Journal of Computer Applications ›› 2019, Vol. 39 ›› Issue (9): 2707-2711.DOI: 10.11772/j.issn.1001-9081.2019020306

• Virtual reality and multimedia computing • Previous Articles     Next Articles

Image forgery detection based on local intensity order and multi-support region

YAN Pu1,2, SU Liangliang1,2, SHAO Hui2, WU Dongsheng2   

  1. 1. Anhui Provincial Key Laboratory of Intelligent Building and Building Energy Conservation(Anhui Jianzhu University), Hefei Anhui 230022, China;
    2. College of Electronic and Information Engineering, Anhui Jianzhu University, Hefei Anhui 230601, China
  • Received:2019-02-25 Revised:2019-05-04 Online:2019-09-10 Published:2019-09-10
  • Supported by:

    This work is partially supported by the National Natural Science Foundation of China (61672032), the Natural Science Foundation of Anhui Province (1908085QF281), the Doctoral Scientific Research Foundation of Anhui Jianzhu University (2017QD13, 2015QD07).


颜普1,2, 苏亮亮1,2, 邵慧2, 吴东升2   

  1. 1. 智能建筑与建筑节能安徽省重点实验室(安徽建筑大学), 合肥 230022;
    2. 安徽建筑大学 电子与信息工程学院, 合肥 230601
  • 通讯作者: 颜普
  • 作者简介:颜普(1986-),男,安徽亳州人,讲师,博士,CCF会员,主要研究方向:计算机视觉、模式识别;苏亮亮(1986-),男,安徽安庆人,讲师,博士,CCF会员,主要研究方向:视频图像处理、模式识别;邵慧(1979-),女,安徽长丰人,副教授,博士,主要研究方向:机器学习、图像处理;吴东升(1966-),男,安徽枞阳人,教授,博士,主要研究方向:电磁场理论、数据挖掘。
  • 基金资助:



Image forgery detection is currently one of the research focuses of digital image processing, and copy-move forgery is the most frequently used techniques in it. The forgery region is subjected to the operations of scale, rotation, JPEG compression, adding noise and so on before the image moved in, thus detecting the forgery becomes hard. Aimming at the image copy-move forgery technology, an image forgery detection algorithm based on Local Intensity Order Pattern (LIOP) and multiple support regions was proposed. Firstly, the affine invariant regions were detected as support regions by Maximally Stable Extremal Region (MSER) algorithm. Secondly, multiple support regions of different scales, resolutions and directions were obtained by NonSubsampled Contourlet Transform (NSCT). Thirdly, the LIOP descriptors invariant to monotonic intensity change and image rotation were extracted on each support region, and the initial feature matching was implemented via bidirectional distance ratio method. Fourthly, spatial clustering was used to classify the matching features, and geometric transformation parameters were estimated for each cluster by using RANdom SAmple Consensus (RANSAC) algorithm. Finally, the essential operations like post-processing were performed to detect the forgery regions. The experimental results show that the proposed algorithm has higher forgery detection accuracy and reliability.

Key words: image forgery, copy-move detection, multi-support region, Nonsubsampled Contourlet Transform (NSCT), Local Intensity Order Pattern (LIOP)



关键词: 图像伪造, 复制-粘贴检测, 多支持区域, 非抽样Contourlet变换, 局部亮度序模式

CLC Number: