Method for converting confocal image into stimulated radiation loss image
The invention provides a method for converting a confocal image into a stimulated radiation loss image, and the method comprises the steps: carrying out the histogram normalization processing of an STED image, cutting a paired Confoal-STED data set, and constructing a network training set; training...
Gespeichert in:
Hauptverfasser: | , , , , |
---|---|
Format: | Patent |
Sprache: | chi ; eng |
Schlagworte: | |
Online-Zugang: | Volltext bestellen |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
Zusammenfassung: | The invention provides a method for converting a confocal image into a stimulated radiation loss image, and the method comprises the steps: carrying out the histogram normalization processing of an STED image, cutting a paired Confoal-STED data set, and constructing a network training set; training a generator network and a discriminator network by using the network training set; cutting the Confocal image and inputting the cut Confocal image into a generator network, and transcoding the image by the generator network to generate an STED image; dividing the STED image generated by the generator network into a plurality of small blocks, screening and calibrating each small block by the discriminator network, and repairing the STED image by using a loss function; and outputting the final STED image. The beneficial effects of the invention are that the problems that the STED imaging technology is large in light path construction difficulty, high in cost, low in stability and easy to poison organisms by light are |
---|