电子学报 ›› 2022, Vol. 50 ›› Issue (8): 1840-1850.DOI: 10.12263/DZXB.20211428

• 学术论文 • 上一篇    下一篇

开放环境下自适应聚类优化包络的相机来源取证

王波1, 王悦1, 王伟2, 侯嘉尧1   

  1. 1.大连理工大学信息与通信工程学院,辽宁 大连 116024
    2.中国科学院自动化所智能感知与计算研究中心,北京 100190
  • 收稿日期:2021-10-19 修回日期:2022-02-09 出版日期:2022-08-25
    • 通讯作者:
    • 王伟
    • 作者简介:
    • 王波 男,1981年生于四川省自贡市.大连理工大学信息与通信工程学院副教授,博士生导师.主要研究方向为人工智能安全和多媒体信息安全.E-mail: bowang@dlut.edu.cn
      王悦 女,1997年生于黑龙江省哈尔滨市.大连理工大学信息与通信工程学院硕士研究生.主要研究方向为数字图像来源鉴别.E-mail: yuewang9779@163.com
      王 伟 男,1984年生于山西省忻州市.中国科学院自动化所副研究员.研究方向多媒体内容安全、人工智能安全、多模态内容分析与理解.E-mail: wei.wong@ia.ac.cn
      侯嘉尧 男,1998年生于辽宁省开原市.大连理工大学信息与通信工程学院硕士研究生.主要研究方向为小样本情况下的相机来源鉴别.E-mail: 32009157@mail.dlut.edu.cn
    • 基金资助:
    • 国家自然科学基金 (U1936117); 大连市科技创新基金 (2021JJ12GX018); 模式识别国家重点实验室开放课题基金 (202100032); 中央高校基本科研业务费专项资金 (No.DUT21GF303 (DUT20TD110); No.DUT20RC (3)088

Envelope Optimization Based on Adaptive Clustering for Open-Set Camera Model Identification

WANG Bo1, WANG Yue1, WANG Wei2, HOU Jia-yao1   

  1. 1.Faculty of Electronic Information and Electrical Engineering,Dalian University of Technology,Dalian,Liaoning 116024,China
    2.Center for Research on Intelligent Perception and Computing (CRIPAC),Institute of Automation,Chinese Academy of Sciences,Beijing 100190,China
  • Received:2021-10-19 Revised:2022-02-09 Online:2022-08-25 Published:2022-09-08
    • Corresponding author:
    • WANG Wei

摘要:

针对相机来源取证中的开放环境问题,本文提出一种自适应聚类优化包络的相机来源取证方法,解决了现有方法在训练相机模型数量少的恶劣情况下检测精度低的问题.首先,通过手肘法得到每一类相机数据的聚类个数,并以该聚类数为参照进行k-means聚类;然后将得到的相机模型子类数据分别进行支持向量数据描述以刻画其子包络,并根据所属相机模型类别将子包络合成一个更具细节特征的特征包络;最后通过判决法则将来自未知相机模型的图像排除,并将判断为已知来源的图像分类溯源,进而实现开放环境下的相机来源鉴别.实验结果表明,在Dresden和SOCRatES两个公开数据集上,本文提出的算法具有更优的鲁棒性和扩展性,与已有方法相比,在KACC,UACC和OACC三个评估指标和时间复杂度上均表现出更优越的性能.

关键词: 开放环境, 数字图像取证, 相机来源鉴别, 手肘法, 聚类包络优化

Abstract:

In this paper, an envelope optimization based on adaptive clustering for open-set camera model identification is proposed for the open-set problem of source camera identification, which solved the problem of low detection accuracy of the existing methods in the bad situation with few known camera models. Firstly, the clustering number of each type of camera data is obtained by the elbow method, and k-means clustering is performed with this clustering number as the reference. Then the sub-class data of the camera model are described by the technique of support vector data description, respectively to describe its hypersphere sub-envelope, and the sub-envelope is synthesized into a new hypersphere envelope with more detailed features according to the class of the camera model. Finally, the images from unknown camera models are excluded by the decision rule, and the images from known sources are classified and traceable to achieve source camera identification in the open-set. Experimental results on the two public datasets Dresden and SOCRatES show that the method proposed in this paper has better robustness and scalability. Compared with the existing methods, the three evaluation indicators of KACC, UACC, and OACC and time complexity are superior.

Key words: open-set, digital image forensics, source camera identification, elbow method, envelope of clustering optimization

中图分类号: