Unlock instant, AI-driven research and patent intelligence for your innovation.

A kind of multi-qr code recognition method

A recognition method and QR code technology, applied in the field of multi-QR code recognition, can solve the problems of poor QR code imaging quality, difficulty in balancing decoding accuracy and efficiency, and pseudo-position detection pattern interference, and achieve the effect of improving recognition performance.

Active Publication Date: 2019-08-13
福州觉感视觉软件科技有限公司
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Limited by the resolution of the camera, the imaging quality of the QR code is poor. It is necessary to increase the tolerance of the search position detection pattern, but at the same time it will bring interference from the pseudo position detection pattern. The traditional multi-QR code decoding method cannot adapt to the pseudo position detection pattern. the existence of
[0004] The number of QR codes to be searched is unknown in advance, so it is difficult to balance the accuracy and efficiency of decoding, and a stable search process is required

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A kind of multi-qr code recognition method
  • A kind of multi-qr code recognition method

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach

[0027] A kind of specific implementation mode of the present invention is as follows:

[0028] Such as figure 1 and figure 2 As shown, this method processes 8-bit grayscale images by default. If the obtained color image is converted into a grayscale image and then input, the original image P(x,y) is obtained, where x,y are pixel coordinates.

[0029] In step 1.1, filter the grayscale image P(x, y) first, and the options are Gaussian filtering or mean filtering with a convolution kernel of 3×3 to reduce noise interference.

[0030] Step 1.2, increase the contrast of the image and strengthen the features of the QR code. The function of step 2.1 is to prevent the noise signal from being amplified in this step. You can use the Adaptive Histogram Equalization Algorithm (AHE), and setting the window parameter to 64*64 is a reasonable size. This method can well adapt to the characteristics of large changes in gray value in large-resolution images, and can increase the contrast o...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The present invention provides a multi-QR code identification method. An original image is filtered, the contrast of the original image is amplified, the two-dimensional features are enhanced, and multiple position detection graphs are searched from the image; the position detection graphs, belonging to the same QR code, in the multiple position detection graphs are set to be the same group; and the limited calculation resource is flexibly distributed in each part, and in the condition of ensuring the accuracy, and the consumed time of the process is controlled in the acceptable range.

Description

technical field [0001] The invention relates to a multi-QR code recognition method. Background technique [0002] As a novel way of information storage and transmission, two-dimensional codes are widely used in the links of certificates, bills, commodities and cargo transportation. Compared with other forms of two-dimensional codes, QR codes have obvious characteristics and can be quickly located. It has the characteristics of recognizing and being able to compile Chinese characters, so it is well supported on the mobile phone terminal. As QR codes are valued by more and more companies, the requirements for its identification methods are getting higher and higher. Different from mobile phone scanning codes, the pictures taken by industrial cameras in the process of automated production have the following characteristics that will cause Difficulties in identifying codes: [0003] Limited by the resolution of the camera, the imaging quality of the QR code is poor. It is nece...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G06K7/14
CPCG06K7/1417G06K7/1447G06K7/1478
Inventor 林宇吴闽帆黄旭东
Owner 福州觉感视觉软件科技有限公司