A high-resolution automated optical inspection (AOI) system based on parallel computing is developed to achieve fast inspection and classification of surface defects. To perform fast inspection, the AOI apparatus is connected to a central computer which executes image processing instructions in a graphical processing unit. Defect classification is simultaneously implemented with Hu’s moment invariants and back propagation neural (BPN) approach. Experiments on touch panel glass show that using 100 training samples and 1000 cycle iterations in BPN, the accurate classification of surface defects for a 350 × 350 pixels image can be completed in less than 0.1 ms. Moreover, the inspection of a 43 mm × 229 mm sample that yields an 800 megapixel raw data can be completed remarkably fast in less than 3 s. Thus, the AOI system is capable of performing fast, reliable, and fully integrated inspection and classification equipment for in-line measurements.

开发了基于并行计算的高分辨率自动光学检查（AOI）系统，以实现表面缺陷的快速检查和分类。为了执行快速检查，将AOI设备连接到中央计算机，该中央计算机在图形处理单元中执行图像处理指令。胡氏矩不变性和反向传播神经（BPN）方法可同时实现缺陷分类。触摸面板玻璃上的实验表明，在BPN中使用100个训练样本和1000次循环迭代，可以在不到0.1 ms的时间内完成对350×350像素图像的表面缺陷的准确分类。此外，可以在不到3 s的时间内迅速完成对产生800兆像素原始数据的43 mm×229 mm样本的检查。因此，AOI系统能够快速执行