Vehicle bottom shadow characteristics-based rapid license plate positioning method

Abstract

The invention discloses a method for rapidly positioning a license plate in a video image. By the method, license plate candidate regions are rapidly segmented by utilizing a gradient shadow detection method and a one-dimensional filtering technology on the basis of vehicle bottom shadow characteristics and then are positioned precisely. The method comprises the following steps of: (1) extracting a frame of image in video and segmenting processing regions; (2) graying the images of the processing regions and performing gray stretch; (3) performing primary coarse positioning according to the vehicle bottom shadow characteristics; (4) de-noising by a one-dimensional filtering method and determining candidate regions; and (5) precisely positioning the candidate regions by using morphology. The method has the advantages of easiness in implementation, high robustness, high precision, high real-time performance and the like, and can provide a new real-time and reliable rapid positioning method for the license plate positioning in license plate identification.

Description

technical field [0001] The invention belongs to the technical field of license plate recognition, and is a rapid license plate location method based on the shadow features of the bottom of the car. The method combines the shadow features of the bottom of the car and uses a gradient shadow detection method and a one-dimensional filtering technology to perform rough positioning on the possible area of ​​the license plate. Combined with mathematical morphology to accurately locate the license plate. Background technique [0002] License Plate Recognition (LPR) technology is one of the key technologies in Intelligent Transportation Systems (ITS), which can be applied to high-definition bayonet security systems, intersection traffic parameter collection systems, expressway management systems, etc. The accuracy of license plate location directly determines the effect of subsequent character segmentation and recognition. The purpose of license plate location is to accurately segme...

AI Technical Summary

Problems solved by technology

However, the color itself contains complex information and requires a large amount of calculation, and when the license plate is not clear, it will inevitably affect the positioning effect

In the method based on the dense hopping of the vertical edge of the license plate gray image, Hamid Mahini et al. published the paper "An efficient features-based license plate localization method ( An efficient multi-feature-based license plate location method)” locates the license plate according to the vertical edge dense jump features generated between the license plate characters, but the positioning accuracy is not high when there are rich texture features near the license plate or the license plate is blurred

In the method of obtaining license plate position based on horizontal and vertical projection features, W.B.Horng published "Efficiently locating vehicle license plates" in "12thIPPR Conference on Computer Vision Graphics and Image Processing (12th World Computer Vision and Image Processing Symposium)" in 1999. Based on vertical line detection (efficient license plate location based on vertical line detection)" According to the horizontal and vertical texture of the license plate is dense and rich, but the body image is just the opposite, the horizontal and vertical projection method is used to capture the position of the license plate, which was used at that time method, when the front or rear of the car contains many other texture-rich parts, it is difficult to locate

In the method based on mathematical morphology, the paper "A Morphological-Based License Plate Location" published by Rezaie et al. in the "IEEE International Conference on Image Processing (International Conference on Image Processing of the International Institute of Electrical and Electronics Engineers)" in 2007 makes full use of the license plate The shape characteristics of the license plate (the area of ​​the license plate character group is rectangular after morphological processing) to locate the license plate. The selection of structural elements in this method should be determined according to the size of the strokes of the characters in the license plate and the interval between characters, so the scope of the algorithm is limited and accurate. degree is not high

Images