光学精密工程2024，Vol.32Issue(20)：3047-3058,12.DOI:10.37188/OPE.20243220.3047
面向显微视觉的端对端去模糊模型
End-to-end deblurring model for microscopic vision
摘要
Abstract
The measurement of microscopic vision is commonly used in micro-assembly and other fields.However,due to limitations such as depth of field in microscopic imaging,the image may appear blurred and affect the accuracy of measurement.Although the technology of auto-focusing in optical microscopy can alleviate defocusing problems,it will be too time-consuming to adapt to the requirements of efficient production.Herein,an end-to-end deblurring model that integrates blurring discrimination and multi-branch recovery was presented,in which a divide-and-conquer strategy of chunking,discrimination,de-blurring,and fusion was established.Firstly,the image was divided into sub-images,which were then si-multaneously processed by a discriminator and a recovery network.The discriminator employed the Fouri-er transform to obtain the frequency-domain map of the sub-images.From the frequency domain map,the Vision Transformer network extracted deep blur features with global correlation.The output of the blur-ring degree was then discriminated.The multi-branch recovery network was used to directionally recover sub-images with different blurring degrees based on the discriminative output.Finally,the spliced sub-im-ages were fused to obtain high-resolution images.The experimental results indicate that the model can ef-fectively restore multi-blurred microscopic images,with a discriminator accuracy reaching 0.94.More-over,after undergoing processing by the multi-branch restoration network,the PSNR metric shows an av-erage improvement of 6.3.关键词
微装配/显微视觉/模糊度判别/频域处理Key words
micro-assembly/microscopic vision/blur classification/frequency domain processing分类
计算机与自动化引用本文复制引用
徐征,何佳珩,王彦琪,王晓东,任同群..面向显微视觉的端对端去模糊模型[J].光学精密工程,2024,32(20):3047-3058,12.基金项目
国防基础科研计划资助项目(No.JCKY2022203B006) （No.JCKY2022203B006）
中央高校基本科研业务费资助项目(No.DUT24LAB112) （No.DUT24LAB112）
