[1]龚震霆,陈光喜,任夏荔,等.基于卷积神经网络和哈希编码的图像检索方法[J].智能系统学报编辑部,2016,11(3):391-400.[doi:10.11992/tis.201603028]
 GONG Zhenting,CHEN Guangxi,REN Xiali,et al.An image retrieval method based on a convolutional neural network and hash coding[J].CAAI Transactions on Intelligent Systems,2016,11(3):391-400.[doi:10.11992/tis.201603028]
点击复制

基于卷积神经网络和哈希编码的图像检索方法(/HTML)
分享到:

《智能系统学报》编辑部[ISSN:1673-4785/CN:23-1538/TP]

卷:
第11卷
期数:
2016年3期
页码:
391-400
栏目:
出版日期:
2016-06-25

文章信息/Info

Title:
An image retrieval method based on a convolutional neural network and hash coding
作者:
龚震霆12 陈光喜12 任夏荔12 曹建收12
1. 桂林电子科技大学 计算机与信息安全学院, 广西 桂林 541004;
2. 广西高校图像图形智能处理重点实验室, 广西 桂林 541004
Author(s):
GONG Zhenting12 CHEN Guangxi12 REN Xiali12 CAO Jianshou12
1. School of Computer and Information Security, Guilin University of Electronic Technology, Guilin 541004, China;
2. Guangxi Colleges and Universities Key Laboratory of Intelligent Processing of Computer Images and Graphics, Guilin 541004, China
关键词:
图像检索人工特征卷积神经网络卷积特征哈希编码
Keywords:
image retrievalartificial featuresconvolutional neural networkconvolutional featureshash coding
分类号:
TP391
DOI:
10.11992/tis.201603028
摘要:
在图像检索中,传统的基于人工特征的检索方法并不能取得很好的效果。为此提出一种结合卷积神经网络和以前最好水准的哈希编码策略的图像检索方法。鉴于近几年卷积神经网络在大量的计算机视觉任务上的巨大进步,该方法首先使用在ILSVRC数据集上预训练过的VGGNet-D网络模型对实验图像数据集提取卷积特征来得到图像的深层表示,再采用以前最好水准的哈希策略将这些深层表示进行编码,从而得到图像的二进制码,最后再进行快速图像检索。在两个常用的数据集Caltech101和Caltech256上的实验结果表明,本文方法的5个策略相比于以前最好水准的相应的图像检索策略在“精度-召回率”和“平均正确率值-编码位数”两个指标上能获得更优异的性能,证明了本文方法在图像检索上的有效性。
Abstract:
For image retrieval, traditional retrieval methods based on artificial features are not effective enough. Hence, we propose an image retrieval method, which combines a convolutional neural network and previous state-of-the-art hash coding strategies. In view of the great progress that convolutional neural networks have made in a large number of computer vision tasks in recent years, this method first uses the model "VGGNet-D" pre-trained on the ILSVRC’s dataset to extract the convolutional features from experimental image datasets to get the deep representations of images, then adopts previous state-of-the-art hash coding strategies to encode the deep representations to obtain the binary codes, and, finally, performs a quick image retrieval. The experimental results on the commonly used Caltech101 and Caltech256 datasets show that this method’s five strategies, compared with the previous state-of-the-art image retrieval strategies, can obtain better, indeed excellent, performance in both the "Precision-Recall" and "mean Average Precision-Number of bits" metrics, proving the effectiveness of the proposed method in image retrieval.

参考文献/References:

