Recognition method of license plate number of motor vehicle

Abstract

The invention relates to a recognition method of a license plate number of a motor vehicle, and belongs to the technical field of license plate number recognition. The recognition method comprises carrying out median filtering and noise reduction to an input image containing a license plate, locating multiple license plate areas by utilizing a binarization processing method and a morphological processing method, carrying out rotation correction and edge removing processing to the license plate areas one by one, carrying out character cutting by utilizing a vertical projection method, carrying out further edge removing processing to obtained character blocks in a cutting mode, carrying out character recognition by utilizing an enhanced edition template matching method, and therefore achieving fast and accurate license plate recognition. The recognition method improves the precision of license plate location, and fast and precise location of the license plate is achieved. The recognition method can be used in a real-time license place recognition system, and for processing high-speed data flow, meanwhile is high in recognition accuracy, and has certain robustness on illumination variation, influence of rain and mist, indistinct license plates, broken characters and other bad conditions.

Description

technical field [0001] The invention relates to a method for recognizing a motor vehicle license plate number, and belongs to the technical field of license plate recognition. Background technique [0002] Vehicle License Plate Recognition (VLPR) refers to a technology that can detect vehicles on the monitored road and automatically extract vehicle license information (including Chinese characters, English letters, Arabic numerals and license plate colors) for processing. License plate recognition is one of the important components of modern intelligent transportation systems, and it is widely used. Based on digital image processing, pattern recognition, computer vision and other technologies, it analyzes the vehicle images or video sequences captured by the camera, and obtains the unique license plate number of each car, thus completing the recognition process. Through some follow-up processing methods, functions such as parking lot fee management, traffic flow control ind...

AI Technical Summary

Problems solved by technology

The advantages of high-definition are self-evident, but it will also cause some problems in license plate recognition. Due to the wide coverage of high-definition pictures, multiple license plate recognitions may appear in the picture at the same time. Most of the existing license plate recognition systems focus on processing only Contains an image of a car. In the case where the input image contains many motor vehicles, the existing license plate recognition system does not show high performance.

In addition, the high-definition video stream is very large, which puts forward high requirements on the processing speed of the license plate recognition system. If the processing speed is too slow, it may cause missing vehicles, making it difficult to improve the vehicle capture rate and license plate recognition accuracy.

[0006] In addition, currently in the part of the license plate recognition algorithm, since the license plate in our country not only contains English letters and Arabic numerals, but also contains Chinese characters with complicated strokes, the recognition difficulty is much greater than that of foreign countries that only recognize letters and numbers. The road conditions are poor, the license plate is seriously polluted, and the license plate of the actual vehicle will be affected by mud, oil, paint, etc. The characters of the license plate are often broken. Fuzzy, making it more difficult to recognize license plate characters

The template matching method is widely used in the field of automatic license plate recognition because of its fast speed, but under the above harsh conditions, the accuracy of the template matching method is greatly limited. In addition, the template matching method is not good for rotation resistance. , which also limits its scope of application to some extent

Using other methods such as neural networks for recognition will bring about a considerable improvement in processing complexity. Generally speaking, the existing license plate recognition methods have high processing speed and high recognition accuracy at the same time. There are still many deficiencies

Images