Abstract
AbstractDue to the generation of data sets and the rapid improvement of GPU computing performance, in-depth learning has undergone qualitative changes and development in the past decade. Various excellent convolutional neural network models have been implemented and verified, which accelerates the application of the convolutional neural network in various fields. A license plate recognition based on the convolutional neural network is pro-posed for the application of large underground parking lots. An end-to-end identification network framework without segmentation characters is designed. At the same time, sequence information is added to the convolutional neural network for improving the license plate recognition rate. Compared with the existing step-by-step license plate detection and recognition method, the joint solution of a single network can avoid the error accumulation in the intermediate process. At the same time, it can improve the accuracy rate, save the recognition time, accelerate the vehicle entering and leaving time and avoid traffic congestion.KeywordsConvolutional neural networkLicense plate recognitionEnd-to-end identification network
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
