基于CSF和梯度相似度的红外图像质量评价

Infrared image quality evaluation based on CSF and gradient similarity

针对传统的峰值信噪比及常用的结构相似度等图像质量评价方法对人视觉特点考虑的不足,提出了一种基于CSF(对比敏感度函数)和梯度相似度的红外图像质量评价方法。该方法在结构相似度方法的基础上,采用Sobel掩模算子计算图像的梯度幅值对其改进,利用对比度敏感函数赋予图像块以相应权值,最后加权得到整幅图像的评价值。从实验结果可看出,所提方法与传统方法相比与主观评价的一致性更高。

In view of the deficiency of the traditional image quality evaluation method based on peak signal to noise ratio and the most frequently used method based on structural similarity in visual characteristics,an infrared image quality evaluation method based on CSF and gradient similarity is proposed. On the basis of structural similarity,this method is improved by gradient magnitude which is calculated with Sobel operator. Then,the weight which is calculated with the contrast sensitivity function is given to the image block. Finally,the whole evaluation value is obtained according to the weight of the image block. The results of our experiment show that the proposed algorithm is superior to other methods,and is more consistent with human subjective feelings.