Method for recognizing license plate character based on wide gridding characteristic extraction and BP neural network

Abstract

The invention discloses a vehicle license plate character recognition method based on rough grid feature extraction and a BP neural network. The method comprises the following steps: (1). preprocessing a vehicle license plate image to eliminate various interferences and obtain a minimum vehicle license plate region; (2). segmenting the vehicle license plate characters by combining vertical projection and a drop-fall algorithm; (3). screening the segmentation results to eliminate interferences of vertical frames, separators, rivets and the like; (4). normalizing the characters according to the position of a centre of mass; (5). taking each pixel of a normalized characters dot-matrix as a grid to extract the original features of the characters; (6). designing the BP neural network with a secondary classifier according to the situation of the vehicle license plate; and (7). reasonably constructing a training sample database to train the neural network, and adjusting the training samples by the recognition effect to realize accurate recognition of the network. The method effectively eliminates the noise interference, quickly and accurately segments the characters, steadily and effectively recognizes Chinese characters, and realizes the balance between real-time property and accuracy in the whole recognition course.

Description

technical field [0001] The invention relates to a license plate character recognition technology. Background technique [0002] With the license plate recognition (LPR) system being more and more widely used in road toll management systems, traffic monitoring, parking lot management, license plate verification, traffic statistics and other occasions, how to achieve more accurate and efficient license plate recognition A hot spot of current research. License plate character recognition is a key step in the automatic license plate recognition system, and the quality of the recognition effect directly affects the performance of the entire recognition system. [0003] For the obtained license plate image, the usual recognition includes two key steps of license plate character segmentation and license plate character recognition. [0004] License plate character segmentation is to divide the license plate area into a single character area to facilitate the next character recogn...

AI Technical Summary

Problems solved by technology

[0007] In order to overcome the disadvantages of the existing license plate character recognition method that the character segmentation algorithm is greatly affected by the license plate image quality, the recognition algorithm has poor recognition effect on low-quality character images, and the poor recognition effect on Chinese characters, the present invention provides a method with poor segmentation effect. Affected by the image quality of the license plate, the recognition effect on Chinese characters is good. A license plate character recognition method based on coarse grid feature extraction and BP neural network

Images