基于改进哈希算法的图像检索方法

doi:10.16180/j.cnki.issn1007-7820.2020.05.005

电子科技 ›› 2020, Vol. 33 ›› Issue (5): 28-32.doi: 10.16180/j.cnki.issn1007-7820.2020.05.005

基于改进哈希算法的图像检索方法

陆超文,李菲菲,陈虬

上海理工大学光电信息与计算机工程学院,上海 200093

收稿日期:2019-03-30 出版日期:2020-05-15 发布日期:2020-06-02
作者简介:陆超文(1994-),男,硕士研究生。研究方向:图像处理与模式识别。|李菲菲(1970-),女,博士,教授。研究方向:多媒体信息处理,图像处理与模式识别,信息检索等。|陈虬(1972-),男,博士,教授,博士生导师。研究方向:图像处理与模式识别,计算机视觉,信息检索等。
基金资助:
上海市高校特聘教授(东方学者)岗位计划(ES2015XX)

An Image Retrieval Algorithm Based on Improved Hashing Method

LU Chaowen,LI Feifei,CHEN Qiu

School of Optical-Electrical and Computer Engineering,University of Shanghai for Science and Technology,Shanghai 20093,China

Received:2019-03-30 Online:2020-05-15 Published:2020-06-02
Supported by:
Research supported by The Program for Professor of Special Appointment (Eastern Scholar) at Shanghai Institutions of Higher Learning(ES2015XX)

摘要/Abstract

摘要：

当前主流图像检索技术所采用的传统视觉特征编码缺少足够的学习能力,影响学习得到的特征表达能力。此外,由于视觉特征维数高,会消耗大量的内存,因此降低了图像检索的性能。文中基于深度卷积神经网络与改进的哈希算法,提出并设计了一种端到端训练方式的图像检索方法。该方法将卷积神经网络提取的高层特征和哈希函数相结合,学习到具有足够表达能力的哈希特征,从而在低维汉明空间中完成对图像数据的大规模检索。在两个常用数据集上的实验结果表明,所提出的哈希图像检索方法的检索性能优于当前的一些主流方法。

关键词: 图像检索, 卷积神经网络, 哈希算法, 视觉特征, 汉明空间, 特征编码, 特征维度

Abstract:

The coding methods of the traditional visual features adopted in current image retrieval approaches lack sufficient learning ability and have no strong feature expression ability.In addition, due to the high dimensionality of visual features, a large amount of memory is consumed, thus reducing the performance of image retrieval. In this paper, an image retrieval algorithm with end-to-end training based on deep and improved hashing method was proposed and designed. The proposed algorithm combined the high-level features extracted by CNN with Hash function and learned Hash codes with expression ability to perform large-scale image retrieval in low-dimensional Hamming space. The experimental results on two main datasets showed that the retrieval performance of the proposed method was superior to that of some state-of-the-art ones.

Key words: image retrieval, convolutional neural network, Hashing method, visual feature, Hamming space, feature coding, feature dimension

中图分类号:

TP391

陆超文,李菲菲,陈虬. 基于改进哈希算法的图像检索方法[J]. 电子科技, 2020, 33(5): 28-32.

LU Chaowen,LI Feifei,CHEN Qiu. An Image Retrieval Algorithm Based on Improved Hashing Method[J]. Electronic Science and Technology, 2020, 33(5): 28-32.

图/表 5

图1

图2

表1

图3

图4

参考文献 17

[1]	Alexandr A, Piotr I. Near-optimal Hashing algorithms for approximate nearest neighbor in high dimensions [C]. Berkeley:IEEE Symposium on Foundations of Computer Science, 2006.
[2]	Weiss Y, Torralba A, Fergus R. Spectral Hashing [C]. Auckland:International Conference on Neural Information Processing Systems, 2008.
[3]	Gong Y, Lazebnik S. Iterativequantization:A procrustean approach to learning binary codes [C]. Washington:Computer Vision & Pattern Recognition, 2011.
[4]	Kulis B, Darrell T. Learning to Hash with binary reconstructive embeddings [C]. Vancouver:Proceedings of the 23^rd Annual Conference on Neural Information Processing Systems, 2009.
[5]	Norouzi M E, Fleet D J. Minimal loss Hashing for compact binary codes [C]. Washington:Proceedings of the 28 ^th International Conference on Machine Learning , 2011.
[6]	Chang S F, Jiang Y G, Ji R, et al. Supervised Hashing with kernels [C]. Providence:IEEE Conference on Computer Vision and Pattern Recognition, 2012.
[7]	Oliva A, Torralba A . Modeling the shape of the scene:a holistic representation of the spatial envelope[J]. International Journal of Computer Vision, 2001,42(3):145-175.
[8]	Xia R, Pan Y, Lai H, et al. Supervised Hashing for image retrieval via image representation learning [C]. Quebec:Proceedings of the AAAI Conference on Artificial Intelligence, 2014.
[9]	Lai H, Pan Y, Liu Y, et al. Simultaneous feature learning and Hash coding with deep neural networks [C]. Boston: IEEE Conference on Computer Vision and Pattern Recognition, 2015.
[10]	Zhao F, Huang Y, Wang L, et al. Deep semantic ranking based Hashing for multi-label image retrieval [C]. Boston:IEEE Conference on Computer Vision and Pattern Recognition, 2015.
[11]	Zhang R, Lin L, Zhang R , et al. Bit-scalable deep Hashing with regularized similarity learning for image retrieval and person re-identification[J]. IEEE Transactions on Image Processing, 2015,24(12):4766-4779.
[12]	Wang X, Shi Y, Kitani K M. Deep supervised Hashing with triplet labels [C]. Taipei:13^th Asian Conference on Computer Vision, 2016.
[13]	Zhou Y, Huang S, Zhang Y, et al. Deep Hashing with triplet quantization loss [C]. St.Petersburg:IEEE International Conference on Visual Communications and Image Processing, 2017.
[14]	Yang N D, Xie N H, Yin N J, et al. Supervised deep quantization for efficient image search [C]. Hong Kong: IEEE International Conference on Multimedia & Expo Workshops, 2017.
[15]	Cao Z, Long M, Wang J, et al. HashNet:deep learning to Hash by continuation [C]. Venice:IEEE International Conference on Computer Vision, 2017.
[16]	Li Y, Miao Z, Wang J , et al. Deep binary constraint Hashing for fast image retrieval[J]. Electronics Letters, 2018,54(1):25-27.
[17]	王伟栋, 李菲菲, 谢林 , 等. 基于深度神经网络和哈希算法的图像检索研究[J]. 电子科技, 2018,31(10):52-56.
	Wang Weidong, Li Feifei, Xie Lin , et al. Study on image retrieval based on deep neural networks and Hashing algorithm[J]. Electronic Science and Technology, 2018,31(10):52-56.