[1] SMEULDERS 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.
[2] WAN Ji, WANG Dayong, HOI S C H, et al. Deep learning for content-based image retrieval: a comprehensive study[C]//Proceedings of the 22nd ACM international conference on multimedia. Orlando, USA, 2014: 157-166.
[3] LOWE D G. Distinctive Image features from scale-invariant keypoints[J]. International journal of computer vision, 2004, 60(2): 91-110.
[4] BAY H, TUYTELAARS T, VAN GOOL L. SURF: speeded up robust features[M]//LEONARDIS A, BISCHOF H, PINZ A. Computer vision-ECCV 2006. Berlin Heidelberg: Springer, 2006: 404-417.
[5] SARIKAYA R, HINTON G E, DEORAS A. Application of deep belief networks for natural language understanding[J]. IEEE/ACM transactions on audio, speech, and language processing, 2014, 22(4): 778-784.
[6] LANDECKER W, CHARTRAND R, DEDEO S. Robust sparse coding and compressed sensing with the difference map[C]//Proceedings of the 13th European conference on computer vision. Zurich, Switzerland, 2014: 315-329.
[7] GRAVES A, MOHAMED A R, HINTON G. Speech recognition with deep recurrent neural networks[C]//Proceedings of the IEEE international conference on acoustic speech and signal processing. Vancouver, British Columbia, Canada, 2013: 6645-6649.
[8] BRUNA J, SZLAM A, LECUN Y. Signal recovery from pooling representations[J]. Eprint Arxiv, 2013: 307-315.
[9] LI Haoxiang, LIN Zhe, SHEN Xiaohui, et al. A convolutional neural network cascade for face detection[C]//Proceedings of the 2015 IEEE conference on computer vision and pattern recognition. Boston, Massachusetts, USA, 2015: 5325-5334.
[10] GIRSHICK R, DONAHUE J, DARRELL T, et al. Rich feature hierarchies for accurate object detection and semantic segmentation[C]//Proceedings of the 2014 IEEE conference on computer vision and pattern recognition. Columbus, OH, USA, 2014: 580-587.
[11] LIN Min, CHEN Qiang, YAN Shuicheng. Network in network[C]//Proceedings of international conference on learning representations. Banff, Canada, 2014.
[12] GIONIS A, INDYK P, MOTWANI R. Similarity search in high dimensions via hashing[C]//Proceedings of the 25th international conference on very large data bases. San Francisco, CA, USA, 1999: 518-529.
[13] WEISS Y, TORRALBA A, FERGUS R. Spectral hashing[C]//Proceedings of conference on neural information processing systems. Vancouver, British Columbia, Canada, 2008: 1753-1760.
[14] KULIS B, DARRELL T. Learning to hash with binary reconstructive embeddings[C]//Advances in neural information processing systems 22: 23rd annual conference on neural information processing systems 2009. Vancouver, British Columbia, Canada, 2010: 1042-1050.
[15] RAGINSKY M, LAZEBNIK S. Locality-sensitive binary codes from shift-invariant kernels[C]//Advances in neural information processing systems 22: conference on neural information processing systems 2009. Vancouver, British Columbia, Canada, 2009: 1509-1517.
[16] GONG Yunchao, LAZEBNIK S, GORDO A, et al. Iterative quantization: a procrustean approach to learning binary codes for large-scale image retrieval[J]. IEEE transactions on pattern analysis and machine intelligence, 2013, 35(12): 2916-2929.
[17] NOROUZI M, FLEET D J. Minimal loss hashing for compact binary codes[C]// Proceedings of the 28th international conference on machine learning. Bellevue, WA, USA, 2011: 353-360.
[18] JIN Zhongming, LI Cheng, LIN Yue, et al. Density sensitive hashing[J]. IEEE transactions on cybernetics, 2014, 44(8): 1362-1371.
[19] KRIZHEVSKY A, SUTSKEVER I, HINTON G E. ImageNet classification with deep convolutional neural networks[C]//Advances in Neural Information Processing Systems 25. Lake Tahoe, Nevada, USA, 2012.
[20] DONAHUE J, JIA Yangqing, VINYALS O, et al. DeCAF: a deep convolutional activation feature for generic visual recognition[C]//Proceedings of the 31st international conference on machine learning. Beijing, China, 2014: 647-655.
[21] ZEILER M D, FERGUS R. Visualizing and Understanding Convolutional Networks[C]//Proceedings of the 13th European conference on computer vision. Zurich, Switzerland, 2014: 818-833.
[22] SERMANET P, EIGEN D, ZHANG Xiang, et al. OverFeat: integrated recognition, localization and detection using convolutional networks[J]. Eprint Arxiv, 2013.
[23] RAZAVIAN A S, AZIZPOUR H, SULLIVAN J, et al. CNN features off-the-shelf: an astounding baseline for recognition[C]//Proceedings of the 2014 IEEE conference on computer vision and pattern recognition workshops. Columbus, OH, USA, 2014: 512-519.
[24] XIA Rongkai, PAN Yan, LIU Cong, et al. Supervised hashing for image retrieval via image representation learning[C]//Proceedings of the 24th AAAI conference on artificial intelligence. Qubec City, Canada, 2014: 2156-2162.
[25] GUO Jinma, LI Jianmin. CNN Based Hashing for Image Retrieval[Z]. arXiv: 1509. 01354v1, 2015.
[26] LIN K, YANG H F, HSIAO J H, et al. Deep learning of binary hash codes for fast image retrieval[C]//Proceedings of the 2015 IEEE conference on computer vision and pattern recognition workshops (CVPRW). Boston, Massachusetts, USA, 2015: 27-35.
[27] ANDONI A, INDYK P. Near-optimal hashing algorithms for approximate nearest neighbor in high dimensions[C]//Proceedings of IEEE 54th annual symposium on foundations of computer science. Berkeley, CA, USA, 2006: 459-468.
[28] SIMONYAN K, ZISSERMAN A. Very deep convolutional networks for large-scale image recognition[J]. Eprint Arxiv, 2014.
[29] LI Feifei, FERGUS R, PERONA P. Learning generative visual models from few training examples: an incremental Bayesian approach tested on 101 object categories[J]. Computer vision and image understanding, 2007, 106(1): 59-70.
[30] GRIFFIN G, HOLUB A, PERONA P. Caltech-256 object category dataset[R]. CaltechAUTHORS: CNS-TR-2007-001, 2007.

