Abstract: With the development of deep learning in recent years, image aesthetic evaluation has gradually become a new hot research topic. The application of deep convolution neural network in image aesthetic evaluation has successfully achieved considerable development results and has attracted wide attention. In order to solve the problems of incomplete literature survey and insufficient understanding of the development of this technology, this paper elaborates its development in detail from the perspectives of global perception and local perception, personalized query, combination of extracting handcrafted features and deep convolution neural network. The application of image aesthetics evaluation, image clipping and tool application are also discussed. The future work is prospected from the perspectives of fully combining multi-scene, skillfully using composition rules, and establishing aesthetic image data sets in advance.

Key words: deep learning, image aesthetic evaluation, deep convolution neural network

摘要： 随着近年来深度学习的日益发展，图像美学评价逐渐成为一个新的热门研究课题，深度卷积神经网络在图像美学评价的应用成功地取得了可观的发展成果，并引起了广泛的关注。为了解决现有综述存在的文献概括不全、对该技术的发展情况认识不足的问题，先后从全局感知和局部感知、个性化查询、手工特征提取与深度卷积神经网络结合等角度对其发展情况进行了详细地阐述，对图像美学评价、图像裁剪、工具应用等应用情况作了分析，并从充分结合多场景、巧用构图规则、提前建立美学图像数据集等角度进行了未来工作展望。

关键词: 深度学习, 图像美学评价, 深度卷积神经网络