算法	MNIST				CIFAR10
算法	12位	24位	32位	48位	12位	24位	32位	48位
Ours(with BN)	0.973	0.980	0.979	0.985	0.541	0.595	0.589	0.599
Ours(withoutBN)	0.963	0.978	0.982	0.956	0.511	0.470	0.496	0.494
DHN	N/A				0.555	0.594	0.603	0.621
DNNH	N/A				0.552	0.566	0.558	0.581
CNNH+	0.969	0.975	0.971	0.975	0.465	0.521	0.521	0.532
CNNH	0.957	0.963	0.956	0.960	0.439	0.511	0.509	0.522
KSH	0.872	0.891	0.897	0.900	0.303	0.337	0.346	0.356
ITQ-CCA	0.659	0.694	0.714	0.726	0.264	0.282	0.288	0.295
MLH	0.472	0.666	0.652	0.654	0.182	0.195	0.207	0.211
BRE	0.515	0.593	0.613	0.634	0.159	0.181	0.193	0.196
SH	0.265	0.267	0.259	0.250	0.131	0.135	0.133	0.130
ITQ	0.388	0.436	0.422	0.429	0.162	0.169	0.172	0.175
LSH	0.187	0.209	0.235	0.243	0.121	0.126	0.120	0.120

基于改进哈希算法的图像检索方法

An Image Retrieval Algorithm Based on Improved Hashing Method

RichHTML

PDF (PC)

赞

可视化

摘要/Abstract

引用本文

使用本文

图/表 5

参考文献 17

相关文章 15

Metrics

本文评价

推荐阅读 10

[1]	李辉,王一丞. 基于CNNCIFG-Attention模型的文本情感分类[J]. 电子科技, 2022, 35(2): 46-51.
[2]	程晓雅,张雷. 基于深度学习的有遮挡人脸识别方法研究[J]. 电子科技, 2022, 35(1): 35-39.
[3]	战荫伟,朱百万,杨卓. 一种车脸识别算法的研究与应用[J]. 电子科技, 2021, 34(8): 1-7.
[4]	廖璐明,张伟. 基于改进VGG16网络的混合批量训练交通标志识别[J]. 电子科技, 2021, 34(8): 8-13.
[5]	马立新,豆晨飞,宋晨灿,杨天笑. 基于特征融合卷积神经网络的绝缘子无损检测[J]. 电子科技, 2021, 34(7): 26-30.
[6]	顾伟,李菲菲,陈虬. 基于多特征融合的行人检测方法[J]. 电子科技, 2021, 34(5): 29-34.
[7]	薛永杰,巨志勇. 基于改进AlexNet的鱼类识别算法[J]. 电子科技, 2021, 34(4): 12-17.
[8]	闫书豪,乔美英. 基于一维WConv-BiLSTM的轴承故障诊断算法[J]. 电子科技, 2021, 34(4): 75-82.
[9]	葛靖,刘子龙. 基于CNN和LSTM的睡眠呼吸暂停检测算法[J]. 电子科技, 2021, 34(2): 21-26.
[10]	朱斌,刘子龙. 基于新型初始模块的卷积神经网络图像分类方法[J]. 电子科技, 2021, 34(2): 52-56.
[11]	张灿,陈玮,尹钟. 基于弱监督宫颈细胞图像的语义分割方法[J]. 电子科技, 2021, 34(12): 68-74.
[12]	张莹,刘子龙,万伟. 基于Faster R-CNN的无人机车辆目标检测[J]. 电子科技, 2021, 34(11): 11-20.
[13]	李诚,刘昊,蒋希峰,吴军法,韩文刚,高建国. 基于VGG网络的发电机定转子智能诊断算法[J]. 电子科技, 2021, 34(11): 62-66.
[14]	董波,周燕,王永雄. 基于渐进结构感受野和全局注意力的显著性检测[J]. 电子科技, 2021, 34(1): 23-30.
[15]	张翔,史志才,陈良. 基于SWA优化级联网络的表情识别方法[J]. 电子科技, 2020, 33(9): 16-20.