Artificial neural network-based license plate recognition learning method and system
An artificial neural network and license plate recognition technology, applied in the field of license plate recognition learning methods and systems based on artificial neural networks, can solve problems affecting license plate results, meet the requirements of reducing recognition distance and environment, improve license plate recognition results, and effectively The effect of identity
Inactive Publication Date: 2018-05-18
克立司帝控制系统(上海)股份有限公司
View PDF8 Cites 1 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0002] In the current license plate recognition system, the license plate is visually different in sunny weather, rainy, and snowy weather. At the same time, there are many types of license plate itself, with different shapes, colors, and sizes. Different angles will affect the final license plate result
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
[0031] The present invention will be described in detail below in conjunction with specific embodiments. The following examples will help those skilled in the art to further understand the present invention, but do not limit the present invention in any form. It should be noted that those skilled in the art can make several changes and improvements without departing from the concept of the present invention. These all belong to the protection scope of the present invention.
[0032] Such as figure 1 , 2 As shown, a kind of license plate recognition learning method based on artificial neural network provided by the invention comprises steps:
[0033] Artificial neural network building steps: use each license plate recognition device as an artificial neuron, form the artificial neural network of the license plate recognition system through the network, learn the sample license plate given by the license plate recognition device to obtain an experience table, and predict the r...
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 provides an artificial neural network-based license plate recognition learning method and system. The method comprises the following steps that: each license plate recognition instrumentis adopted as an artificial neural neuron, and the artificial neural network of a license plate recognition system can be obtained through the networking of the artificial neural neurons, and samplelicense plates given by the license plate recognition instruments are learned, so that an experience table is obtained, and a recognition result is predicted according to the experience table; by means of regression analysis, whether a plurality of characters of unified license plates or a plurality of characters of a plurality of license plates are related is judged, and the relation directions and relation intensities of the characters are obtained, and a mathematical model is established; target license plates are verified, so that the response variables and explanatory variables of the mathematical model are adjusted; and by means of classification analysis, sample classes to which new sample license plates belong are judged according to the features of the known sample license plates,and feature parameters are selected through calculation, a discriminant function is established, and the sample license plates are classified. With the method and system of the invention adopted, theeffective identity of a vehicle can be accurately recognized, requirements for recognition distances and environments are decreased, and installation and maintenance costs are saved.
Description
technical field [0001] The present invention relates to the technical field of vehicle identification, in particular to an artificial neural network-based license plate identification learning method and system. Background technique [0002] In the current license plate recognition system, the license plate is visually different in sunny weather, rainy, and snowy weather. At the same time, there are many types of license plate itself, with different shapes, colors, and sizes. Different angles will affect the final license plate result. [0003] Machine learning is a branch of artificial intelligence. Learning algorithms involve a large number of disciplines such as statistics, approximation theory, convex analysis, and computational complexity theory. Neural networks are computed by a large number of artificial neuron connections. The weights of neuron connections in a neural network and the excitation values of neurons change; the activation function defines how neur...
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): G06K9/00G06N3/08
CPCG06N3/08G06V20/54G06V20/625
Inventor 王玮
Owner 克立司帝控制系统(上海)股份有限公司