Label identification method and device

Abstract

The invention provides a label identification method and device. The method includes the following steps that: an actual label image is obtained; binarization processing is performed on the actual label image; contour region images contained in the binarized actual label image are identified; contour region images, the number of the contour vertexes of which, satisfies the requirement of a preset vertex number, are filtered out from the contour region images, and therefore, contour region images, the number of the contour vertexes of which, satisfies the requirement of the preset vertex number, are obtain to form a valid image data set; shape correction processing is performed on the contour region images in the valid image data set according to the coordinates of the vertexes of the preset contour of a standard label image; and data information corresponding to the actual label image which has been subjected to the shape correction processing is identified. Since the shape of the actual label image is corrected, shape distortion influence on the label image, caused by different shooting angles, can be eliminated, and the identified data information is more accurate and reliable.

Description

technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to a label recognition method and device. Background technique [0002] In recent years, various types of labels, such as two-dimensional code labels, have been widely used in people's lives, such as for identifying objects, payment and so on. [0003] Take the use of a QR code label to identify an object in a shopping mall as an example. In practical applications, a QR code label for uniquely identifying the object can be generated according to certain label generation rules, and the QR code label can be pasted on the on the surface of the object. When the user purchases the object and pays, the settlement personnel can scan the QR code label with a scanner, thereby identifying and reading the data information corresponding to the label, and completing settlement and other processing. [0004] When identifying the label, you may encounter such a problem. The ...

AI Technical Summary

Problems solved by technology

The reason for the misrecognition results may be due to the influence of external factors

After research, it is found that different lighting conditions, different shooting or scanning angles often have a greater impact on the accuracy of recognition results.

Images