Image Classification Algorithm for Deep Belief Network Based on Multi-feature Fusion

doi:10.3969/j.issn.1000-3428.2015.11.042

Abstract

Abstract: Taking the single feature and the major classification algorithms into consideration,an image classification algorithm based on fusion of multi-feature for Deep Belief Network(DBN) is proposed to classify the nature images.The features about color,texture,shape are extracted and the characteristic weight matrix is formed.Then the characteristic matrix is normalized.The samples are trained and classified using the DBN with four levels which is constructed.The proposed method has been evaluated on the Corel dataset by train weight,and the result shows that the average classification accuracy is 85.1% by the proposed algorithm,which is higher then single feature algorithm and other mainstream algorithms.

Key words: Deep Belief Network(DBN), image classification, feature extraction, multi-feature fusion, image retrival

摘要： 针对现有单一特征描述符及浅层结构分类算法分类正确率较低的问题,基于底层图像特征提出一种针对自然界图像特点的深度置信网络(DBN)图像分类算法。提取样本图像中的颜色、纹理和形状特征,构成多特征融合的权重矩阵,并对特征矩阵进行归一化处理,利用构建的4层DBN分类器进行训练和分类。采用Corel图库,通过训练权重进行测试,结果表明,该算法的平均分类正确率达到85.1%,高于使用单一特征的分类算法和其他主流分类算法。

关键词: 深度置信网络, 图像分类, 特征提取, 多特征融合, 图像检索

CLC Number:

TP391

XU Qingyong,JIANG Shunliang,HUANG Wei,LI Jing,XU Shaoping,YE Famao. Image Classification Algorithm for Deep Belief Network Based on Multi-feature Fusion[J]. Computer Engineering, doi: 10.3969/j.issn.1000-3428.2015.11.042.

许庆勇,江顺亮,黄伟,李菁,徐少平,叶发茂. 基于多特征融合的深度置信网络图像分类算法[J]. 计算机工程, doi: 10.3969/j.issn.1000-3428.2015.11.042.

/ / Recommend / Download Citations

URL: http://www.ecice06.com/EN/10.3969/j.issn.1000-3428.2015.11.042

http://www.ecice06.com/EN/Y2015/V41/I11/245

References

参考文献［1］许元飞.基于纹理的检索算法研究［J］.西安科技大学学报,2013,33(4):470-474. ［2］Bengio Y,Delalleau O.On the Expressive Power of Deep Architectures［C］//Proceedings of the 14th International Conference on Discovery Science.Berlin,Germany:Springer-Verlag,2011:18-36. ［3］Wei Huang,Yan Gao,Chan K L.A Review of Region-based Image Retrieval［J］.Journal of Signal Processing Systems,2010,59(2):143-161. ［4］Datta R,Joshi D,Li J,et al.Image Retrieval:Ideas,Influences,and Trends of the New Age［J］.ACM Computing Surveys,2008,40(2):1-5. ［5］邓金杰,肖诗斌,吕学强,等.基于多特征融合的图像检索研究［C］//第四届图像图形技术与应用学术会议论文集.北京:中国传媒大学出版社,2009:189-193. ［6］Zheng Liang,Wang Shengjin,Tian Qi.Coupled Binary Embedding for Large-scale Image Retrieval［J］.IEEE Transactions on Image Processing,2014,23(8):3368-3380. ［7］Zheng Liang,Wang Shengjin,Liu Ziqiong,et al.Packing and Padding:Coupled Multi-index for Accurate Image Re-trieval［C］//Proceedings of CVPR’14.Washington D.C.,USA:IEEE Press,2014:1947-1954. ［8］Freund Y,Schapire R E.Experiments with a New Boosting Algorithm［C］//Proceedings of ICML’96.Washington D.C.,USA:IEEE Press,1996:148-156. ［9］Jordan A.On Discriminative vs. Generative Classifiers:A Comparison of Logistic Regression and Naive Bayes［C］//Proceedings of NIPS’01.［S.l.］:NIPS Foundation,Inc.,2001:605-610. ［10］Zhang J,Marszalek M,Lazebnik S,et al.Local Features and Kernels for Classification of Texture and Object Categories:A Comprehensive Study［J］.International Journal of Computer Vision,2007,73(2):213-238. ［11］孙劲光,蒋金叶,孟祥福,等.一种数值属性的深度置信网络分类方法［J］.计算机工程与应用,2014,50(2):112-115. ［12］Bengio Y.Learning Deep Architectures for AI［J］.Foundations and Trends in Machine Learning,2009,1(1):321-360 ［13］Hinton G E,Osindero S,Teh Y W.A Fast Learning Algorithm for Deep Belief Nets［J］.Neural Computation,2006,18(7):1527-1554. ［14］付燕,鲜艳明.基于多特征和改进SVM集成的图像分类［J］.计算机工程,2011,37(21):196-198. ［15］Smith J R,Chang S.Automated Binary Texture Feature Sets for Image Retrieval［C］//Proceedings of IEEE International Conference on Acoustic,Speech,and Signal.Washington D.C.,USA:IEEE Press,1996:2239-2242. ［16］Haralick R M,Shanmugam K,Dinstein I.Texture Features for Image Classification［J］.IEEE Transactions on Systems,1973,3(6):610-621 ［17］Tamura H.Textural Features Corresponding to Visual Perception［J］.IEEE Transactions on Systems,1978,8(6):460-473. ［18］孙志军,薛磊,许阳明,等.深度学习研究综述［J］.计算机应用研究,2012,29(8):2806-2810. ［19］Welling M,Rosen-Zvi M,Hinton G.Exponential Family Harmoniums with an Application to Information Retrieval［C］//Proceedings of NIPS’05.［S.l.］:NIPS Foundation,Inc.,2005:1481-1488. ［20］Williams C,Agakov F.An Analysis of Contrastive Divergence Learning in Gaussian Boltzmann Machines,EDI-INFRR-0120［R］.Edinburgh,UK:Institute for Adaptive and Neural Computation,University of Edinburgh,2002. ［21］Carreira-Perpinan M,Hinton G.On Contrastive Diver-gence Learning［C］//Proceedings of the 10th Inter-national Workshop on Artificial Intelligence and Statistics.［S.l.］:Society for Artificial Intelligence and Statistics,2005:33-40. ［22］Hinton G E.Distributed Representations,CS-84-157［R］.Toronto,Canada:Computer Science Department,University of Toronto,1984. ［23］罗晓清,吴小俊,王土同,等.基于二次融合多特征的多聚焦图像融合［J］.数据采集与处理,2010,25(4):430-436. ［24］Hinton G E.Training Products of Experts by Minimizing Contrastive Divergence［J］.Neural Computation,2002,14(8):1771-1800. ［25］Rao M B,Kavitha C H.A New Feature Set for Content Based Image Retrieval［J］.Information Communication and Embedded Systems,2013,1(1):84-89. ［26］Murala S,Maheshwari R P,Balasubramanian R.Direc-tional Local Extrema Patterns:A New Descriptor for Content Based Image Retrieval［J］.International Journal of Multimedia Information Retrieval,2012,1(3):191-203. ［27］Hiremath S,Pujari J.Content Based Image Retrieval Using Color,Texture and Shape Features［C］//Proceed-ings of the 15th International Conference on Advanced Computing and Communications.Washington D.C.,USA:IEEE Press,2007:780-784. 编辑金胡考

