摘要
分析了常用的图像质量参数,采用方差分析对图像质量参数在拼接图像盲检测中的应用进行筛选。通过提取对拼接图像较为敏感的图像质量评价量再融合基于隐马尔科夫模型的特征向量来建立模型,以捕获原始图像和拼接图像之间的统计差异,选用支持向量机作为分类器进行训练和测试,对拼接图像的盲检测进行了研究。实验结果表明,该方法精确度高、应用面广,在图像拼接检测中有着广阔的前景。
Common image quality measures are analyzed, and analysis of variance is used to select the image quality measures which are more sensitive to image blind splicing detection. A new splicing detection scheme is proposed based on the model consisting of features from hidden Markov model and image quality metrics. This model can capture statistical differences between original image and spliced image. Support vector machine is chosen as a classifier to train and test the given images. Experimental results demonstrate that the scheme has some advantages of high-accuracy and widely-application, indicating that the proposed approach possesses promising capability in splicing detection.
出处
《计算机工程与设计》
CSCD
北大核心
2009年第12期3005-3008,共4页
Computer Engineering and Design
基金
国家自然科学基金项目(60473022)
关键词
图像质量评价量
数字图像盲取证
图像拼接检测
方差分析
隐马尔科夫模型
支持向量机
image quality metrics （IQMs）
digital image forensics
image splicing detection
analysis of variance （ANOVA）
hidden Markov model （HMM）
support vector machine （SVM）
