摘要
该算法针对古籍图像复制粘贴篡改检测需求而设计。算法以SURF算法为基础,引入小波变换并改进,清除Hessian矩阵中噪声斑点;引入用于图像分割的简单线性迭代聚类算法并改进,减少匹配检索用时;改进欧氏距离匹配阈值选取策略,提高篡改检测匹配度;引入图像局部色彩方差,提升检测匹配准确性。结合古籍图像篡改实例,并与当前其他主流算法就检测效果进行比较分析,结果表明,该算法在匹配检测准确度和检测用时两方面更具优势,更能有效地鉴定图像篡改信息。
The algorithm in this paper is designed for the demand of copy-paste tampering detection for antiquarian images. The algorithm is based on the SURF algorithm, and the wavelet transform is included and enhanced to remove the noise spots in the Hessian matrix;the simple linear iterative clustering algorithm for image segmentation is introduced and improved to reduce the matching retrieval time;the Euclidean distance matching threshold selection strategy is refined to increase the tampering detection matching;the local color variance of the image is adopted to improve the detection matching accuracy. The results show that the algorithm is more advantageous in both matching detection accuracy and detection time.
作者
王永飞
王春
Wang Yongfei;Wang Chun(Tongling Vocational and Technical College,Tongling 244061,China;Tongling Fourth People’s Hospital,Tongling 244061,China)
出处
《六盘水师范学院学报》
2021年第4期100-111,共12页
Journal of Liupanshui Normal University
基金
2020年度铜陵职业技术学院自然科学重点研究项目“数字噪声图像损伤修复技术分析研究”(tlpt2020NK014)
2017年度安徽省高等学校质量工程项目“MOOC‘PHOTOSHOP实用教程’”(2017mooc348)。
关键词
古籍图像
篡改匹配
小波变换
SLIC
antiquarian images
tampering matching
Wavelet transform
SLIC
