上海交通大学学报(自然版) ›› 2011, Vol. 45 ›› Issue (10): 1547-1551.

• 自动化技术、计算机技术 • 上一篇    下一篇

基于图片DCT域共生矩阵的图像拼接盲检测

陈古春a,苏波b,王士林b,李生红a   

  1. (上海交通大学 a.电子工程系; b.信息安全工程学院,上海 200240)
  • 收稿日期:2010-10-26 出版日期:2011-10-31 发布日期:2011-10-31
  • 基金资助:

    国家重点基础研究发展计划(973项目)(2010CB731403,2010CB731406),国家自然科学基金项目(61071152),上海市教育发展基金会晨光计划(2008CG15)资助

Blind Detection of Splicing Image Based on Gray Level Co-occurrence Matrix of Image DCT Domain

 CHEN  Gu-Chun-a, SU  Bo-b, WANG  Shi-Lin-b, LI  Sheng-Hong-a   

  1. (a.Department of Electronic Engineering; b.School of Information Security Engineering,Shanghai Jiaotong University, Shanghai 200240, China)
  • Received:2010-10-26 Online:2011-10-31 Published:2011-10-31

摘要: 通过对图像拼接技术的分析,提出了一种基于灰度共生矩阵的拼接图像检测算法.该算法把离散余弦变换(DCT)与灰度共生矩阵结合,计算图片DCT域上的灰度共生矩阵,将共生矩阵作为特征向量,采用特征提取分类方法,利用支持向量机(SVM)分类器进行分类预测.实验结果表明,该算法在哥伦比亚大学灰度图片库和中国科学院彩色图片库上达到了91.2%和98.5%的最高检测准确率.

关键词: 拼接图像检测, 分块离散余弦变换, 灰度共生矩阵, 支持向量机

Abstract: Through analysis on the characteristic of image splicing,a new image splicing blind detection approach was proposed. It extracts the gray level cooccurrence matrix(GLCM)based on the thresholded DCT coefficients of the image. The gray level cooccurrence matrixes along the four directions serve as feature vector for image splicing detection. Support vector machine(SVM)is utilized as the classifier in the proposed method. The experimental results indicate that this new scheme can achieve the accuracy of 91.2% and 98.5% on gray image dataset of Columbia University and color image dataset of Chinese academy of sciences (CAS) respectively.

Key words:  , image splicing detection; multi block discrete cosine transform (DCT); gray level cooccurrence matrix; support vector machine (SVM)

中图分类号: