CNN视觉特征的图像检索

doi:10.13190/j.jbupt.2015.s1.023

北京邮电大学学报 ›› 2015, Vol. 38 ›› Issue (s1): 103-106,120.doi: 10.13190/j.jbupt.2015.s1.023

CNN视觉特征的图像检索

李钊^1,2,3, 卢苇¹, 邢薇薇¹, 孙占全^2,3, 王伟东¹, 魏云超¹

1. 北京交通大学软件学院, 北京 100044;
2. 山东省计算中心国家超级计算济南中心, 济南 250014;
3. 山东省计算机网络重点实验室, 济南 250014

收稿日期:2014-08-22 出版日期:2015-06-28 发布日期:2015-06-28
作者简介:李钊(1975—), 男, 博士生, E-mail: 11112095@bjtu.edu.cn; 卢苇(1963—), 男, 教授, 博士生导师.
基金资助:
国家自然科学基金项目(61370128)

Image Retrieval Based on CNN Visual Features

LI Zhao^1,2,3, LU Wei¹, XING Wei-wei¹, SUN Zhan-quan^2,3, WANG Wei-dong¹, WEI Yun-chao¹

1. School of Software Engineering, Beijing Jiaotong University, Beijing 100044, China;
2. National Supercomputing Center in Jinan, Shandong Computer Science Center, Jinan 250014, China;
3. Shandong Provincial Key Laboratory of Computer Network, Jinan 250014, China

Received:2014-08-22 Online:2015-06-28 Published:2015-06-28

摘要/Abstract

摘要：

卷积神经网络(CNN)是当前图像识别领域的研究热点,利用预训练的CNN网络提取的图像特征展示出了较强的图像识别能力. 主要对比分析了传统视觉特征和CNN视觉特征在基于内容图像检索任务中的性能表现,并指出了一些可以值得深入研究的方向. 在两个公开数据库(Pascal Sentence 和 Pascal VOC 2007)的实验尝试表明CNN视觉特征比传统的视觉特征更适用于图像检索.

关键词: 卷积神经网络, 基于内容的图像检索, 特征提取, 深度学习

Abstract:

Convolutional neural network (CNN) currently becomes research focus for image recognition. The visual features extracted from the pre-trained CNN demonstrate powerful ability for various recognition tasks. The performance of traditional visual features and CNN visual features for content-based image retrieval was mainly compared. Experiments on the two public available datasets of Pascal Sentence and Pascal VOC 2007 show that, a sufficient performance of CNN visual features used in image retrieval when compared with traditional visual features.

Key words: convolutional neural network, content-based image retrieval, feature extraction, deep learning

中图分类号:

TN911.22

李钊, 卢苇, 邢薇薇, 孙占全, 王伟东, 魏云超. CNN视觉特征的图像检索[J]. 北京邮电大学学报, 2015, 38(s1): 103-106,120.

LI Zhao, LU Wei, XING Wei-wei, SUN Zhan-quan, WANG Wei-dong, WEI Yun-chao. Image Retrieval Based on CNN Visual Features[J]. JOURNAL OF BEIJING UNIVERSITY OF POSTS AND TELECOM, 2015, 38(s1): 103-106,120.

参考文献

[1] Edkins J, Graham M. Content-based image retrieval [R]. University of Northumbria at Newcastle: Technical Report, 1999.

[2] Oliva A, Antonio T. Modeling the shape of the scene: a holistic representation of the spatial envelope [J]. International Journal of Computer Vision, 2001, 42(3): 145-175.

[3] Lowe D G. Distinctive image features from scale-invariant keypoints [J]. International Journal of Computer Vision, 2004, 60(2): 91-110.

[4] Dalal N, Bill T. Histograms of oriented gradients for human detection [C]//CVPR. San Diego, USA: IEEE, 2005: 886-893.

[5] Datta R, Joshi D. Image retrieval: ideas, influences, and trends of the new age [J]. ACM Computing Surveys (CSUR), 2008, 40(2): 5.

[6] Hinton G E, Ruslan R S. Reducing the dimensionality of data with neural networks [J]. Science, 2006, 313(5786): 504-507.

[7] Cun L, Boser B. Handwritten digit recognition with a back-propagation network [C]//Advances in Neural Information Processing Systems. Denver, Colorado, USA: MIT, 1990: 396-404.

