ITM Web Conf.
Volume 45, 20222021 3rd International Conference on Computer Science Communication and Network Security (CSCNS2021)
|Number of page(s)||6|
|Section||Computer Technology and System Design|
|Published online||19 May 2022|
Fast all-focus image reconstruction method based on light field imaging
School of Electronic Information and Engineering, Changchun University of Science and Technology, Changchun, Jilin 130022, China
2 School of Opto-Electronic Engineering, Changchun University of Science and Technology, Changchun, Jilin 130022, China
* Corresponding author: ShuzhenWang@mails.cust.edu.cn
To achieve high-quality imaging of all focal planes with large depth of field information, a fast all-focus image reconstruction technology based on light field imaging is proposed: combining light field imaging to collect field of view information, and using light field reconstruction to obtain a multi-focus image source set, using the improved NSML image fusion method performs image fusion to quickly obtain an all-focus image with a large depth of field. Experiments have proved that this method greatly reduces the time consumed in the image fusion process by simplifying the calculation process of NSML, and improves the efficiency of image fusion. This method not only achieves excellent fusion image quality, but also improves the real-time performance of the algorithm.
© The Authors, published by EDP Sciences, 2022
This is an Open Access article distributed under the terms of the Creative Commons Attribution License 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.