基于尺度不变特征变换的快速图像拷贝检测

doi:10.11772/j.issn.1001-9081.2017.12.3447

计算机应用 ›› 2017, Vol. 37 ›› Issue (12): 3447-3451.DOI: 10.11772/j.issn.1001-9081.2017.12.3447

基于尺度不变特征变换的快速图像拷贝检测

郑丽君¹, 李新伟^1,2, 卜旭辉¹

1. 河南理工大学电气工程与自动化学院, 河南焦作 454000;
2. 河南省高等学校控制工程重点学科开放实验室, 河南焦作 454000

收稿日期:2017-06-12 修回日期:2017-08-28 出版日期:2017-12-10 发布日期:2017-12-18
通讯作者: 李新伟
作者简介:郑丽君(1993-),女,河南郑州人,硕士研究生,主要研究方向:图像分析与处理;李新伟(1983-),男,河南南阳人,讲师,博士,主要研究方向:图像哈希、视频指纹、多媒体信息;卜旭辉(1981-),男,河南商丘人,副教授,博士生导师,博士,主要研究方向:数据驱动控制、智能信息处理。
基金资助:
国家自然科学基金资助项目（61402152，61403130）；河南省高等学校控制工程重点学科开放实验室课题项目（KG2014-06）；河南理工大学博士基金资助项目（B2013-022）。

Scale invariant feature transform-based fast image copy detection

ZHENG Lijun¹, LI Xinwei^1,2, BU Xuhui¹

1. School of Electrical Engineering and Automation, Henan Polytechnic University, Jiaozuo Henan 454000, China;
2. Key Laboratory of Control Engineering of Henan Province, Jiaozuo Henan 454000, China

Received:2017-06-12 Revised:2017-08-28 Online:2017-12-10 Published:2017-12-18
Supported by:
This work is partially supported by the National Natural Science Foundation of China (61402152,61403130), the Key Laboratory of Control Engineering of Henan Province (KG2014-06), the Doctoral Funds for the Henan Polytechnic University (B2013-022).

摘要/Abstract

摘要： 针对传统基于尺度不变特征变换（SIFT）特征的图像拷贝检测算法特征提取速度慢、匹配效率不高的问题，提出了一种基于SIFT特征点位置分布与方向分布特征的快速图像拷贝检测算法。首先，提取SIFT特征点二维位置信息，通过计算各个特征点与图像中心点的距离、角度，分块统计各区间的特征点数量，依据数量关系量化生成二值哈希序列，构成一级鲁棒特征；然后，根据特征点一维方向分布特征分块统计各方向子区间特征点数量，依据数量关系构成二级图像特征；最后，拷贝检测时采用级联式过滤框架作出是否为拷贝的判断。仿真实验结果表明，与传统SIFT以128维特征描述子为基础构建哈希序列的图像拷贝检测算法相比，所提算法在保证鲁棒性与独特性不降低的同时，特征提取时间缩短为原来的1/20，匹配时间也缩短了1/2以上，可满足在线拷贝检测的需求。

关键词: 拷贝检测, 图像哈希, 尺度不变特征变换, 级联检索, 分布特征

Abstract: Focusing on the problems of low feature extraction speed and low matching efficiency of the traditional image copy detection algorithm based on Scale Invariant Feature Transform (SIFT) feature, a fast image copy detection algorithm based on location distribution and orientation distribution features of SIFT feature points was proposed. Firstly, the two-dimensional location information of SIFT feature points was extracted. The number of feature points in each interval was counted with block statistics by calculating the distance and angle between each feature point and image center point. The binary hash sequence was generated to construct the first order robust feature according to the quantitative relationship. Then, the numbers of sub-interval feature points in all directions were counted with block statistics according to the one-dimensional direction distribution feature of feature points, and the secondary image feature was constructed according to the quantitative relationship. Finally, a cascade filter framework was used in the copy detection to make a judgement about whether the copy or not. The simulation experimental results show that, compared with the traditional copy detection algorithm which constructs the hash sequence based on the SIFT feature with 128-dimensional descriptor, the feature extraction time of the proposed algorithm is shortened to the original 1/20, and the matching time is also reduced by more than 1/2. Therefore the proposed algorithm meet the requirement of online copy detection.

