Deep Learning-Based Dynamic Region of Interest Autofocus Method for Grayscale Image
Author:
Wang Yao12, Wu Chuan1, Gao Yunlong1ORCID, Liu Huiying12ORCID
Affiliation:
1. Changchun Institute of Optics, Fine Mechanics and Physics, Chinese Academy of Sciences, Changchun 130033, China 2. University of Chinese Academy of Sciences, Beijing 100049, China
Abstract
In the field of autofocus for optical systems, although passive focusing methods are widely used due to their cost-effectiveness, fixed focusing windows and evaluation functions in certain scenarios can still lead to focusing failures. Additionally, the lack of datasets limits the extensive research of deep learning methods. In this work, we propose a neural network autofocus method with the capability of dynamically selecting the region of interest (ROI). Our main work is as follows: first, we construct a dataset for automatic focusing of grayscale images; second, we transform the autofocus issue into an ordinal regression problem and propose two focusing strategies: full-stack search and single-frame prediction; and third, we construct a MobileViT network with a linear self-attention mechanism to achieve automatic focusing on dynamic regions of interest. The effectiveness of the proposed focusing method is verified through experiments, and the results show that the focusing MAE of the full-stack search can be as low as 0.094, with a focusing time of 27.8 ms, and the focusing MAE of the single-frame prediction can be as low as 0.142, with a focusing time of 27.5 ms.
Reference39 articles.
1. Autofocus area design of digital imaging system;Li;Acta Photonica Sin.,2002 2. Herrmann, C., Bowen, R.S., Wadhwa, N., Garg, R., He, Q.R., Barron, J.T., and Zabih, R. (2020, January 14–19). Learning to Autofocus. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Electr Network, Seattle, WA, USA. 3. Enhanced Autofocus Algorithm Using Robust Focus Measure and Fuzzy Reasoning;Lee;IEEE Trans. Circuits Syst. Video Technol.,2008 4. Pech-Pacheco, J.L., Cristóbal, G., Chamorro-Martínez, J., and Fernández-Valdivia, J. (2000, January 3–7). Diatom autofocusing in brightfield microscopy: A comparative study. Proceedings of the 15th International Conference on Pattern Recognition (ICPR-2000), Barcelona, Spain. 5. A Novel Auto-Focus Method for Image Processing Using Laser Triangulation;Zhang;IEEE Access,2019
|
|