中文摘要：

自动调光是全自动显微成像中的一项关键技术。为了解决已有调光算法空白视野失效、不能实时处理图像和调光精度低等问题，本文从分析清晰度评价函数随光源亮度变化曲线入手，验证了这类函数的调光性能。根据光学显微镜的成像原理和观测目标的特点，考虑与图像清晰度无关、仅与图像亮度信息有关的变量，提出了利用空白区域的灰度均值寻找最优光亮度的算法。通过人工训练样本方式获取最优灰度均值，最后通过单变量手优法得到最优光源亮度。基于自行研发的全自动显微镜系统对本文算法进行了验证，实验结果证明了算法的有效性。

英文摘要：

Dimmer automation is one of the key issues in automatic microscopy.The traditional methods suffer from blank vision failure,not real-time image processing and low dimmer accuracy.This paper validates dimmer performance of the definition evaluation function through the change curve.Considering the optical microscope imaging principle and characteristics of the observed object,this paper proposes an algorithm searching best light intensity based on average gray of blank areas.Then acquire the best average gray through artificial training samples and best light intensity through single variable optimization method.Experimental investigation has been conducted to demonstrate the validity of the proposed method.