Key words: copy detection, image hash, Scale Invariant Feature Transform (SIFT), cascade search, distribution feature

中图分类号:

TP391.41

郑丽君, 李新伟, 卜旭辉. 基于尺度不变特征变换的快速图像拷贝检测[J]. 计算机应用, 2017, 37(12): 3447-3451.

ZHENG Lijun, LI Xinwei, BU Xuhui. Scale invariant feature transform-based fast image copy detection[J]. Journal of Computer Applications, 2017, 37(12): 3447-3451.

参考文献

[1] 余艳伟,周学海,许华杰.用于拷贝检测的鲁棒图像特征提取方法[J].武汉大学学报(理学版),2013,59(1):87-92.(YU Y W, ZHOU X H, XU H J. A robust feature extraction scheme in image copy detection[J]. Journal of Wuhan University (Natural Science Edition), 2013, 59(1):87-92.)
[2] 刘炜,欧阳建权,李泽洲,等.运用边缘方向直方图进行图像拷贝检测[J].计算机工程与应用,2010,46(31):184-187.(LIU W, OUYANG J Q, LI Z Z, et al. Edge histogram-based image copy detection algorithm[J]. Computer Engineering and Applications, 2010, 46(31):184-187.)
[3] 邹复好,李晓威,许治华,等.抗旋转和等比缩放失真的图像拷贝检测技术[J].计算机研究与发展,2009,46(8):1349-1356.(ZOU F H, LI X W, XU Z H, et al. Image copy detection with rotation and scaling tolerance[J]. Journal of Computer Research and Development, 2009, 46(8):1349-1356.)
[4] KIM C. Content-based image copy detection[J]. Signal Processing:Image Communication, 2003, 18(3):169-184.
[5] MONGA V, MIHCAK M K. Robust and secure image hashing via non-negative matrix factorization[J]. IEEE Transactions on Information Forensics and Security, 2007, 2(3):376-390.
[6] 王瑞,郝娜,张波,等.一种自适应Harris角点检测算法[J].火力与指挥控制,2015,40(7):84-86.(WANG R, HAO N, ZHANG B, et al. Harris corners detection method based on self-adapting non-maximal suppression algorithm[J]. Fire Control & Command Control, 2015, 40(7):84-86.)
[7] 刘兆庆,李琼,刘景瑞,等.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, et al. SIFT based image hashing algorithm[J]. Chinese Journal of Scientific Instrument, 2011, 32(9):2024-2028.)
[8] 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):274-278.(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):274-278.)
[9] LOWE D G. Distinctive image features from scale-invariant keypoints[J]. International Journal of Computer Vision, 2004, 60(2):91-110.
[10] KE Y, SUKTHANKAR R. PCA-SIFT:a more distinctive representation for local image descriptors[C]//Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Piscataway, NJ:IEEE, 2004:506-513.
[11] 颜雪军,赵春霞,袁夏.2DPCA-SIFT:一种有效的局部特征描述方法[J].自动化学报,2014,40(4):675-682.(YAN X J, ZHAO C X, YUAN X. 2DPCA-SIFT:an efficient local feature descriptor[J]. Acta Automatica Sinica, 2014, 40(4):675-682.)
[12] LYU X D, WANG Z J. Perceptual image hashing based on shape contexts and local feature points[J]. IEEE Transactions on Information Forensics and Security, 2012, 7(3):1081-1093.
[13] 许佳佳,张叶,张赫.基于改进Harris-SIFT算子的快速图像配准算法[J].电子测量与仪器学报,2015,29(1):48-54.(XU J J, ZHANG Y, ZHANG H. Fast image registration algorithm based on improved Harris-SIFT descriptor[J]. Journal of Electronic Measurement and Instrumentation, 2015, 29(1):48-54.)
[14] LING H F, YAN L Y, ZOU F H, et al. Fast image copy detection approach based on local fingerprint defined visual words[J]. Signal Processing, 2013, 93(8):2328-2338.
[15] 张春美.特征点提取及其在图像匹配中的应用研究[D].郑州:信息工程大学,2008:10.(ZHANG C M. Study on feature point detecting and its application to image matching[D]. Zhengzhou:Information Engineering University, 2008:10.)
[16] MIKOLAJCZYK K, SCHMID C. Performance evaluation of local descriptors[J]. IEEE Transaction on Pattern Analysis & Machine Intelligence, 2005, 27(10):1615-1630.

