计算机应用 ›› 2017, Vol. 37 ›› Issue (10): 2903-2906.DOI: 10.11772/j.issn.1001-9081.2017.10.2903

• 计算机视觉与虚拟现实 • 上一篇    下一篇

基于颜色分量间相关性的图像拼接篡改检测方法

郑继明1, 苏慧嘉2   

  1. 1. 重庆邮电大学 理学院, 重庆 400065;
    2. 重庆邮电大学 计算机科学与技术学院, 重庆 400065
  • 收稿日期:2017-04-05 修回日期:2017-06-01 出版日期:2017-10-10 发布日期:2017-10-16
  • 通讯作者: 郑继明(1963-),男,四川简阳人,教授,硕士,主要研究方向:小波分析、模式识别,E-mail:zhengjm@cqupt.edu.cn
  • 作者简介:郑继明(1963-),男,四川简阳人,教授,硕士,主要研究方向:小波分析、模式识别;苏慧嘉(1991-),男,山西朔州人,硕士研究生,主要研究方向:图像处理.
  • 基金资助:
    重庆市教委科学技术研究项目(KJ1400428)。

Image splicing detection method based on correlation between color components

ZHENG Jiming1, SU Huijia2   

  1. 1. College of Science, Chongqing University of Posts and Telecommunications, Chongqing 400065, China;
    2. College of Computer Science and Technology, Chongqing University of Posts and Telecommunications, Chongqing 400065, China
  • Received:2017-04-05 Revised:2017-06-01 Online:2017-10-10 Published:2017-10-16
  • Supported by:
    This work is partially supported by the Science and Technology Research Project of Chongqing Municipal Education Commission (KJ1400428).

摘要: 由于目前数码相机在获取自然图像时,都存在着某种颜色滤波阵列(CFA)插值效应,使得图像颜色分量间具有很大的相关性。针对此问题提出基于CFA插值产生插值特性的图像拼接篡改检测方法。首先对图像颜色分量进行CFA插值预测,得到预测误差;然后计算图像块预测误差的局部加权方差得到图像块的CFA特征;最后根据高斯混合参数模型,对提取特征进行分类得到篡改区域。在标准拼接篡改图像数据集中的实验结果显示,此方法能够有效地检测出图像篡改区域的精确位置。

关键词: 图像拼接, 颜色滤波阵列插值, 颜色分量, 拼接篡改检测, 预测误差

Abstract: When using digital camera to get natural images, there exits Color Filter Array (CFA) interpolation effect, which makes great correlation between color components of the images. A new method was proposed to detect splicing operation by using interpolation characteristics of CFA interpolation process. Firstly, the prediction error was obtained by CFA interpolation for image color components. Then, the local weighted variance of image block predicting error was calculated to get the CFA characteristics of the natural image. Finally, to classify and derive the local splicing area, the Gaussian Mixture Model (GMM) was used according to extracted features. Experimental results in the standard splicing tamper the image data set demonstrate that the proposed method can effectively detect the exact location of the tampered area of the image.

Key words: image splicing, Color Filter Array (CFA) interpolation, color components, splicing detection, prediction error

中图分类号: