摘要
提出一种自然图像和计算机生成图形的鉴别方法。借用模式识别中的二分类概念,采用块离散余弦变换和统计矩特征量来建立模型,以捕获自然图像和计算机生成图形的统计差异,选用支持向量机作为分类器进行训练和测试。实验结果表明,该方法具有精确度高、应用面广的优点,在自然图像和计算机生成图形的鉴别中有着广阔的前景。
This paper proposes a new detection scheme to discriminate computer graphics from photo images. The detection can be regarded as a two-class pattern recognition problem and the model is established based on block discrete cosine transform （DCT） and statistical moment eigenvalue extracted from the given test image. This model can capture statistical differences between photo images and computer graphics. Kernel-based Support Vector Machine （ SVM ） is chosen as a classifier to train and test the given images. Experimental results demonstrate that this new detection scheme has some advantages of high-accuracy and widely-application, indicating that the proposed approach possesses promising capability in discrimination of computer graphics from photo images.
出处
《计算机应用与软件》
CSCD
2009年第12期30-33,共4页
Computer Applications and Software
基金
国家自然基金项目(60473022)
关键词
自然图像
计算机生成图形
统计矩特征
支持向量机
Photo images Computer graphics Statistical moment characteristic Support vector machine （SVM）
