17914993. METHOD FOR RECOGNIZING LICENSE PLATE CHARACTERS, ELECTRONIC DEVICE AND STORAGE MEDIUM simplified abstract (BOE TECHNOLOGY GROUP CO., LTD.)
METHOD FOR RECOGNIZING LICENSE PLATE CHARACTERS, ELECTRONIC DEVICE AND STORAGE MEDIUM
Organization Name
BOE TECHNOLOGY GROUP CO., LTD.
Inventor(s)
METHOD FOR RECOGNIZING LICENSE PLATE CHARACTERS, ELECTRONIC DEVICE AND STORAGE MEDIUM - A simplified explanation of the abstract
This abstract first appeared for US patent application 17914993 titled 'METHOD FOR RECOGNIZING LICENSE PLATE CHARACTERS, ELECTRONIC DEVICE AND STORAGE MEDIUM
Simplified Explanation
The patent application describes a method and apparatus for recognizing characters on license plates using a convolutional neural network. The method involves obtaining a vehicle image, locating the license plate area, and extracting features from the license plate image using a convolutional neural network with a residual network structure. This approach effectively avoids gradient vanishing and reduces feature loss, allowing for accurate recognition of license plate characters using a bidirectional recurrent neural network model.
- The method uses a convolutional neural network with a residual network structure for feature extraction.
- It avoids the need for character segmentation by directly recognizing the whole license plate.
- The approach improves recognition speed and accuracy by avoiding segmentation and separate recognition for license plate characters.
Potential Applications
This technology can be applied in various areas where license plate character recognition is required, such as:
- Traffic management systems: Automated recognition of license plate characters can assist in traffic monitoring, toll collection, and parking management.
- Law enforcement: Police departments can use this technology for automatic identification of vehicles involved in crimes or traffic violations.
- Access control: It can be used in gated communities, parking lots, and secure facilities to grant or deny access based on license plate recognition.
Problems Solved
The technology solves the following problems:
- Eliminates the need for character segmentation: Traditional methods require segmenting license plate characters before recognition, which can be complex and time-consuming.
- Improves recognition speed: By directly recognizing the whole license plate, the technology reduces the processing time compared to segmenting and recognizing individual characters.
- Enhances recognition accuracy: The use of a convolutional neural network with a residual network structure reduces feature loss and improves the accuracy of license plate character recognition.
Benefits
The technology offers several benefits:
- Faster and more accurate license plate character recognition: By avoiding character segmentation, the method improves recognition speed and accuracy.
- Simplified implementation: The use of a convolutional neural network with a residual network structure simplifies the recognition process and eliminates the need for complex character segmentation algorithms.
- Improved efficiency in various applications: The technology can enhance the efficiency of traffic management systems, law enforcement, and access control systems by automating license plate character recognition.
Original Abstract Submitted
A license plate character recognition method and apparatus, an electronic device, and a storage medium. The method comprises: after obtaining a vehicle image captured by an image capturing device, positioning a vehicle plate area in the vehicle image to obtain a license plate image, and performing feature extraction on the license plate image by means of a convolutional neural network comprising a residual network structure. Gradient vanishing is effectively avoided and feature loss in a convolutional process of the convolutional neural network is reduced, so that a bidirectional recurrent neural network model can accurately recognize license plate characters in the license plate image on the basis of feature information of the license plate image. Therefore, character segmentation for a license plate is not needed, license plate characters on the license plate can be obtained by directly recognizing the whole license plate, segmentation and separate recognition for the license plate characters are avoided, and the recognition speed and the recognition accuracy are improved.
