Unlock instant, AI-driven research and patent intelligence for your innovation.

A Lightweight Neural Network-Based License Plate Recognition Method

A neural network and license plate recognition technology, applied in the direction of neural learning methods, biological neural network models, neural architectures, etc., can solve problems such as limitations of accuracy and generalization capabilities, speed impact, etc., to solve the misalignment of input and output, improve The effect of detecting speed and reducing the amount of parameters

Active Publication Date: 2022-07-08
UNIV OF ELECTRONICS SCI & TECH OF CHINA
View PDF9 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This method is divided into two steps of character area segmentation and character classification. It is not an end-to-end method, and the speed will be affected accordingly.
And the segmentation based on the license plate character area is based on the traditional algorithm, and the accuracy and generalization ability have certain limitations.

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 more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A Lightweight Neural Network-Based License Plate Recognition Method
  • A Lightweight Neural Network-Based License Plate Recognition Method
  • A Lightweight Neural Network-Based License Plate Recognition Method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0064] The invention designs a license plate recognition method based on a lightweight neural network, adopts the CTC loss function to train the lightweight neural network model, realizes end-to-end training without segmentation, and effectively solves the situation that the input and output are not aligned, especially The following setting methods are adopted: including the preparation of the data set, the construction of the lightweight neural network model and the recognition of the license plate,

[0065] The preparation of the data forms a license plate picture with the license plate number as the file name, specifically:

[0066] First, obtain video screenshots from road videos, form sample images, and save them in the images folder; preferably, collect several videos of driving vehicles from the monitoring probe, and save one picture per second, a total of Collect more than 30,000 images (sample images) and save them to the images folder, where the sample images are all...

Embodiment 2

[0080] This embodiment is further optimized on the basis of the above-mentioned embodiment, and the same parts as the above-mentioned technical solutions will not be repeated here. In order to further realize the present invention, the following setting methods are specially adopted: the step 1) specifically It is: input the matrix with dimension [32, 3, 24, 92] into the first two-dimensional convolutional layer, after normalization operation (batch normalization) and nonlinear activation (relu), the dimension is [32, 64, 22 , 92] the first feature matrix x1; the first two-dimensional convolutional layer is provided with 64 convolution kernels with a stride of 1 and a size of 3×3.

Embodiment 3

[0082] This embodiment is further optimized on the basis of any of the above-mentioned embodiments, and the same parts as the foregoing technical solutions will not be repeated here. In order to better realize the present invention, the following setting method is specially adopted: the step 2 )Specifically:

[0083] 2.1) Input the first feature matrix x1 into the pooling layer to obtain a feature matrix of [32, 32, 20, 90]; in the step 2.1), the pooling area size is (1, 3, 3) and the step size is (1, 1, 1) pooling layer;

[0084] 2.2) Input the feature matrix obtained in step 2.1) into a special convolutional layer (named small_basic_block), and the output result after normalization operation (batch normalization) and nonlinear activation (relu), the dimension is [32, 128, 20, 90 ] of the second feature matrix x2.

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

No PUM Login to View More

Abstract

The invention discloses a license plate recognition method based on a lightweight neural network, including the preparation of a data set, the construction of a lightweight neural network model, and the recognition of the license plate. The construction of the lightweight neural network model includes the following steps : 1) form the first characteristic matrix x1; 2) form the second characteristic matrix x2; 3) form the third characteristic matrix x3; 4) form the fourth characteristic matrix x4; 5) combine the first characteristic matrix x1, the second characteristic matrix x2, the third feature matrix x3, the channels of the fourth feature matrix x4 are fused, and then the feature vector is obtained through the convolution layer with a convolution kernel size of 1×1 and a stride of 1; 6) Based on the CTC loss function to achieve lightweight training of high-level neural network model; using CTC loss function for lightweight neural network model training to achieve end-to-end training without segmentation, effectively solving the situation of input and output misalignment.

Description

technical field [0001] The invention relates to the fields of pattern recognition technology, traffic monitoring technology and the like, in particular, to a license plate recognition method based on a lightweight neural network. Background technique [0002] License plate recognition is a crucial link in the modern intelligent transportation system and the core function of the intelligent transportation system. It uses technical means to extract the license plate number of the vehicle to obtain vehicle information. In my country, motor vehicle license plates need to be registered with the traffic management department. There is a one-to-one relationship between license plates and vehicles. Therefore, information acquisition, management and monitoring of motor vehicles can be performed according to motor vehicle license plates. In this case, a license plate recognition system is required to efficiently and accurately collect license plate number information quickly. [0003...

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
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G06V20/54G06N3/04G06N3/08G06T3/00
CPCG06N3/08G06V20/54G06V20/625G06N3/045G06T3/02Y02T10/40
Inventor 张裕星殷光强李耶杨晓宇殷雪朦李慧萍黄方正
Owner UNIV OF ELECTRONICS SCI & TECH OF CHINA