CN109543692B - Binaryzation method special for image containing QR code - Google Patents
Binaryzation method special for image containing QR code Download PDFInfo
- Publication number
- CN109543692B CN109543692B CN201811424622.1A CN201811424622A CN109543692B CN 109543692 B CN109543692 B CN 109543692B CN 201811424622 A CN201811424622 A CN 201811424622A CN 109543692 B CN109543692 B CN 109543692B
- Authority
- CN
- China
- Prior art keywords
- gray
- value
- threshold
- binarization
- code
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/28—Quantising the image, e.g. histogram thresholding for discrimination between background and foreground patterns
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06K—GRAPHICAL DATA READING; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
- G06K7/00—Methods or arrangements for sensing record carriers, e.g. for reading patterns
- G06K7/10—Methods or arrangements for sensing record carriers, e.g. for reading patterns by electromagnetic radiation, e.g. optical sensing; by corpuscular radiation
- G06K7/14—Methods or arrangements for sensing record carriers, e.g. for reading patterns by electromagnetic radiation, e.g. optical sensing; by corpuscular radiation using light without selection of wavelength, e.g. sensing reflected white light
- G06K7/1404—Methods for optical code recognition
- G06K7/1408—Methods for optical code recognition the method being specifically adapted for the type of code
- G06K7/1417—2D bar codes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06K—GRAPHICAL DATA READING; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
- G06K7/00—Methods or arrangements for sensing record carriers, e.g. for reading patterns
- G06K7/10—Methods or arrangements for sensing record carriers, e.g. for reading patterns by electromagnetic radiation, e.g. optical sensing; by corpuscular radiation
- G06K7/14—Methods or arrangements for sensing record carriers, e.g. for reading patterns by electromagnetic radiation, e.g. optical sensing; by corpuscular radiation using light without selection of wavelength, e.g. sensing reflected white light
- G06K7/1404—Methods for optical code recognition
- G06K7/146—Methods for optical code recognition the method including quality enhancement steps
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Toxicology (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Electromagnetism (AREA)
- Health & Medical Sciences (AREA)
- Multimedia (AREA)
- Quality & Reliability (AREA)
- Facsimile Image Signal Circuits (AREA)
- Character Input (AREA)
Abstract
The application discloses a binarization method special for an image containing a QR code, which comprises the following steps: step 1, dividing a QR code image to be identified into a plurality of view widgets according to a preset dimension; step 2, determining a binarization threshold value corresponding to the view small window according to pixel points contained in the view small window and all rows of pixel points in the QR code image to be identified corresponding to the view small window; and 3, performing binarization processing on pixel points in the QR code image to be recognized according to a binarization threshold value to generate a QR code binarization image. Through the technical scheme in the application, the binarization processing effect of the QR code image under the condition of uneven illumination is optimized, and the identification capability of the QR code image is improved.
Description
Technical Field
The application relates to the technical field of binaryzation, in particular to a special binaryzation method for an image containing a QR code.
Background
Quick Response matrix Code (QR Code) was invented by DENSO WAVE corporation of japan in 1994, and is one of many two-dimensional barcodes, and is the most common two-dimensional barcode at present. The QR code uses four standardized codes of numbers, alphanumerics, binary systems and Chinese characters, stores data information in longitudinal and transverse dimensions, and inherits the characteristics of a positioning point structure, a data fault-tolerant mechanism and the like of the two-dimensional code. The binaryzation of the image containing the QR code is a key link for extracting effective area information, and the quality of the image containing the QR code after binaryzation directly influences the implementation of the subsequent decoding step. The core of the binarization algorithm is a selection rule of a threshold value, and the threshold value of the current general image binarization algorithm is mainly divided into a global threshold value and a local threshold value.
In the prior art, the binarization algorithm of the global threshold is only suitable for processing images with uniform illumination and highly ideal image quality. For the binarization algorithm of the local adaptive threshold, although an image with uneven illumination which cannot be processed by the global threshold is improved, no consideration is given to the situation that when all pixel gray values in a plurality of continuous local adaptive windows are in a highly concentrated normal distribution with extremely small variance, that is, the local adaptive windows fall on the homochromatic regions of the QR code image, the homochromatic regions are changed into non-homochromatic regions after binarization with a high probability, and information of the regions is damaged.
