Unsupervised Hashing algorithm based on sparse autoencoder

Li-ping ZHANG; Wei-ping MENG; Jia-hai TAN

doi:10.3788/YJYXS20183311.0950

您当前的位置：

首页 >

文章列表页 >

Unsupervised Hashing algorithm based on sparse autoencoder

Image Processing | 更新时间：2020-08-12

- Unsupervised Hashing algorithm based on sparse autoencoder
- Chinese Journal of Liquid Crystals and Displays Vol. 33, Issue 11, Pages: 950-957(2018)
- 作者机构：
  
  1.陕西国际商贸学院, 陕西西安 712046
  2.中国科学院西安光学精密机械研究所, 陕西西安 710119
- 作者简介：
- 基金信息：
- DOI：10.3788/YJYXS20183311.0950
  CLC： O431.2;O431.1
- Received：20 June 2018，
  
  Accepted：09 July 2018，
  
  Published：05 November 2018
- 稿件说明：
移动端阅览
Li-ping ZHANG, Wei-ping MENG, Jia-hai TAN. Unsupervised Hashing algorithm based on sparse autoencoder[J]. Chinese journal of liquid crystals and displays, 2018, 33(11): 950-957.
DOI：

Li-ping ZHANG, Wei-ping MENG, Jia-hai TAN. Unsupervised Hashing algorithm based on sparse autoencoder[J]. Chinese journal of liquid crystals and displays, 2018, 33(11): 950-957. DOI： 10.3788/YJYXS20183311.0950.

摘要

最近邻搜索在大规模图像检索中变得越来越重要。在最近邻搜索中，许多哈希方法因为快速查询和低内存被提出。然而，现有方法在哈希函数构造过程中对数据稀疏结构研究的不足，本文提出了一种无监督的稀疏自编码的图像哈希方法。基于稀疏自编码的图像哈希方法将稀疏构造过程引入哈希函数的学习过程中，即通过利用稀疏自编码器的KL距离对哈希码进行稀疏约束以增强局部保持映射过程中的判别性，同时利用L2范数来哈希编码的量化误差。实验中用两个公共图像检索数据集CIFAR-10和YouTube Faces验证了本文算法相比其他无监督哈希算法的优越性。

Abstract

Nearest neighbor search is becoming more and more important in large scale image retrieval.Many hash methods are proposed in nearest neighbor search owing to fast query and low memory. However

there is a lack of research on the sparse structure of data in the process of hash function construction. The proposed hashing method introduces the sparse construction process into the learning process of hash function and uses KL distance of sparse autoencoder on hash code sparse constraints to enhance locality preserving discriminant mapping process. The proposed method leverages L2 norm to control quantization error in hash encoding. The experimental results on two common image retrieval datasets CIFAR-10 and YouTube Faces show that the proposed algorithm is superior to other unsupervised hashing algorithms.

关键词

Keywords

references

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

UHLMANN J K. Satisfying general proximity/similarity queries with metric trees[J]. Information Processing Letters , 1991, 40(4):175-179.

JÉGOU H, DOUZE M, SCHMIDC. Product quantization for nearest neighbor search[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence , 2010, 33(1):117-128.

KULIS B, DARRELL T. Learning to hash with binary reconstructive embeddings[C]// Advances in Neural Information Processing Systems . Vancouver: NIPS, 2009: 1042-1050.

NOROUZI M E, FLEET DJ. Minimal loss hashing for compact binary codes[C]// Proceedings of the 28th International Conference on Machine Learning . Bellevue: ICML, 2011: 353-360.

GIONIS A, INDYK P, MOTWANIR. Similarity search in high dimensions via hashing[C]// Proceedings of the 25th International Conference on Very Large Data Bases . San Francisco: Morgan Kaufmann, 1999: 518-529.

WEISS Y, TORRALBA A, FERGUS R. Spectral hashing[C]// Proceedings of the 21st International Conference on Neural Information Processing Systems . Vancouver: Curran Associates Inc., 2008: 1753-1760.

GONG Y C, 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.

王丽杰, 杨羽翼.利用主成分权重重置实现牛奶成分浓度快速检测中近红外光谱的净化去噪[J].光学学报, 2017, 37(10):1030003.

WANG L J, YANG Y Y. Purification and noise elimination of near infrared spectrum in rapid detection of milk components concentration by using principal component weight resetting[J]. Acta Optica Sinica , 2017, 37(10):1030003. (in Chinese)

XU J, XIANG L, LIUQ, et al . Stacked Sparse Autoencoder (SSAE) for nuclei detection on breast cancer histopathology images[J]. IEEE Transactions on Medical Imaging , 2015, 35(1):119-130.

YUAN Y, LU X Q, LI X L. Learning hash functions using sparse reconstruction[C]// Proceedings of 2014 International Conference on Internet Multimedia Computing & Service . Xiamen: ACM, 2014: 14.

KRIZHEVSKY A. Learning multiple layers of features from tiny images[D]. Toronto: Computer Science Department, University of Toronto, 2009.

WOLF L, HASSNER T, MAOZI. Face recognition in unconstrained videos with matched background similarity[C] Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition . Colorado Springs: IEEE, 2011: 529-534.

JIANG Q Y, LI W J. Scalable graph hashing with feature transformation[C]// Proceedings of the 24th International Conference on Artificial Intelligence . Buenos Aires: AAAI Press, 2015: 2248-2254.

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

SONG D J, LIU W, JI R R, et al . Top rank supervised binary coding for visual search[C]// Proceedings of 2015 IEEE International Conference on Computer Vision . Santiago: IEEE, 2015: 1922-1930.

HE K M, WEN F, SUN J. K-means hashing: an affinity-preserving quantization method for learning binary compact codes[C]// Proceedings of 2013 IEEE Conference on Computer Vision and Pattern Recognition . Portland: IEEE, 2013: 2938-2945.

LIONG V E, LU J W, WANG G, et al . Deep hashing for compact binary codes learning[C]// Proceedings of 2015 IEEE Conference on Computer Vision and Pattern Recognition . Boston: IEEE, 2015: 2475-2483.

张智丰, 裴志利.一种稳健的紧凑图像哈希算法[J].激光与光电子学进展, 2017, 54(10):101002.

ZHANG Z F, PEI ZL. A robust compact image hash algorithm[J]. Laser & Optoelectronics Progress , 2017, 54(10):101002. (in Chinese)

王彦超, 郭静博, 周丽宴.基于数据投影降维机制与对称局部二值模式的紧凑图像哈希算法[J].激光与光电子学进展, 2017, 54(2):138-149.

WANG Y C, GUO J B, ZHOUL Y. The compact image hash algorithm based on the data projection and the symmetric local two value mode[J]. Laser & Optoelectronics Progress , 2017, 54(2):138-149. (in Chinese)

SUI L S, ZHANG X, TIAN A L. Optical multiple-image authentication scheme based on the phase retrieval algorithm in gyrator domain[J]. Journal of Optics , 2017, 19(5):055702.

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

No data

Related Author

No data

Related Institution

No data

AI问答

Address：No.3888 Dong Nanhu Road, Changchun, Jilin, China 130033 Postal code：130033
Tel：0431-86176059 Email：yjxs@ciomp.ac.cn
Technical support is provided by Beijing Founder electronics co., LTD 吉ICP备11002662号-17 京公网安备11010802024621
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