Please wait a minute...
Advanced Search
现代图书情报技术  2015, Vol. 31 Issue (6): 41-48    DOI: 10.11925/infotech.1003-3513.2015.06.07
  研究论文 本期目录 | 过刊浏览 | 高级检索 |
一种应用多储备池回声状态网络的图像语义映射研究
王华秋1, 王斌1, 聂珍2
1 重庆理工大学计算机科学与工程学院 重庆 400054;
2 重庆理工大学图书馆 重庆 400054
Research on Image Semantic Mapping with Multiple-Reservoirs Echo State Network
Wang Huaqiu1, Wang Bin1, Nie Zhen2
1 College of Computer Science and Engineering, Chongqing University of Technology, Chongqing 400054, China;
2 Chongqing University of Technology Library, Chongqing 400054, China
全文: PDF(1199 KB)   HTML  
输出: BibTeX | EndNote (RIS)      
摘要 

目的】建立图像低层特征到高层语义的映射, 填补图像检索中的“语义鸿沟”, 以提高检索准确率。【方法】借鉴集成学习思想, 将多储备池回声状态网络(MESN)应用于图像语义映射模型中。图像低层特征按照类型划分后, 通过不同的储备池训练, 并对训练结果进行线性融合。【结果】该模型相对于BP神经网络和传统ESN, 平均映射错误率分别下降31.64%和19.28%, 查准率分别提高4.56%和1.86%。【局限】储备池参数通过人工设定, 未构造参数优化算法。【结论】实验结果证明, 将多储备池回声状态网络应用于图像语义映射中是有效的。

服务
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章
王斌
聂珍
王华秋
关键词 图像语义回声状态网络多储备池集成学习    
Abstract

[Objective] The mapping between low-level visual feature and high-level semantic information is built up to fill the “semantic gap” of image retrieval and improve accuracy. [Methods] Referring to the idea of ensemble learning, Multiple-Reservoirs Echo State Networks (MESN) is applied to semantic mapping model. After the low-level visual features of images are divided by feature types and trained by different reservoirs, the training results are combined linearly. [Results] Compared to BP Neural Network and traditional Echo State Network, the average error rate of MESN decreases by 31.64% and 19.28% respectively, the precision rate increases 4.56% and 1.86% respectively. [Limitations] The parameters of reservoirs are set artificially. Parameter optimization algorithm isn't constructed. [Conclusions] Experimental results show that the semantic mapping model of Echo State Networks with Multiple-Reservoirs is effective.

Key wordsImage semantic    Echo State Network    Multiple-Reservoirs    Ensemble learning
收稿日期: 2014-10-31     
:  G354.4  
基金资助:

本文系国家社会科学基金一般项目“数字图书馆智能图像检索系统研制”(项目编号:14BTQ053)和重庆市研究生教育教学改革研究项目“研究生《大数据挖掘》课程案例与演示系统研制”(项目编号: yjg143090)的研究成果之一。

通讯作者: 王华秋, ORCID: 0000-0002-6789-6775, E-mail: wanghuaqiu@163.com。     E-mail: wanghuaqiu@163.com
作者简介: 作者贡献声明: 王华秋: 提出研究命题、研究思路和实验方案, 论文最终版本修订; 王斌: 采集、分析数据, 算法设计及实现, 论文起草; 聂珍: 文献检索及综述。
引用本文:   
王华秋, 王斌, 聂珍. 一种应用多储备池回声状态网络的图像语义映射研究[J]. 现代图书情报技术, 2015, 31(6): 41-48.
Wang Huaqiu, Wang Bin, Nie Zhen. Research on Image Semantic Mapping with Multiple-Reservoirs Echo State Network. New Technology of Library and Information Service, DOI:10.11925/infotech.1003-3513.2015.06.07.
链接本文:  
http://manu44.magtech.com.cn/Jwk_infotech_wk3/CN/10.11925/infotech.1003-3513.2015.06.07

