• 中国计算机学会会刊
  • 中国科技核心期刊
  • 中文核心期刊

计算机工程与科学 ›› 2025, Vol. 47 ›› Issue (10): 1787-1798.

• 计算机网络与信息安全 • 上一篇    下一篇

面向DCT系数分析的Seam Carving对象移除定位方法

蔺聪,马鸿基,司徒晓晴,甄荣桂,肖洪涛,邓宇乔   

  1. (1.广东财经大学统计与数据科学学院,广东 广州 510320;
    2.信息技术教育部重点实验室(中山大学),广东 广州 510006;3.广东财经大学信息学院,广东 广州 510320; 
    4.开平市马冈镇人民政府,广东 江门 529300;5.北京国瑞数智技术有限公司,北京 100082)
  • 收稿日期:2024-12-16 修回日期:2025-02-15 出版日期:2025-10-25 发布日期:2025-10-29
  • 基金资助:
    国家自然科学基金(62441237,62472199);信息技术教育部重点实验室(中山大学)开放基金课题(2024ZD001);广东省哲学社会科学规划项目(GD24XTS02,GD25CXW07);广东省教育科学规划项目(2023GXJK295,2022GXJK201);广东大学生科技创新培育专项资金(pdjh2025bk099);广东财经大学2022年度一流本科教学质量与教学改革工程项目

Localization of object removal by Seam Carving via DCT coefficient analysis

LIN Cong,MA Hongji,SITU Xiaoqing,ZHEN Ronggui,XIAO Hongtao,DENG Yuqiao   

  1. (1.School of Statistics and Data Science,Guangdong University of Finance & Economics,Guangzhou 510320;
    2.Ministry of Education Key Laboratory of Information Technology,Sun Yat-sen University,Guangzhou 510006;
    3.School of Information,Guangdong University of Finance & Economics,Guangzhou 510320; 
    4.People’s Government of Magang Town,Kaiping City,Jiangmen 529300; 
    5.Beijing GRDI Technology Co.,Ltd.,Beijing 100082,China)
  • Received:2024-12-16 Revised:2025-02-15 Online:2025-10-25 Published:2025-10-29

摘要: 随着数字图像处理技术的飞速发展,图像篡改手段日益多样化和隐蔽化,其中一种重要篡改方式就是对象移除。Seam Carving可应用于调整图像大小和对象移除。针对通过Seam Carving进行对象移除这一篡改方式,首次将双量化效应引入Seam Carving对象移除,根据Seam Carving对象移除过程中产生的DCT异常块,提出了一种基于DCT系数分析的Seam Carving对象移除定位方法。首先,提取JPEG图像中的量化矩阵和DCT系数直方图。其次,根据直方图估算出主要量化矩阵和原始DCT系数,并使用贝叶斯方法估算出图像篡改区域的后验概率图。最后,对该后验概率图进行去噪和定位,得到移除区域的准确位置。实验结果表明,该方法能够有效地检测和定位Seam Carving对象移除,为该问题的解决提供了一种新的研究思路。

关键词: 图像取证, 篡改检测, 对象移除, Seam Carving, 双量化效应

Abstract: With the advancement of digital image processing, image tampering techniques have grown increasingly diverse and covert, among which object removal is a critical manipulation technique. Seam Carving, initially designed for content-aware resizing of images, can also be exploited for object removal. To address this tampering technique, this paper proposes a novel forensic method to localize object removal by Seam Carving by analyzing anomalies in DCT coefficients. For the first time, the paper introduces the double quantization effect into object removal by Seam Carving. Specifically, the paper identifies abnormal DCT blocks generated during Seam Carving-based object removal. The proposed method involves three key steps: 1) extracting the quantization matrix and DCT coefficient histograms from JPEG images; 2) estimating the primary quantization matrix and original DCT coefficients based on histograms, followed by generating a posterior probability map of tampered regions using a Bayesian framework; 3) denoising and thresholding the probability map to pinpoint the location of removed objects. Experimental results demonstrate that the proposed method effectively detects and localizes Seam Carving object removal. This method provides a new research direction for tampering forensics. 

Key words: image forensics, tampering detection, object removal, Seam Carving, double quantization effect