[1]	Na MA, Tingxin WEN, Xu JIA, Xiaohui LI. Adaptive Vehicle Face Re-identification Model Under Complex Illumination Conditions [J]. Computer Engineering, 2023, 49(8): 275-282, 290.
[2]	Ping CAO, Huaizhi YANG, Yijun BO, Jia YOU, Chunjie ZHANG, Danyong LI. Low-quality Crack Image Classification with Multi-Knowledge Distillation [J]. Computer Engineering, 2023, 49(7): 204-213.
[3]	DAI Haolei, HUANG Yonghui, ZHOU Guoxu. Clustering Analysis Based on Hyper-graph Regularized Non-Negative Tensor Train Decomposition [J]. Computer Engineering, 2023, 49(6): 81-89.
[4]	SONG Yukai, XIE Jiang. Lightweight Speech Emotion Recognition Model Based on Multi-Task Learning [J]. Computer Engineering, 2023, 49(5): 122-128.
[5]	ZHANG Boyi, ZHE Tiantian, ZHAO Xinxu, LIU Qinghua, WANG Jiachen. Fatigue Driving Detection Based on Eye and Mouth State Recognition Network [J]. Computer Engineering, 2023, 49(5): 310-320.
[6]	CHEN Wenxuan, ZENG Bi, GUO Zhixing. Fall Detection Method Integrating Multi-Feature and Semantic Graph Convolution Network [J]. Computer Engineering, 2023, 49(5): 277-285,294.
[7]	LI Peiyu, ZHANG Yali. Face Image Super-Resolution Reconstruction Based on Improved SRGAN Model [J]. Computer Engineering, 2023, 49(4): 199-205.
[8]	GENG Lei, FU Hongliang, TAO Huawei, LU Yuan, GUO Xinying, ZHAO Li. Speech Emotion Recognition Based on Dynamic Convolution Recurrent Neural Network [J]. Computer Engineering, 2023, 49(4): 125-130,137.
[9]	GUAN Ripeng, KUANG Liqun, JIAO Shichao, XIONG Fengguang, HAN Xie. Retrieval Method of 3D Models Driven by Multi-modal Feature Fusion and Word Embedding [J]. Computer Engineering, 2023, 49(4): 101-107,113.
[10]	HE Yue, CHEN Guangsheng, JING Weipeng, XU Zekun. Remote Sensing Image Retrieval Based on Deep Multi-Similarity Hashing Method [J]. Computer Engineering, 2023, 49(2): 206-212.
[11]	HAN Yanling, SHEN Siyang, XU Lijun, WANG Jing, ZHANG Yun, ZHOU Ruyan. GPU Parallel Method for Deep Learning Image Classification [J]. Computer Engineering, 2023, 49(1): 191-200.
[12]	GAO Qingji, LI Tianhao, XING Zhiwei, LIU Peipei. Point Cloud Semantic Segmentation Method Based on Block Feature Fusion [J]. Computer Engineering, 2022, 48(9): 37-44,54.
[13]	ZHOU Haiyun, XIANG Xuezhi, WANG Xinyao, REN Wenkai. Chained End-to-End Pedestrian Multi-Object Tracking Network with Multi-Feature Fusion [J]. Computer Engineering, 2022, 48(9): 305-313.
[14]	YAN Jing, ZHANG Xueying, LI Fenglian, CHEN Guijun, HUANG Lixia. Regression Prediction Model Combining Stack Supervised AE and Variable Weighted ELM [J]. Computer Engineering, 2022, 48(8): 62-69,76.
[15]	LI Kequan, CHEN Yan, LIU Jiachen, MU Xiangwei. Survey of Deep Learning-Based Object Detection Algorithms [J]. Computer Engineering, 2022, 48(7): 1-12.

Please choose a citation manager

Content to export