近年来,图像质量评价方法在图像处理和理解领域受到越来越多的关注。传统的方法主要关注噪声、清晰度、分辨率等影响图像质量的底层因素。随着数码设备的不断发展,这些底层因素已经得到很好的解决,人们能够很容易地获得具有较高底层质量,即低噪声、高清晰度、高分辨率的图像。因此,图像质量评价的焦点逐渐转向从美学的角度进行评价。对于一幅图像,主要从两个角度来考虑其是否符合人类主观的美学需求:1)图像的主题是否突出;2)图像的布局是否合理。基于上述考虑,提出一种结合图像景深和构图的质量评价方法:一方面,提出一种基于模糊度量的浅景深判断方法,浅景深的图像能够突出主题、虚化背景,具有更强的视觉冲击力与美学表现力;另一方面,提出一种基于"三分法"的图像构图评价方法,符合"三分法"构图的图像布局更加紧凑有力、简洁明了、符合人类的欣赏习惯;最后,将浅景深判断与图像构图评价进行结合,从美学的角度自动地对图像进行客观、综合的评价。按本文方法,可以挑选出符合以上美学规则的图像。从实验结果可以看出,根据本文方法选出的高质量图像也符合人类主观的美学需求。

Image quality assessment has attracted increasing attention in recent years. Conventional algorithms focus on measuring the image degradation caused by low-level features like noise, definition, and resolution. However, with the ra- pid development of digital devices, images with low-noise, high definition, and high resolution can be obtained easily, making these low-level features less important in quality assessment. In this paper, we propose an image quality assessment method from the perspective of aesthetics. An image is assessed by two metrics: 1) whether it has a clear topic and 2) whether its composition is friendly to human viewers. We propose an image assessment method combining depth-of-field(DoF) and composition to achieve the above mentioned goal. We first introduce a blur measurement based low-DoF detection approach. A low-DoF image with a clear topic and blurred background is considered to have greater visual impact. Furthermore, we assess the image composition by how well it is consistent with the rule of thirds, which can make the images more compact. Finally, we combine low-DoF and composition to get an objective aesthetic assessment. The experiment results suggest images assessed with high qualities by the proposed method are also good images according to human aesthetics.