收稿日期: 2016-04-26
修回日期: 2016-07-07
网络出版日期: 2016-11-30
基金资助
国家自然科学基金（No.61402152）；河南省高等学校控制工程重点学科开放实验室课题基金（No.KG2014-06）；河南理工大学博士基金（No.B2013-022）资助
Robust Image Hashing Based on Content Structure Diagram
Received date: 2016-04-26
Revised date: 2016-07-07
Online published: 2016-11-30
为提高拷贝检测系统的鲁棒性和效率，提出一种鲁棒图像哈希算法. 用Gabor变换系数构建图像内容结构图，将它从笛卡尔坐标系变换到极坐标系进行归一化. 将归一化的结构子图加权，求得特征向量，最后通过量化得到二值哈希码. 基于Gabor系数的内容结构图有很强的鲁棒性和独特性，量化中采用的失真哈希码融合和双密钥进一步提升了算法的鲁棒性、独特性、紧凑性. 利用公开数据库分别对所提出的算法和多种代表性算法进行对比实验，比较对象包括非负矩阵分解哈希、形状上下文哈希、圆环分割与不变向量距离哈希. 实验表明，该算法在查准率和查全率方面均表现突出，匹配效率也有大幅提升，整体性能优于对比算法.
李新伟, 夏秀珍 . 基于内容结构图的鲁棒图像哈希[J]. 应用科学学报, 2016 , 34(6) : 691 -701 . DOI: 10.3969/j.issn.0255-8297.2016.06.005
Robust image hashing is proposed for improving robustness and matching efficiency of copy detection system. Gabor transform coefficients of the image are used to construct structure diagrams. They are transformed from the Cartesian coordinates to polar coordinates, and normalized to obtain new diagrams. The weighted sum of their subblock pixels are calculated to obtain feature vectors, which are then quantized to produce the final binary hash codes. The structure diagrams based on Gabor coefficients proposed in this work are robust and distinctive. The distorted hash code fusion and double keys used in quantization further improve robustness, distinctiveness and compactness of the algorithm. The proposed method is compared with several representative image hashing approaches such as the non-negative matrix factorization hashing, radial and angular shape context hashing, ring partition and invariant vector distance hashing using a large image database. The results show that the overall performance of the proposed algorithm is significantly better than the other methods in terms of precision and recall rates, as well as matching efficiency.
[1] Venkatesan R, Koon S M, Jakubowski M H,Moulin P. Robust image hashing [C]//The IEEE International Conference on Image Processing (ICIP), 2000: 664-666.
[2] 闫允一,姜帅,郭宝龙.结合稳定兴趣点和Gabor小波的图像检索[J].西安电子科技大学学报,2014, 41(5): 118-123. Yan Y Y, Jiang S, Guo B L. Image retrieval using stable interest points and Gabor wavelet[J]. Journal of Xidian University, 2014, 41(5): 118-123. (in Chinese)
[3] Kozat S S, Venkatesan R, Mihcak M K. Robust perceptual image hashing via matrix invariants[C]//The IEEE International Conference Image Processing (ICIP), 2004: 3443-3446.
[4] Monga V, Mihcak M K. Robust and secure image hashing via nonnegative matrix factorizations
[J]. IEEE Transactions on Information and Forensics Security, 2007, 2(3): 376-390.
[5] Monga V, Evans B L. Perceptual image hashing via feature points: performance evaluation and tradeoffs [J]. IEEE Transaction on Image Processing, 2006, 15(11): 3452-3465.
[6] 刘兆庆,李琼,刘景瑞. 一种基于SIFT的图像哈希算法[J]. 仪器仪表学报,2011, 32(9): 2024-2028. Liu Z Q, Li Q, Liu J R. SIFT based image hashing algorithm [J]. Chinese Journal of Scientific Instrument, 2011, 32(9): 2024-2028. (in Chinese)
[7] 孙锐,闫晓星,高隽. 基于SIFT和PCA的图像感知哈希方法[J]. 电路与系统学报,2013, 18(1): 274-228. Sun R, Yan X X, Gao J. A perceptual image hashing method via SIFT and PCA [J]. Journal of Circuits and Systems, 2013, 18(1): 274-228. (in Chinese)
[8] Ling H F, Yan L Y, Zou F H, Liu C, Feng H. Fast image copy detection approach based on local fingerprint defined visual words [J]. Signal Processing, 2013, 93: 2328-2338.
[9] 林莹,杨扬,凌康. 多特征综合的视频拷贝检测[J]. 计算机辅助设计与图形学学报,2013, 18(5): 591-599. Lin Y, Yang Y, Ling K. Video copy detection based on multiple visual features synthesizing [J]. Journal of Image and Graphics, 2013, 18(5): 591-599. (in Chinese)
[10] Lü X D, Wang Z J. Perceptual image hashing based on shape contexts and local feature points [J]. IEEE Transactions on Information and Forensics Security, 2012, 7(3): 1081-1093.
[11] Li Y N, Lu Z M, Zhu C, Niu X M. Robust image hashing based on random Gabor filtering and dithered lattice vector quantization [J]. IEEE Transactions on Information and Forensics Security, 2012, 21(4): 1963-1980.
[12] Zhao Y, Wang S Z, Zhang X P, Yao H. Robust hashing for image authentication using Zernike moments and local features [J]. IEEE Transactions on Information and Forensics Security, 2013, 8(1): 55-63.
[13] Tang Z J, Zhang X Q, Zhang S C. Robust perceptual image hashing based on ring partition and NMF [J]. IEEE Transactions on Knowledge and Data Engineering, 2014, 26(3): 711-724.
[14] Tang Z J, Zhang X Q, Li X X, Zhang S C. Robust image hashing with ring partition and invariant vector distance [J]. IEEE Transactions on Information and Forensics Security, 2016, 11(1): 200-214.
[15] 师文,朱学芳. 基于轮廓重构和特征点弦长的图像检索[J]. 软件学报,2014, 25(7): 1557-1567. Shi W, Zhu X F. Image retrieval based on contour reconstruction and feature point chord length [J]. Journal of Software, 2014, 25(7): 1557-1567. (in Chinese)
[16] Liu C, Wechsler H. Gabor feature based classification using the enhanced fisher linear discriminant model for face recognition [J]. IEEE Transactions on Image Processing, 2002, 11 (4): 467-476.
[17] 刘帅师,田彦涛,万川. 基于Gabor多方向特征融合与分块直方图的人脸表情识别方法[J]. 自动化学报,2011, 37(12): 1455-1463. Liu S S, Tian Y T, Wan C. Facial expression recognition method based on Gabor multiorientation features fusion and block histogram [J]. Acta Automatic Sinica, 2011, 37(12): 1455-1463. (in Chinese)
[18] http://wang.ist.psu.edu/docs/related.shtml
/
| 〈 |
|
〉 |