相似文献/References:

[1]辛雨璇,闫子飞.基于手绘草图的图像检索技术研究进展[J].智能系统学报编辑部,2015,10(02):167.[doi:10.3969/j.issn.1673-4785.201401045]
 XIN Yuxuan,YAN Zifei.Research progress of image retrieval based on hand-drawn sketches[J].CAAI Transactions on Intelligent Systems,2015,10(3):167.[doi:10.3969/j.issn.1673-4785.201401045]
[2]陈阳,董肖莉,李卫军,等.基于仿生形象思维方法的图像检索算法的改进[J].智能系统学报编辑部,2015,10(02):209.[doi:10.3969/j.issn.1673-4785.201411022]
 CHEN Yang,DONG Xiaoli,LI Weijun,et al.Improvement of an image retrieval algorithm based on biomimetic imaginal thinking[J].CAAI Transactions on Intelligent Systems,2015,10(3):209.[doi:10.3969/j.issn.1673-4785.201411022]
[3]杨晓兰,强彦,赵涓涓,等.基于医学征象和卷积神经网络的肺结节CT图像哈希检索[J].智能系统学报编辑部,2017,12(06):857.[doi:10.11992/tis.201706035]
 YANG Xiaolan,QIANG Yan,ZHAO Juanjuan,et al.Hashing retrieval for CT images of pulmonary nodules based on medical signs and convolutional neural networks[J].CAAI Transactions on Intelligent Systems,2017,12(3):857.[doi:10.11992/tis.201706035]
[4]阿丽亚·巴吐尔,努尔毕亚·亚地卡尔,吾尔尼沙·买买提,等.改进SURF特征的维吾尔文复杂文档图像匹配检索[J].智能系统学报编辑部,2019,14(02):296.[doi:10.11992/tis.201709014]
 ALIYA Batur,NURBIYA Yadikar,HORNISA Mamat,et al.Complex Uyghur document image matching and retrieval based on modified SURF feature[J].CAAI Transactions on Intelligent Systems,2019,14(3):296.[doi:10.11992/tis.201709014]

备注/Memo

备注/Memo:
收稿日期:2016-3-17;改回日期:。
基金项目:国家自然科学基金项目(61462018);广西学位与研究生教育改革和发展专项课题(JGY2014060);广西数字传播与文化软实力中心开放项目(ZFZD1408008);广西高校图像图形智能处理重点实验室开放基金项目(LD15042X).
作者简介:龚震霆,男,1991年生,硕士研究生,主要研究方向为计算机视觉、机器学习。陈光喜,男,1971年生,博士生导师,主要研究方向为可信计算、图像处理。主持完成国家自然基金项目2项、广西省科学基金及企业开发项目多项。获桂林市科技进步三等奖1项、广西教学成果奖一等奖1项。发表学术论文30余篇,主编教材1部。任夏荔,女,1992年生,硕士研究生,主要研究方向为计算机视觉、深度学习。
通讯作者:龚震霆.E-mail:gongxs7@163.com.
更新日期/Last Update: 1900-01-01