Frame detection license plate anti-counterfeiting method and system based on deep learning

The invention discloses a frame detection license plate anti-counterfeiting method and system based on deep learning, and the method comprises the steps: obtaining a to-be-detected attack picture which comprises a license plate region and a container region; marking a boundary rectangular frame of a...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: ZHOU ZHUOLI, YANG SHUANGXIANG, REN PENG
Format: Patent
Sprache:chi ; eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:The invention discloses a frame detection license plate anti-counterfeiting method and system based on deep learning, and the method comprises the steps: obtaining a to-be-detected attack picture which comprises a license plate region and a container region; marking a boundary rectangular frame of a container and a rectangular frame of a license plate according to the to-be-detected attack picture; and judging the authenticity of the license plate according to a trained frame detection model, the boundary rectangular frame of the container and the rectangular frame of the license plate. According to the method, association judgment is carried out by utilizing the position relationship between the frame of the container of the fake license plate and the frame of the license plate, so that common attacks of mobile phones, ipads and printing paper can be prevented, the method is simple to implement, and extra physical mark information is not needed; and meanwhile, a relatively high anti-counterfeiting rate can b