Due to inadequate global population growth, there has been a dramatic increase in the volume of traffic on today's state-of-the-art highways. Vehicle identification and traffic congestion assessment are both critical. The secret is to use readers for license plates to gather data about automobiles. The rapid and precise detection of vehicle crossings required the development of a deep learning framework or networks. The proposed approach relies on the Densenet121 technique for license plate segmentation, with the inclusion of an adaptable attention network to better extract the digits and letters. According to the findings, it is best to use a vehicle predictor powered by deep learning to spot plates and numbers at the same time. To do this, we used Python in conjunction with many deep learning instruments. Experimental assessments have proven that deep learning is effective due to its state-of-the-art detection precision and computational economy. The research also dives into the obstacles encountered and possible remedies for automatic plate recognition in pictures. License plate readers have several practical applications including toll collecting, accident investigation, and identity of suspicious vehicles.
Vehicle Number Plate Detection using Deep Learning
23.02.2024
524815 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Car Number Plate Detection using Deep Learning
IEEE | 2022
|Automatic vehicle license plate number detection using machine learning
BASE | 2020
|