Automatic identification system of number plate on the basis of simplified convolutional neural network

Abstract

The invention discloses an automatic identification system of a number plate on the basis of a simplified convolutional neural network. The convolutional neural network comprises an input layer, a convolutional layer, a pooling layer, a hidden layer and a classification output layer and solves the problem of number plate identification under a daily background. The number plate identification comprises the following steps: positioning, segmenting and identifying. The invention puts forward a positioning method which extracts colorful edges by colorful edge information and colorful information. Since parameters in the method are set on the basis of color features, noise in the daily background can be effectively inhibited, and input images of different sizes can be subjected number plate extraction. The automatic identification system omits a front convolutional layer of a traditional depth convolutional neural network and only keeps one layer of convolutional layer and one hidden layer. As the supplementation of a missing convolutional layer and the strengthening of input features, a gray level edge image obtained by a Sobel operator is used as the input of a colorful image, i.e., coarsness features which are artificially extracted replace features extracted by multiple convolutional layers of the traditional convolutional neural network.

Description

technical field [0001] The invention relates to the field of license plate recognition, in particular to an automatic license plate recognition system based on a simplified convolutional neural network, which solves two technical problems of license plate location and automatic recognition in the daily background. Background technique [0002] Technology is constantly updating and developing, which has profoundly affected people's daily life, and the field of intelligent vehicle management is no exception. The concept of intelligent transportation system was put forward in the 19th century and has become the development trend of road transportation in the world today. License plate recognition technology is based on computer technology, image processing technology, and pattern recognition to establish a vehicle feature model, such as license plate, model, color, etc., and realize automatic recognition. The parking space guidance technology guides the vehicle to the vacant p...

AI Technical Summary

Problems solved by technology

In the license plate character recognition task, due to the regular shape of the license plate characters, the changes are not as complicated as handwritten fonts. However, the traditional deep convolutional neural network has a complex structure and many parameters, which not only reduces the training speed, but also makes it difficult for the neural network to converge to a satisfactory result. As a result, underfitting is prone to occur, and the recognition effect is not good

Images