论文:2012,Vol:30,Issue(2):291-295
引用本文:
高芳, 郑江滨, 蔡里宁 . 基于 NSCT 变换和图像质量评价的拼接图像检测[J]. 西北工业大学
Gao Fang, Zheng Jiangbin, Cai Lining . An Effective Method for Blind Detection of Image Splicing with Nonsubsampled Contourlet Transform and Image Quality Evaluation[J]. Northwestern polytechnical university

基于 NSCT 变换和图像质量评价的拼接图像检测
高芳, 郑江滨, 蔡里宁
1. 西北工业大学 计算机学院,陕西 西安 710072;
2. 61938 部队,陕西 西安 710072
摘要:
基于 NSCT 的多分辨率、 局域化、 各向异性、 平移不变性等特性, 文章提出一种新的拼接图像检测方法, 利用 NSCT 和图像质量评价提取出多维图像矩特征以捕获原始图像与伪造图像间的差异,最后利用 SVM 分类器对图像库进行训练和测试, 得到了较好的试验结果。与同类方法相比文中运用了较少的特征向量维数达到了拼接检测目的。
关键词:    NSCT    SVM    统计特征量    图像质量评价   
An Effective Method for Blind Detection of Image Splicing with Nonsubsampled Contourlet Transform and Image Quality Evaluation
Gao Fang, Zheng Jiangbin, Cai Lining
1. Department of Computer Science and Engineering,Northwestern Polytechnical University,Xi'an 710072,China;
2. 61938 Troops,Xi'an 710072,China
Abstract:
Nonsubsampled contourlet transform (NSCT) has multi-resolution, location, anisotropy, translation in-variance and other characteristics. Sections 1 and 2 of the full paper explain the method of detection mentioned inthe title. Their core consists of: (1) we utilize the statistical properties of an image and its quality evaluation to ex-tract its features, thus capturing the differences between original image and fake image; (2) for the statistical prop-erties, we use image blocks to obtain the coefficient matrices with the NSCT; we evaluate the image quality with theblock effects. Section 3 uses the support vector machine to train and test the image splicing. The test results, givenin Tables 1 and 2, and their analysis show preliminarily that, compared with other detection methods, our detectionmethod can indeed effectively reduce the number of dimensions of the statistical properties and the computationalcomplexity.
Key words:    analysis    algorithms    anisotropy    classification (of information)    computational complexity    errors    e-valuation    experiments    feature extraction    image processing    sampling    statistics;nonsubsampledcontourlet transform (NSCT)    support vector machine    image quality assessment    transform   
收稿日期: 2011-05-12     修回日期:
DOI:
基金项目: 西北工业大学研究生创业种子基金(2011-2012)资助
通讯作者:     Email:
作者简介: 高芳(1987-),女,西北工业大学硕士研究生,主要从事图像处理与信息安全研究。
相关功能
PDF(724KB) Free
打印本文
把本文推荐给朋友
作者相关文章
高芳  在本刊中的所有文章
郑江滨  在本刊中的所有文章
蔡里宁  在本刊中的所有文章

参考文献:
[1] Minh N Do, Martin Vetterli. The Contourlet Transform:An Efficient Directional Multiresolution Image Representation. IEEETrans on Image Processing, 2005, 14: 2091-2106
[2] Zhou Jianping, Arthur L Cunha, Minh N Do. Nonsampled Contourlet Transform: Constraction and Application in Enhancement.Department of Electrical and Computer Engineering University of Illinois at Urbana-Champaign, 2005
[3] Hou Wang, Hamid R Sheikh, Alan C Bovik. No-Reference Perceptual Quality Assessment of JPEG Compressed Images. The U-niversity of Texas at Austin, USA, 2002
[4] Wang Z, Bovik A C, Evans B L. Blind Measurement of Blocking Artifacts in Images. IEEE Trans on Image Procesing, 2000, 3: 981-984
[5] Suykens J A K, Vandewalle J. Least Squares Support Vector Machine Classifiers. Neural Processing Letters, 1999, 293-300
[6] Ng Tiantsong, Chang Shihfu. A Data Set of Authentic and Spliced Image Blocks. Electrical Engineering Department ColumbiaUniversity, New York, 2004