License plate recognition system based on deep neural network

Abstract

The invention discloses a license plate recognition system based on a deep neural network. The license plate recognition system comprises a license plate extraction step, a license plate recognition step and a data set experiment result step. S1, license plate extraction: license plate extraction is the most critical part in a license plate recognition system, directly affects the quality of a subsequent license plate recognition result, and comprises three parts: license plate positioning, license plate segmentation and license plate correction; multiple license plate positioning methods areavailable; according to the license plate recognition system based on the deep neural network, a license plate segmentation network based on the deep convolutional neural network is provided, a license plate pixel region can be directly segmented, end-to-end training of license plates of various countries is supported, and the license plate recognition network supporting variable length based on the deep convolutional neural network is provided. Characters do not need to be pre-segmented, the license plate sequence can be directly output only by decoding network output, and end-to-end trainingof license plates of all countries is supported.

Description

technical field [0001] The invention relates to the technical field of license plate recognition, in particular to a license plate recognition system based on a deep neural network. Background technique [0002] With the rapid development of the economy, the increasing number of vehicles makes the license plate recognition technology more and more important in our social life. Traffic management, digital monitoring, vehicle identification, and parking management all have extremely high demands on license plate recognition technology. As a complex problem, license plate recognition faces many challenges: blurry images, low-light images, diversity of license plates (license plates from different countries), physical factors and weather interference, etc., all of which will lead to errors in license plate segmentation and recognition. Therefore, a robust license plate recognition system needs to be able to cope with various challenges in reality and maintain high-precision rec...

AI Technical Summary

Problems solved by technology

[0006] The purpose of the present invention is to provide a license plate recognition system based on a deep neural network, to solve the above-mentioned background technology because the binary image or intermediate representation is used as input, so the quality of character segmentation is affected by input noise, low resolution, fuzzy or Deformation factors have a greater influence; character recognition usually uses an optical character recognition method (OCR) for recognition, and the quality of recognition depends heavily on the results of character segmentation

Images