摘要
图像质量评价是图像处理技术的基础。由于图像处理结果的最终接受者是人,因此在评价图像质量时必须考虑到人类视觉系统的特性。为此利用小波的多分辨率分析方法与人眼视觉系统(HVS)信息处理特性相类似的特点,结合对比敏感度函数的带通特性,提出了一种无参考的客观图像质量评价方法。实验结果表明,该评价方法优于传统的质量评价方法,而且能较好地与人的主观视觉感受保持一致。
Image quality assessment is the base of image processing technology. Since human being is the final receiver of the image, the key point of the image assessment is that it must be taken into account match the characteristics of human visual system. In this paper, wavelet multi-resolution analysis is used. That is because it matches well with the model of HVS. Combined with the band-pass property of contrast sensitivity function, a no-reference objective image quality assessment method was proposed. The experimental results show that the new assessment method is superior to the traditional assessment ,method and it is better consistent with human subjective sensation.
出处
《微型机与应用》
2010年第9期38-40,共3页
Microcomputer & Its Applications
基金
山西省自然科学基金资助项目(2007012003)
关键词
图像质量评价
小波变换
人类视觉系统
对比敏感度函数
image quality assessment
wavelet transform
human visual system（HVS）
contrast sensitivity function（CSF）
