Real-time license plate recognition method based on deep learning in complex scene
A deep learning and complex scene technology, applied in the field of image processing technology and text recognition, can solve the problems of information loss, insufficient recognition ability of ALPR system, and limited types of license plate recognition, so as to avoid resource consumption, reduce network parameters and detection time overhead Effect
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Example Embodiment
[0026] figure 1 It is the overall flow chart of the license plate recognition system of the present invention. The license plate recognition process is divided into three steps:
[0027] The first step, the license plate area detection and classification network settings:
[0028] The deep learning object detection algorithm combined with SSD-MobileNet is the license plate area detection and classification method of the present invention, and the license plate area location and classification are simultaneously completed in an end-to-end network.
[0029] figure 2 It is a schematic diagram of the structure of the license plate detection classification network SSD-MobileNet.
[0030] This method realizes the detection and classification of five Chinese license plates (classes=5) including: blue license plate, yellow license plate, white license plate, black license plate and new energy license plate. First send the image to the feature extraction network. The feature extraction netw...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap