Defect detection based on deep learning

Methods and systems are provided for detecting defects on a sample. A system includes one or more computer systems and one or more components executed by the one or more computer systems. The assembly includes a deep learning model configured for generating, for a location on a sample, a gray scale simulated design data image from a high resolution image generated by a high resolution imaging system at the location. The computer system is configured to generate a simulated binary design data image for the location from the gray scale simulated design data image. The computer system is also configured to detect a defect on the sample at the location by subtracting design data for the location from the simulated binary design data image. 提供用于检测样本上的缺陷的方法及系统。一种系统包含一或多个计算机系统及由所述一或多个计算机系统执行的一或多个组件。所述组件包含深度学习模型，其经配置用于针对样本上的位置从由高分辨率成像系统在所述位置处产生的高分辨率图像产生灰阶模拟设计数据图像。所述计算机系统经配置用于从所述灰阶模拟设计数据图像产生所述位置的模拟二进制设计数据图像。所述计算机系统还经配置用于通过从所述模拟二进制设计数据图像减去所述位置的设计数据来检测所述样本上所述位置处的缺陷。