Disclosure of Invention
The purpose of this application lies in: the calculation speed of the local threshold algorithm is improved, and the binarization processing effect of the QR code image under the condition of uneven illumination is optimized.
The technical scheme of the application is as follows: a binarization method special for an image containing a QR code is provided, and the method comprises the following steps: step 1, dividing a QR code image to be identified into a plurality of view widgets according to a preset dimension; step 2, determining a binaryzation threshold value corresponding to the view small window according to pixel points contained in the view small window and all lines of pixel points in the QR code image to be identified corresponding to the view small window; and 3, performing binarization processing on pixel points in the QR code image to be identified according to a binarization threshold value to generate the QR code binarization image.
In any one of the above technical solutions, further, step 1 specifically includes: step 11, carrying out gray processing on a QR code image to be recognized; and step 12, generating a plurality of view widgets according to the preset dimensionality and the processed QR code image to be identified.
In any one of the above technical solutions, further, before step 12, the method further includes: adding redundant pixel points at the tail end of the QR code image to be identified after graying processing according to the number of columns in the preset dimension, wherein the preset dimension is 1 x n dimension, the number of columns is n, and the number of columns is a positive integer greater than or equal to 10;
in any one of the above technical solutions, further, step 2 specifically includes: step 21, calculating a first gray average value of pixel points contained in the view small window, and calculating a first gray threshold value of the view small window according to a preset correction coefficient and the first gray average value; step 22, calculating second gray level mean values of all line pixel points in the QR code image to be identified corresponding to the view small window, and calculating second gray level threshold values of the line pixel points according to a preset correction coefficient and the second gray level mean values; step 23, calculating a third gray threshold value according to the first gray threshold value and the second gray threshold value by adopting a weighting algorithm; and 24, determining a binarization threshold of the view small window according to the size relation between the gray value variance of the pixel points in the view small window and a preset variance threshold, wherein the binarization threshold is one of a first gray threshold and a third gray threshold.
In any of the above technical solutions, further, the step 23 of calculating a third grayscale threshold specifically includes: setting the first weight value to be larger than the second weight value; calculating a third gray threshold according to a weighting calculation formula, the first weight, the second weight, the first gray threshold and the second gray threshold, wherein the weighting calculation formula is as follows:
in the formula, TH crct Is a third gray scale threshold, w 1 Is the first weight, TH 1 Is a first gray scale threshold, w 2 Is the second weight, TH 2 Is the second gray scale threshold.
In any of the above technical solutions, further, the first weight w 1 Value of 9, the second weight w 2 Is 1.
In any of the above technical solutions, further, the determining the binarization threshold in step 24 specifically includes: calculating gray value variances of all row pixel points in the QR code image to be identified corresponding to the view small window; and comparing the gray value variance with a preset variance threshold, recording the third gray value threshold as a binarization threshold when the gray value variance is judged to be less than or equal to the preset variance threshold, and recording the first gray value threshold as the binarization threshold when the gray value equation is judged to be greater than the preset variance threshold.
In any of the above technical solutions, further, a calculation formula for calculating the first gray threshold or the second gray threshold is:
wherein, when a =1,the calculation formula is a calculation formula of the first gray threshold value,
is the total number of pixel points in the view small window, and when alpha =2, the calculation formula is the calculation formula of the second gray degree threshold value, and->
Is the total number of pixels in the row pixel, g δ Is the pixel gray value of the delta-th pixel point, and theta is a preset correction coefficient.
In any of the above technical solutions, further, a value of the preset correction coefficient is 0.87.
In any of the above technical solutions, further, step 3 specifically includes: and when the pixel gray value of the pixel point is judged to be smaller than the binarization threshold, setting the pixel gray value of the pixel point to be 0, and when the pixel gray value of the pixel point is judged to be larger than or equal to the binarization threshold, setting the pixel gray value of the pixel point to be 255.