[1] Gudivada V N, Raghavan V V. Content-based Image Retrieval System [J]. IEEE Computer, 1995, 28(9): 18-22.
[2] Smeulder A W M, Worring M, Santini S, et al. Content-based Image Retrieval at the End of the Early Years [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000, 22(12): 1349-1380.
[3] Li J, Huang S, He R, et al. Image Classification Based on Fuzzy Support Vector Machine [C]. In: Proceedings of the 2008 International Symposium on Computational Intelligence and Design, Wuhan, China. 2008: 68-71.
[4] Kundu M K, Chowdhury M. Image Retrieval Using NN Based Pre-classification and Fuzzy Relevance Feedback [C]. In: Proceedings of the 2010 Annual IEEE India Conference (INDICON), Kolkata, India. 2010: 1-4.
[5] 杨栋, 周秀玲, 郭平.基于贝叶斯通用背景模型的图像标注[J]. 自动化学报, 2013, 39(10): 1674-1680. (Yang Dong, Zhou Xiuling, Guo Ping. Image Annotation with Bayesian Universal Background Model [J]. Acta Automatica Sinica, 2013, 39(10): 1674-1680.)
[6] Manjunath B S, Ohm J R, Vasudevan V V, et al. Color and Texture Descriptors [J]. IEEE Transactions on Circuits and Systems for Video Technology, 2001, 11(6): 703-715.
[7] Alexandre L A, Embrechts M J, Linton J. Benchmarking Reservoir Computing on Time-independent Classification Tasks [C]. In: Proceedings of the 2009 International Joint Conference on Neural Networks, Atlanta, GA, USA. 2009: 89-93.
[8] 郭嘉, 雷苗, 彭喜元. 基于相应簇回声状态网络静态分类方法[J]. 电子学报, 2011, 39(3): 14-18. (Guo Jia, Lei Miao, Peng Xiyuan. Echo State Networks for Static Classification with Corresponding Clusters [J]. Acta Electronica Sinica, 2011, 39(3): 14-18.)
[9] Stricker M A, Orengo M. Similarity of Color Images [C]. In: Proceedings of the SPIE Storage and Retrieval for Image and Video Databases III, 1995: 381-392.
[10] Haralick R M, Shangmugam K, Dinstein Its'Hak. Texture Feature for Image Classification [J]. IEEE Transactions on Systems, Man and Cybernetics, 1973, SMC-3(6): 610-621.
[11] Gabor D. Theory of Communication [J]. IEE, 1946, 93(3): 429-457.
[12] Jaeger H. The “Echo State” Approach to Analysing and Training Recurrent Neural Networks [R]. German National Reasearch Center for Information Technology, 2001.
[13] 郭嘉. 回声状态网络分类方法及其应用研究[D]. 哈尔滨: 哈尔滨工业大学, 2011. (Guo Jia. Research on Echo State Networks Classification Algorithm and Application [D]. Harbin: Harbin Institute of Technology, 2011. )
[14] 彭喜元, 郭嘉, 王建民.基于随机子空间与多储备池的分类方法[J]. 仪器仪表学报, 2011, 32(11): 2487-2492. (Peng Xiyuan, Guo Jia, Wang Jianmin. Random Subspace and Multiple Reservoirs Based Classifier [J]. Chinese Journal of Scientific Instrument, 2011, 32(11): 2487-2492.)
[15] 唐耀华, 高静怀, 包乾宗. 一种新的选择性支持向量机集成学习算法[J]. 西安交通大学学报, 2008, 42(10): 1221-1225. (Tang Yaohua, Gao Jinghuai, Bao Qianzong. Novel Selective Support Vector Machine Ensemble Learning Algorithm [J]. Journal of Xi'an Jiaotong University, 2008, 42(10): 1221-1225.)
[16] 张春霞, 张讲社. 选择性集成学习算法综述[J]. 计算机学报, 2011, 34(8): 1399-1410. (Zhang Chunxia, Zhang Jiangshe. A Survey of Selective Ensemble Learning Algorithms [J]. Chinese Journal of Computers, 2011, 34(8): 1399-1410.)
[17] Jaeger H, Lukoevicius M, Popovici D, et al. Optimization and Applications of Echo State Networks with Leaky-Integrator Neurons [J]. Neural Networks, 2007, 20(3): 335-352.
[18] Image Rank Machine [DB/OL]. [2014-09-15]. http://www. ci.gxnu.cn/cbir.

[1] 余本功,陈杨楠,杨颖. 基于nBD-SVM模型的投诉短文本分类*[J]. 数据分析与知识发现, 2019, 3(5): 77-85.
[2] 肖连杰,郜梦蕊,苏新宁. 一种基于模糊C-均值聚类的欠采样集成不平衡数据分类算法*[J]. 数据分析与知识发现, 2019, 3(4): 90-96.
[3] 操玮,李灿,贺婷婷,朱卫东. 基于集成学习的中国P2P网络借贷信用风险预警模型的对比研究*[J]. 数据分析与知识发现, 2018, 2(10): 65-76.
[4] 曾金,陆伟,丁恒,陈海华. 基于图像语义的用户兴趣建模*[J]. 数据分析与知识发现, 2017, 1(4): 76-83.
[5] 王南,赵捧未,窦永香,秦春秀,赵飞. 图像语义检索中的反馈噪声及其抑制算法研究[J]. 现代图书情报技术, 2007, 2(10): 42-46.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
版权所有 © 2015 《数据分析与知识发现》编辑部
地址:北京市海淀区中关村北四环西路33号 邮编:100190
电话/传真:(010)82626611-6626,82624938
E-mail:jishu@mail.las.ac.cn