.png){kind=icon}
.png){kind=icon}
Return
Multifocus Image Fusion Algorithm Based on Rough Set and Neural Network
.png){kind=icon}
PRE
AI
DOI：10.1109/JSEN.2020.2969490.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
The depth of field of the imaging device is limited, which makes it sometimes difficult to present all of the different objects on the same image. In order to solve this problem, the multi-focus image fusion fuses the source images focused on different positions in the same scene, thereby extracting the focused portions of all the source images to obtain a clearer image. In order to obtain a better fusion image, PCNN (Pulse Coupled Neural Network) and rough set are used in the fusion of multi-focus images. First, the neighborhood spatial frequency and local variance of the source image pixels are calculated. The neighborhood space frequency is used as the input of PCNN, and the local variance is taken as the link strength of PCNN corresponding to the gods. The source image pixels are sorted according to the rough set theory, and finally the merged images are generated. The simulation experiment shows that the algorithm is superior to some other fusion algorithms in a certain degree.
Keywords:
Confocal image fusion
pulse coupling to neural network
rough set
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
4.5
Papers:
2.1W
Citations:
7.3W