License plate character recognition method based on K-L transform and LS-SVM

Abstract

The invention discloses a license plate character recognition method based on the combination of K-L transformation and LS-SVM. Firstly, the method of K-L transformation is adopted to carry out dimensionality reduction of features to a character image of the license plate; then, according to the permutation features of the character image of the license plate, the cluster distance method of cluster analysis is adopted, and four groups of optimal LS-SVM classifiers of binary trees are designed to respectively realize the recognition of English alphabets, numbers, characters and English alphabets plus numbers in license plate characters. The method adopted by the invention better solves the problem that other license plate character recognition methods have unidentifiable fields, does not require to traverse all classifiers when classifying, thus greatly improving classifying efficiency, shortening the feature extraction process of the license plate characters, reducing the calculation work of sample training and the recognition time of the license plate characters and simultaneously improving the recognition rate of a license plate recognition system and the capability of classification and promotion.

Description

technical field [0001] The invention relates to an automatic recognition method of a character image of a motor vehicle license plate, belonging to the technical fields of pattern recognition, computer image processing and intelligent transport system (Intelligent Transport System, ITS) control. Automatic license plate recognition technology is an important part of intelligent transportation system. Background technique [0002] The license plate recognition system (License Plate Recognition System LPRS) composed of automatic license plate recognition technology is a highly intelligent comprehensive integrated system based on image processing, computer vision, pattern recognition and other technologies, as an important means of road traffic management automation and vehicle monitoring It plays an important role in road traffic monitoring and control. The license plate recognition system consists of two parts: hardware and software: on the hardware, it consists of controllab...

AI Technical Summary

Problems solved by technology

[0007] ①Template matching-it is easy to lead to poor discrimination ability of similar characters, and slow recognition speed due to too large dimension of feature data

For characters with deformation, displacement, tilt, etc., it is easy to cause misrecognition

[0008] ② Neural network - Although it has strong pattern classification ability, the convergence speed of the algorithm is slow, and its global optimality cannot be guaranteed, and it faces problems such as the selection of network input data and the design of network structure

Using the neural network method for license plate character recognition, the recognition rate largely depends on the number of training samples, and the recognition accuracy is relatively low in the absence of feature extraction.

[0009] ③ Feature matching method - because the description and operation of structural features take up a lot of storage and computing resources, the algorithm is relatively complex to implement and the recognition speed is slow

However, SVM also has deficiencies, such as: the classification accuracy for complex problems is not high enough; when the training sample aliasing is serious, the SVM classification surface is too complex, which is prone to over-learning; for some complex cases, due to the large SVM set, Will result in slower decision making etc.

Images