Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

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

A license plate recognition and data generation technology, applied in character and pattern recognition, image enhancement, image data processing, etc., can solve problems such as unsatisfactory recognition rate, high computational complexity, and resource consumption

Active Publication Date: 2020-07-07
SHANGHAI UNIV
View PDF4 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

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.

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 more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • License plate character recognition method based on data enhancement and data generation
  • License plate character recognition method based on data enhancement and data generation
  • License plate character recognition method based on data enhancement and data generation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0027] like figure 1 and Image 6 As shown, it is a method for recognizing license plate characters based on the neural network of data enhancement and data generation involved in this embodiment. Shadows caused by low light, overexposure, rain and sand and other factors. The shooting angle affects the deformation of the license plate. Shooting from the side or looking down will cause a relatively large degree of deformation of the characters. The real-time requirement means that the recognition speed of the license plate is very high. It is necessary to quickly recognize the characters of the license plate at the entrance of the ramp without causing road congestion.

[0028] The data enhancement and data generation method proposed in this embodiment only requires a small amount of manual marking of real license plates. The recurrent adversarial generation network requires a thousand or more real data, but these real data do not require manual annotation, because the traini...

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

No PUM Login to View More

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...

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
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/34G06K9/46G06K9/62G06N3/04G06N3/08G06T7/11
CPCG06T7/11G06N3/084G06T2207/20132G06V30/153G06V10/56G06N3/045G06F18/214Y02T10/40
Inventor 吴昌浩徐树公张舜卿曹姗
Owner SHANGHAI UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products