[8] Alex K, Ilya S. Imagenet classification with deep convolutional neural networks [C]//Advances in Neural Information Processing Systems. Lake Tahoe, Nevada, USA: MIT, 2012: 1097-1105.

[9] Deng Jia, Dong Wei. Imagenet: a large-scale hierarchical image database [C]//CVPR. Miami, USA: IEEE, 2009: 248-255.

[10] Ali S R, Hossein A, Josephine S, et al. Cnn features off-the-shelf: an astounding baseline for recognition [C]//CVPRW. Columbus, USA: IEEE, 2014: 512-519.

[11] Jia Yangqing, Shelhamer E. Caffe: convolutional architecture for fast feature embedding [C]//Proceedings of the ACM International Conference on Multimedia. Orlando, USA: ACM, 2014: 675-678.

[12] Rashtchian C, Peter Y. Collecting image annotations using Amazons mechanical turk [C]//Proceedings of the NAACL HLT Workshop on Creating Speech and Language Data with Amazons Mechanical Turk. Los Angeles, USA: MIT, 2010: 139-147.

[13] Everingham M, Gool V L. The pascal visual object classes (voc) challenge [J]. International Journal of Computer Vision, 2010, 88(2): 303-338.

[14] Hwang S J, Grauman K. Accounting for the relative importance of objects in image retrieval [C]//BMVC. Aberystwyth, UK: BMVA, 2010: 1-12.

[1]	刘阳, 滕颖蕾, 牛涛, 郅佳琳. 基于深度强化学习的滤波器剪枝方案[J]. 北京邮电大学学报, 2023, 46(3): 31-36.
[2]	靳梦凡, 黄智濒, 储志强. 复杂环境下多模态指导的点云补全方法[J]. 北京邮电大学学报, 2023, 46(3): 103-108.
[3]	荣震宇刘建毅. 基于Transformer和MLP的眼底血管分割算法[J]. 北京邮电大学学报, 2023, 46(1): 26-31.
[4]	余佳润王亚峰. 一种低信噪比下基于深度学习的DoA估计方法[J]. 北京邮电大学学报, 2022, 45(6): 119-125.
[5]	宋宇博高嘉振. 改进YOLOv3算法的交通多目标检测方法[J]. 北京邮电大学学报, 2022, 45(5): 103-108.
[6]	张小乾谈振王潇梁芹万黎明. 基于正交投影学习的图像特征提取算法[J]. 北京邮电大学学报, 2022, 45(5): 85-90,128.
[7]	叶康张淑军郭淇李辉崔雪红. 基于CM-Transformer的连续手语识别[J]. 北京邮电大学学报, 2022, 45(5): 49-53,78.
[8]	刘金桐, 杨国兴, 刘晓鸿, 王光宇. 针对心电图分类模型的平滑攻击算法[J]. 北京邮电大学学报, 2022, 45(4): 44-50.
[9]	黄柳婷, 刘可欣, 牛凯, 常春, 贺志强. 基于深度学习的哮喘患者CT影像黏液栓自动识别[J]. 北京邮电大学学报, 2022, 45(4): 58-63.
[10]	武兴坤, 罗涛, 刘爱军, 杨明, 张文静. 面向主动脉缩窄辅助诊断的神经网络模型设计[J]. 北京邮电大学学报, 2022, 45(4): 1-6.
[11]	武兴坤罗涛刘爱军杨明张文静李剑峰李文秀. 面向主动脉缩窄辅助诊断的神经网络模型设计[J]. 北京邮电大学学报, 2022, 45(4): 1-6.
[12]	柳长源, 虎浩媛, 毕晓君. 双线性融合网络的驾驶员分心行为识别[J]. 北京邮电大学学报, 2022, 45(2): 79-84.
[13]	许同乐, 孟良, 孔晓佳, 苏元浩, 孙砚飞. 基于EEMD的ICNN故障诊断方法[J]. 北京邮电大学学报, 2022, 45(2): 110-116.
[14]	李晓辉, 王先文, 樊韬, 刘佳文, 万宏杰. 基于卷积神经网络的高性能5G下行同步算法[J]. 北京邮电大学学报, 2022, 45(2): 117-123.
[15]	王靖, 姜竹青, 门爱东, 郭晓强, 王智康. 阶梯式图像去噪方法[J]. 北京邮电大学学报, 2022, 45(1): 52-57.

CNN视觉特征的图像检索

Image Retrieval Based on CNN Visual Features

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

本文评价