Real-time train number recognition method and apparatus

Abstract

The present invention relates to the field of image recognition, and for the problems existing in the prior art, provides a real-time train number recognition method. The method comprises: a step of initial positioning of a train number region: calculating an optimal gray level through a local binary model on input image data, finally obtaining a whole gray level value corresponding to the optimalgray level, and according to the gray level value, positioning the rectangular coordinate containing train number characters from the input image by using a linear two-class classifier; a step of character segmentation: using a dynamic binary method and a connected component analysis algorithm to divide the rectangular coordinate region containing the train number characters into individual characters; and a step of character recognition: performing character recognition on the train number according to the SVM classifier.

Description

technical field [0001] The invention relates to the field of image recognition, in particular to a real-time train number recognition method and device. Background technique [0002] The current train number recognition mainly has the following disadvantages: (1) offline recognition, that is, the recognition result is reported after a long time after the train passes. It may take the second day to recognize the train number of the train, and the time lag affects the work; (2) The type of image for identifying the train number is single. The car number recognition of existing manufacturers in the market either supports area array camera images or supports Line array camera images, there are few car number recognition algorithms that support both area scan cameras and line scan cameras; (3) There are few types of car numbers that support recognition, and the existing train numbers include those starting with HXD for ordinary speed electric locomotives, Shaoshan type car numbe...

AI Technical Summary

Problems solved by technology

[0002] The current train number recognition mainly has the following disadvantages: (1) offline recognition, that is, the recognition result is reported after a long time after the train passes. It may take the second day to recognize the train number of the train, and the time lag will affect the work; (2) The type of image for identifying the train number is single. The car number recognition of existing manufacturers in the market either supports area array camera images, or does not support Line array camera images, there are few train number recognition algorithms that support both area scan cameras and line scan cameras; (3) There are few types of train numbers that support recognition, and the existing train numbers include those starting with HXD for ordinary speed electric locomotives, Shaoshan type car number, bullet train number, two-way train number, etc., the existing train number recognition cannot fully support the above types of car number recognition; (4) the recognition rate is low, the current existing train number recognition rate The average is 92%, which is far from the 99% stipulated by the Railway Corporation.

Images