融合色彩和谐性与构图的图像美学分类方法研究

A Method of Image Aesthetics Classification Based on Color Harmony and Composition

图像美学评价通过构建模拟人脑审美思维的计算模型,对图像作出具有可行性的美学决策。针对现有方法特征选择单一以及无法适用所有类型图像的问题,提出一种基于改进的色彩和谐性并融合构图的图像美学评价方法。现有的色彩和谐性提取方法没有考虑色彩调和模型,只适用于比较简单的颜色组合。为此,提出一种改进的色彩和谐性度量方法。为了更好地对各类图像进行美学分类,又融合了构图特征。在Datta数据库上进行实验,证明了该方法的有效性和普适性。

Image aesthetics can be calculated by constructing a computational model,simulating the human brain's aesthetic thinking and visual system,to make a feasible aesthetic decision.Aiming at the problem that the feature selection of the existing methods is single and can not be applied to all types of images,this paper proposes an image aesthetic evaluation method based on improved color harmony and composition.The existing color harmony calculation methods ignore that color harmony model is only applicable to relatively simple color composition,overlook that the number of colors in the subject area and in the background area is different.Therefore,an improved method of color harmony measurement is proposed in the paper.At the same time,composition is merged to better classify all kinds of images.Experiments on Datta database prove the effectiveness and universality of the proposed method.