基于尺度不变特征变换的快速图像拷贝检测

Scale invariant feature transform-based fast image copy detection

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	胡立华, 左威健, 聂瑶瑶. 基于加权相似性度量的特征匹配方法[J]. 计算机应用, 2021, 41(2): 511-516.
[2]	薄单, 李宗春, 王晓南, 乔涵文. 适用于倾斜影像的加速KAZE-SIFT特征提取算法[J]. 计算机应用, 2019, 39(7): 2093-2097.
[3]	杨春德, 成燕菲. 基于拼接缝自适应消除和全景图矫直的快速图像拼接算法[J]. 计算机应用, 2019, 39(10): 3053-3059.
[4]	李加亮, 蒋品群. 结合变形函数和幂函数权重的图像拼接[J]. 计算机应用, 2019, 39(10): 3060-3064.
[5]	陈虹, 肖越, 肖成龙, 宋好. 基于SIFT算子融合最大相异系数的自适应图像匹配算法[J]. 计算机应用, 2018, 38(5): 1410-1414.
[6]	魏雨汐, 伍岳庆, 陶攀, 姚宇. 基于监督下降方法的左心室超声图像分割[J]. 计算机应用, 2018, 38(2): 545-549.
[7]	马新军, 吴晨晨, 仲乾元, 李园园. 基于SIFT的说话人唇动识别[J]. 计算机应用, 2017, 37(9): 2694-2699.
[8]	陈淑琴, 李智, 程欣宇, 高奇. 人眼视觉特性与SIFT相结合的视频双水印算法[J]. 计算机应用, 2017, 37(7): 1936-1942.
[9]	姬丽娜, 陈庆奎, 陈圆金, 赵德玉, 方玉玲, 赵永涛. 基于GPU的视频流人群实时计数[J]. 计算机应用, 2017, 37(1): 145-152.
[10]	陈娟娟, 刘财兴, 高月芳, 梁云. 基于改进特征袋模型的奶牛识别算法[J]. 计算机应用, 2016, 36(8): 2346-2351.
[11]	许川佩, 王光. 基于OpenCL的尺度不变特征变换算法的并行设计与实现[J]. 计算机应用, 2016, 36(7): 1801-1806.
[12]	吴伟, 丁香乾, 闫明. 基于异常区域感知的多时相高分辨率遥感图像配准[J]. 计算机应用, 2016, 36(10): 2870-2874.
[13]	毛文涛, 王文朋, 蒋梦雪, 欧阳军. 基于局部特征过滤的快速火焰图像识别方法[J]. 计算机应用, 2016, 36(10): 2907-2911.
[14]	赵霞, 朱庆, 肖雄武, 李德仁, 郭丙轩, 张鹏, 胡翰, 丁雨淋. 基于同形变换的航空倾斜影像自动匹配方法[J]. 计算机应用, 2015, 35(6): 1720-1725.
[15]	姬晓飞, 秦宁丽. 光学遥感图像多目标检测及识别算法设计与实现[J]. 计算机应用, 2015, 35(11): 3302-3307.