一种基于HWD结构相似的图像质量评价方法

Image quality assessment based on HWD structural similarity

针对传统图像质量评价方法峰值信噪比PSNR和结构相似度SSIM没有充分考虑人眼视觉特性,所得结果有时并不能与人眼的视觉所感知到的实际质量一致的问题,通过对图像结构相似度和人眼视觉系统的研究,文中提出了一种新的基于HWD结构相似的图像质量评价方法。首先对图像进行Hybrid Wavelets and Directional Filter Banks(HWD)分解,提取图像不同频带不同方向上的信息,然后计算各子带结构相似度,最后综合人眼视觉特性的CSF得到图像质量评价值。实验结果表明文中方法相比峰值信噪比PSNR、结构相似度SSIM算法具有更高的准确性和良好的相关性,可以更好的评价图像质量。

Traditional image quality assessment methods may not be consistent with visual perception because they did not fully consider Human Visual System.Based on the research of image Structural Similarity （SSIM） and Human Visual System （HVS） ,HWD domain-based structural similarity was proposed in this paper. Firstly,images were decomposed into subbands with different scales and directions by hybrid wavelets and directional filter banks （HWD） ,the structural similarity was calculated in each subbands,then the result was masked with contrast sensitivity function （CSF） to evaluate the image quality. Experimental results illustrate that,compared with SSIM and Peak Signal to Noise Ratio （PSNR） ,the proposed method is more consistent with the subjective assessment of human beings,thus can be used to describe the visual perception of image effectively.