Abstract: No-Reference Image Quality Assessment（NRIQA） is a hot topic in Computer Vision（CV） and its cross field due to its wide range of applications. The paper reviews the typical models of NRIQA based on Machine Learning（ML） in the nearly ten years. Firstly, the commonly used public databases and algorithm performance indicators are introduced. The existing problems and their solutions in NRIQA field are explained. Then, the guiding ideology and characteristics are discussed in each algorithm implementation. Finally, the literature compares test results on the different databases, and analyzes development trends by summarizing the present status to provide a reference for researchers.

Key words: Computer Vision（CV）, No-Reference Image Quality Assessment（NRIQA）, Machine Learning（ML）

摘要： 无参考图像质量评价（NRIQA）因其广泛的应用需求一直以来都是计算机视觉及其交叉领域的研究热点。回顾近十几年来基于机器学习的典型NRIQA模型，介绍图像质量评价的常用数据库、算法性能指标、NRIQA主要难点和现有的解决方法；分析了不同模型的思想、实现、特点；最后统计对比多个数据库上的测试结果。总结研究现状、分析发展趋势，为这一领域的研究者提供文献参考。

关键词: 计算机视觉, 无参考图像质量评价, 机器学习