(7): 41-45.
[2]	缪冉,李菲菲,陈虬. 基于卷积神经网络与多尺度空间编码的场景识别方法[J]. 电子科技, 2020, 33(12): 54-58.
[3]	叶子,李若凡. 基于Android的手机恶意代码检测与防护技术[J]. 电子科技, 2019, 32(6): 54-57.
[4]	牟竹青. 基于KPCA-LSSVM的单向阀故障诊断研究[J]. 电子科技, 2019, 32(3): 10-15.
[5]	周庆曙，陈劲杰，纪鹏飞. 基于SVM的多特征手写体汉字识别技术[J]. , 2016, 29(8): 136-.
[6]	茅嫣蕾,魏赟,贾佳. 一种基于KKT条件和壳向量的SVM增量学习算法[J]. , 2016, 29(2): 38-.
[7]	危傲. 基于SVM算法的分类器设计[J]. , 2015, 28(4): 23-.
[8]	徐发国,郑翔,吕涛. 基于HOG和粒子滤波的足球视频中球的跟踪方法[J]. , 2013, 26(9): 36-.
[9]	薛丹,孙万蓉,李京京,贾海龙,杨子峰,王政. 一种基于SVM的改进车牌识别算法[J]. , 2013, 26(11): 22-.
[10]	吉卫卫, 谭晓阳. SVM及其鲁棒性研究[J]. , 2012, 25(5): 97-.