Driver license detection identification method based on internal feature and text field layout in complex scene

Abstract

The invention provides a driver license detection identification method based on an internal feature and a text field layout in a complex scene, which comprises the following steps: firstly, preprocessing an image by using a technique of normalization and SSR enhancement and the like, repairing a frame of a vehicle model frame in the certificate by using morphological operation and line segment repair, obtaining the vehicle model frame contour through the contour detection and filtering, solving the intersection point of the fitting straight line to obtain the vehicle model frame vertex, and combining the standard driving license layout to obtain the driving license area image. Then, analyzing the integral projection information to perform accurate positioning on the position of the vehicle model text area, starting from the position, carrying out coarse positioning and fine positioning on the adjacent non-positioning area at each time to obtain a text area image, and performing tilt correction on the area above the address bar. Finally, combining a plurality of methods to binarize the text area, and identifying characters by using a special character recognition engine. The methodis quick and robust, can quickly and rapidly identify the captured images under various complex scenes, and has better practicability and higher application value.

Description

technical field [0001] The invention belongs to the field of computer vision and is applied to a driver's license recognition system, in particular to a driver's license detection and recognition method based on internal features and text domain layout in complex scenes. Background technique [0002] The driver's license is the driver's driving qualification certificate, through which the driver's driving qualification can be determined. It has always played an important role in traffic law enforcement. In the process of traffic law enforcement, it is often necessary to extract the information in the driver's license. Now. With the continuous development of the social credit system, the driver's license is not only limited to the use of traffic law enforcement, but also as a personal credit certificate, which is included in the credit system, so the driver's license information entry has become a very important work. However, the traditional manual input method is inefficie...

AI Technical Summary

Problems solved by technology

[0003] However, the driver's license pictures taken by general handheld devices often have a series of poor shooting effects such as uneven illumination and document tilt and deformation, and at the same time, the processing must be fast and timely. Therefore, a reliable, accurate, robust and fast driving license identification methods become more important

Images