.png){kind=icon}
.png){kind=icon}
Return
PSO-based imaging restoration method for diffraction imaging systems
.png){kind=icon}
OA
AI
DOI：10.3389/aot.2025.1730807.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Membrane diffraction imaging is one of the most widely used imaging technologies today, which offers the advantages such as lightweight design, large aperture, foldability, and low cost. However, the system imaging quality degrades because of the multiple order diffraction generated by the diffractive elements in practical applications. To eliminate the effects of multiple diffraction orders from the diffractive elements and optimize imaging quality, the system images are post processed. Iterative optimization algorithms are commonly used for image post processing. Particle swarm optimization is a commonly used iterative optimization algorithm, which is often used to search for optimal solutions within the solution space. The particle swarm optimization algorithm has the features of few parameters, simple behavior, and fast iteration speed, which can rapidly and effectively optimize imaging. This paper optimizes the simulated imaging of a diffraction imaging system based on Fresnel zone plates by adopting the particle swarm optimization algorithm. Optimize the system image based on known point spread functions and the system image. System imaging is optimized under the premise of known point spread functions and system imaging. The iteration speed is enhanced, reducing the number of iterations by approximately 99.6 % compared to the random parallel gradient descent algorithm. Simultaneously, contrast is improved by about 5.4 % , while gradient optimization effectiveness increases by approximately 25.4 % after optimization by the particle swarm algorithm. Finally, the derived restoration model was applied to other images, achieving overall improvements in all evaluation metrics.
Keywords:
fresnel zone plate
imaging optimization
multiple orders diffraction
particle swarm optimization algorithm
point spread function
Journal
A
IF:
3
Papers:
8
Citations:
0