License plate character segmentation method and system based on deep learning
The invention discloses a license plate character segmentation method and system based on deep learning, and the method comprises the steps: obtaining a located license plate image, and carrying out the normalization processing of the license plate image; inputting the license plate image obtained t...
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 discloses a license plate character segmentation method and system based on deep learning, and the method comprises the steps: obtaining a located license plate image, and carrying out the normalization processing of the license plate image; inputting the license plate image obtained through normalization processing into a pre-constructed deep learning model, and obtaining a central point position of a license plate character in the license plate image; and obtaining a segmentation position of the license plate character in the license plate image according to the center point position of the license plate character in the license plate image. According to the method, the character position can be accurately positioned based on deep learning, various interferences can be effectively resisted, and meanwhile, the constructed deep learning model can realize accurate positioning in an extremely light scale; according to the method and the system, complicated operations such as graying, binaryzation, |
---|