[1]张少辉,王迤冉.用于图像识别的稀疏高斯编码[J].南京理工大学学报(自然科学版),2016,40(01):61.
 Zhang Shaohui,Wang Yiran.Sparse Gaussian coding for image recognition[J].Journal of Nanjing University of Science and Technology,2016,40(01):61.
点击复制

用于图像识别的稀疏高斯编码
分享到:

《南京理工大学学报》(自然科学版)[ISSN:1005-9830/CN:32-1397/N]

卷:
40卷
期数:
2016年01期
页码:
61
栏目:
出版日期:
2016-02-29

文章信息/Info

Title:
Sparse Gaussian coding for image recognition
作者:
张少辉王迤冉
周口师范学院 网络工程学院,河南 周口 466001
Author(s):
Zhang ShaohuiWang Yiran
College of Network Engineering,Zhoukou Normal University,Zhoukou 466001,China
关键词:
图像识别 深度学习 特征表示 稀疏高斯编码 特征学习 K-means聚类
Keywords:
image recognition deep learning feature representation sparse Gaussian coding feature learning K-means clustering
分类号:
TP391
摘要:
为了解决特征学习过程中导致聚类的不均衡性,提出一种基于高斯编码的特征学习算法,使用K-means聚类进行特征训练,在编码过程中考虑了数据分布的影响,同时保留了K-means编码的稀疏性。并且鉴于K-means聚类的不均衡,还提出了一种特征选择的方法用于去噪和降维。改进的模型不仅很大程度上提高了性能而且训练时间和计算代价均小。在人脸数据库AR以及对象分类库Caltech101上设计了对比实验,实验结果都验证了该算法的有效性和鲁棒性。
Abstract:
In order to solve the malconformation of clustering in the feature learning,the paper presents a sparse Gaussian coding based feature learning algorithm.It can be trained only through K-means clustering.In the encoding process it takes data’s distribution into consideration.Given that the K-means clustering often results in unequal clusters,we also propose a feature selection method that can be used for denoising and dimension reduction.This model achieves high accuracy,and saves training time a lot.In this paper,we have designed a contrast experiment on the face database AR and the object database Caltech101.The experimental results show that the algorithm is effective and robust.

参考文献/References:

[1] 詹曙,王俊,杨福猛,等.基于Gabor特征和字典学习的高斯混合稀疏标识图像识别[J].电子学报,2015,43(3):523-528.

Zhan Shu,Wang Jun,Yang Fumeng,et al.Gaussian mixture sparse representation for image recognition based on gabor features and dictionary learning[J].Acta Electronica Sinica,2015,43(3):523-528.
[2]朱杰,杨万扣,唐振民.基于字典学习的核稀疏表示人脸识别方法[J].模式识别与人工智能,2012,25(5):859-864.
Zhu Jie,Yang Wankou,Tang Zhenmin.A dictionary learning based kernel sparse representation method for face recognition[J].Pattern Recognition and Artificial Intelligence,2012,25(5):859-864.
[3]Hinton G E,Salakhutdinov R R.Reducing the dimensionality of data with neural networks[J].Science,2006,313(5786):504-507.
[4]常晓夫,张文生,董维山.基于多种类视觉特征的混合高斯背景模型[J].中国图象图形学报,2011,16(5):829-834.
Chang Xiaofu,Zhang Wensheng,Dong Weishan.Mixture of Gaussian background modeling method based on multi-category visual features[J].Journal of Image and Graphics,2011,16(5):829-834.
[5]Cueto M A,Morton J,Sturmfels B.Geometry of the restricted Boltzmann machine[J].Algebraic Methods in Statistics & Probability II Ams Special Session Ams,2009,516(8):135-153.
[6]Coates A,Ng A Y,Lee H.An analysis of single-layer networks in unsupervised feature learning[C]//14th International Conference on Artificial Intelligence and Statistics.FT Lauderdale,USA:JMLR W&CP,2011:215-223.
[7]於跃成,刘彩生,生佳根.分布式约束一致高斯混合模型[J].南京理工大学学报,2013,37(6):799-806.
Yu Yuecheng,Liu Caisheng,Sheng Jiagen.Distributed constraints consistency Gaussian mixture mode[J].Journal of Nanjing University of Science and Technology,2013,37(6):799-806.
[8]Martinez A M.The AR face database[R].Barcelona,Spain:Computer Vision Center,1998.

相似文献/References:

[1]王 林,董 楠.基于Gabor特征与卷积神经网络的人体轮廓提取[J].南京理工大学学报(自然科学版),2018,42(01):89.[doi:10.14177/j.cnki.32-1397n.2018.42.01.013]
 Wang Lin,Dong Nan.Human silhouette identification based on Gabor featureand convolutional neural network[J].Journal of Nanjing University of Science and Technology,2018,42(01):89.[doi:10.14177/j.cnki.32-1397n.2018.42.01.013]
[2]姚富光,钟先信,周靖超.粒计算:一种大数据融合智能建模新方法[J].南京理工大学学报(自然科学版),2018,42(04):503.[doi:10.14177/j.cnki.32-1397n.2018.42.04.017]
 Yao Fuguang,Zhong Xianxin,Zhou Jingchao.Granular computing:a new method of intelligent modelingfor big data fusion[J].Journal of Nanjing University of Science and Technology,2018,42(01):503.[doi:10.14177/j.cnki.32-1397n.2018.42.04.017]

备注/Memo

备注/Memo:
收稿日期:2015-09-02 修回日期:2016-01-21
基金项目:河南省科技厅软科学研究计划项目(142400411213,142400411133); 河南省高等学校重点科研项目(15A520118); 河南省科技发展计划项目(NO.152102310381)
作者简介:张少辉(1982-),男,讲师,主要研究方向:图像识别、智能算法及应用,E-mail:zhangshaohui@zknu.edu.cn。
引文格式:张少辉,王迤冉.用于图像识别的稀疏高斯编码[J].南京理工大学学报,2016,40(1):61-66.
投稿网址:http://zrxuebao.njust.edu.cn
DOI:10.14177/j.cnki.32-1397n.2016.40.01.010
更新日期/Last Update: 2016-02-29