Fringe Texture Driven Droplet Measurement End-to-End Network Based on Physics Aberrations Restoration of Coherence Scanning Interferometry
Year: 2024
Type: article
Abstract: Accurate and efficient measurement of deposited droplets' volume is vital to achieve zero-defect manufacturing in inkjet printed organic light-emitting diode (OLED), but it remains a challenge due to droplets' featurelessness. In our work, coherence scanning interferometry (CSI) is utilized to measure the volume. However, the CSI redundant sampling and image degradation led by the sample's transparency decrease the efficiency and accuracy. Based on the prior degradation and strong representation for context, a novel method, volume measurement via fringe distribution module (VMFD), is proposed to directly measure the volume by single interferogram without redundant sampling. Firstly, the 3D point spread function (PSF) for CSI imaging is modeling to relate the degradation and image. Secondly, the Zernike to PSF (ZTP) module is proposed to efficiently compute the aberrations to PSF. Then, a physics aberration restoration network (PARN) is designed to remove the degradation via the channel Transformer and U-net architecture. The long term context is learned by PARN and beneficial to restoration. The restored fringes are used to measure the droplet's volume by constrained regression network (CRN) module. Finally, the performances on public datasets and the volume measurement experiments show the promising deblurring, measurement precision and efficiency.
Source: Micromachines
DOI: 10.3390/mi16010042
Authors: Zhou Zhang, Jiankui Chen, Hua Yang, Zhouping Yin
Institution: Huazhong University of Science and Technology
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: gold
Estimated APC paid: $2,955
Awards: G3596376429, G6348327484
OpenAlex ID: W4405940702