License plate character recognition method based on data enhancement and data generation

Abstract

The invention discloses a license plate character recognition method based on data enhancement and data generation. According to the method, a simulated license plate picture can be randomly generated; after the simulated license plate picture is obtained by the image generator of a cyclic adversarial network, and the simulated license plate picture is mixed with a simulated license plate pictureand an enhanced data picture to generate training data, so that optimization training can be trained on a license plate recognition network; and finally, the trained recognition network is subjected to rapid license plate recognition. According to the method of the invention, a license plate can be correctly and rapidly identified under the influence of low light, low resolution, motion blur and other severe conditions. Meanwhile, a large amount of data needed by neural network training is obtained in a data enhancement and data generation mode, and a large amount of manually-labeled data is not needed.

Description

technical field [0001] The invention relates to a technology in the field of traffic information control, in particular to a method for recognizing license plate characters based on data enhancement and data generation. Background technique [0002] License plate character recognition systems need to cope with challenges such as low light, low resolution, motion blur and other harsh conditions. Although the accuracy rate of the existing deep neural network method for this type of license plate character recognition is much higher than that of the traditional method, it faces problems such as difficult training data collection and labeling. Actual data is not readily available, the acquisition process is slow, and the data needs to be processed and annotated before it can be used for training. For higher annotation accuracy, human inspection is also required. [0003] In the existing technology, there is a method of segmenting the image content and performing separate recog...

AI Technical Summary

Problems solved by technology

However, the former has high computational complexity and the recognition rate is not ideal. Although the latter does not require additional image segmentation, its neural network needs to be trained with a large number of samples to achieve a certain recognition rate, and the training process is also quite resource-intensive.

Images