License plate recognition method and device
A technology of license plate recognition and license plate area, applied in character and pattern recognition, instruments, biological neural network models, etc., can solve problems such as poor recognition effect, inability to distinguish 0 degrees and 180 degrees, unfavorable deployment, etc.
Active Publication Date: 2021-01-08
南京风兴科技有限公司
View PDF5 Cites 3 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0004] The existing technology has a poor recognition effect on situations with large license plate angles, and cannot distinguish between 0 degrees and 180 degrees. The addition of a cyclic neural network leads to slower speeds, which is not conducive to deployment
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0032] In order to enable those skilled in the art to better understand the technical solutions in the embodiments of the present application, and to make the above-mentioned purposes, features and advantages of the embodiments of the present application more obvious and understandable, the technical solutions in the embodiments of the present application are described below in conjunction with the accompanying drawings The program is described in further detail. Apparently, the described exemplary embodiments are only some of the embodiments of the present application, but not all of the embodiments.
[0033] In order to solve the problem in the prior art that the recognition effect of the license plate with a large angle is poor, and it cannot distinguish between 0 degrees and 180 degrees, the use of a recurrent neural network leads to slower speed, which is not conducive to deployment. The license plate recognition method and device shown in the embodiment of the present ap...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses a license plate recognition method and device. The method comprises the steps of extracting license plate image features by adopting a first convolution feature extraction network added with a deformable convolution , wherein the first convolution feature extraction network comprises a head model network for extracting any quadrilateral area and a branch structure for predicting a quadrilateral angle, wherein the head model network for extracting any quadrilateral is used for extracting a plurality of any quadrilaterals and screening out an optimal quadrilateral, and the branch structure predicts the deviation angle between the central axis and the horizontal axis of the optimal quadrangle; converting the license plate image features to obtain a license plate area;and extracting character position information and category information of the license plate area by adopting a second convolution feature extraction network added with hole convolution, and generatinga license plate number according to the character position information and the category information. According to the invention, the license plate recognition speed can be improved, the deployment difficulty is reduced, the license plate directions at 0 degree and 180 degrees can be distinguished, and the method and device can adapt to various complex scenes and has very high recognition accuracy.
Description
technical field [0001] The invention relates to the technical field of security monitoring, in particular to a license plate recognition method and device. Background technique [0002] License plate recognition has a wide range of applications in the field of security monitoring technology, and can be applied to various occasions such as highway toll collection, highway law enforcement, highway inspection, vehicle scheduling, and vehicle detection. [0003] The existing license plate recognition technology uses the convolutional neural network to extract the license plate position information from the image containing the license plate, and obtains the circumscribed rectangle of the license plate. Through the coordinates of the circumscribed rectangle, the license plate area is cut out, and then the convolutional neural network and the recurrent neural network are used to extract the license plate position information. The location information and category information of th...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More IPC IPC(8): G06K9/32G06N3/04
CPCG06V20/63G06N3/045
Inventor 余江勇李辉
Owner 南京风兴科技有限公司