[1]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]
Copy

An image retrieval method based on a convolutional neural network and hash coding

CAAI Transactions on Intelligent Systems[ISSN 1673-4785/CN 23-1538/TP] Volume: 11 Number of periods: 2016 3 Page number: 391-400 Column: 学术论文—机器学习 Public date: 2016-06-25
Title:
An image retrieval method based on a convolutional neural network and hash coding
Author(s):
GONG Zhenting1; 2;  CHEN Guangxi1; 2;  REN Xiali1; 2;  CAO Jianshou1; 2
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
Keywords:
image retrieval; artificial features; convolutional neural network; convolutional features; hash coding
CLC:
TP391
DOI:
10.11992/tis.201603028
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.
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.
Similar References:

Memo

-

Last Update: 1900-01-01

Copyright © CAAI Transactions on Intelligent Systems