The beneficial effect of this application is: the calculation speed of a local threshold value algorithm is improved by dividing a QR code image into a plurality of view small windows by taking row pixel points as units, the binarization processing effect of the QR code image under the condition of uneven illumination is optimized, the value of a binarization threshold value is determined between a first grey threshold value and a third grey threshold value by calculating the grey value variance of the pixel points in the view small windows, the accuracy of the value of the binarization threshold value is improved, and meanwhile, the problem of probability error of binarization of a same color region caused by the fact that a plurality of continuous windows are located in the same color region can be solved.
The method comprises the steps of dividing view small windows line by line, calculating a threshold value by taking the view small windows as units, caching a plurality of lines of image pixel points to support an algorithm for calculating a local self-adaptive threshold value by two-dimensional array blocks line by line, caching single-row pixel points, selecting a binarization threshold value by utilizing the division of the view small windows and the correlation between the view small windows and the pixel points in the row, and obtaining a better QR code image identification effect than the existing QR code image identification effect of performing local self-adaptive threshold value binarization processing on the two-dimensional array blocks line by line on the premise of reducing algorithm complexity and simplifying a binarization threshold value calculation process when processing image input with uneven illumination.
In the application, when the one-dimensional view small window is completely enveloped with pixel points with similar gray values, the first weight of the weight is set to be greater than the second weight, so that the local adaptive threshold after weighted correction, namely the third gray threshold, is based on the local adaptive threshold in the view small window, and is assisted by the line threshold with correlation, therefore, under the action of the line threshold (the second threshold) with lower weight, the problem that probability errors exist in the binarization process of the pixel points in the same color zone enveloped by the view small window is solved, and meanwhile, the problem that the line threshold represented by the second weight excessively affects binarization of the QR code image with uneven illumination, so that the result is not ideal is avoided by setting the first weight of the weight to be greater than the second weight.
Drawings
The advantages of the above and/or additional aspects of the present application will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings of which:
FIG. 1 is a schematic block diagram of a binarization method specific to an image containing a QR code according to one embodiment of the present application;
fig. 2 is a schematic diagram of experimental comparison of a QR code binarized image according to an embodiment of the present application.
Detailed Description
In order that the above objects, features and advantages of the present application can be more clearly understood, the present application will be described in further detail with reference to the accompanying drawings and detailed description. It should be noted that the embodiments and features of the embodiments of the present application may be combined with each other without conflict.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present application, however, the present application may be practiced in other ways than those specifically described herein, and therefore the scope of the present application is not limited by the specific embodiments disclosed below.
The following describes an embodiment of the present application with reference to fig. 1 and 2.
As shown in fig. 1, the present embodiment provides a binarization method dedicated to an image containing a QR code, including:
step 1, dividing a QR code image to be identified into a plurality of view widgets according to a preset dimension;
further, step 1 specifically includes:
step 11, carrying out graying processing on a QR code image to be identified;
and step 12, generating a plurality of view widgets according to the preset dimensionality and the processed QR code image to be identified.
Preferably, step 12 is preceded by: adding redundant pixel points at the tail end of the QR code image to be identified after graying processing according to the number of columns in the preset dimension, wherein the preset dimension is 1 x n dimension, the number of columns is n, and the number of columns is a positive integer greater than or equal to 10;
specifically, the resolution of the to-be-identified QR code image is set to be 478 × 480, and the number n of columns with preset dimensions is 16, that is, 478 pixel points in each row in the to-be-identified QR code image are equally divided into a plurality of view widows. Before generating the view small window, carrying out graying processing on the QR code image to be identified, if adopting a maximum value method, adjusting the RGB value corresponding to each pixel point in the QR code image to be identified, wherein the corresponding calculation formula is as follows:
F’(B,G,R)＝B*0.114+G*0.587+R*0.229，
in the formula, F' (B, G, R) is a gradation value of the pixel after the gradation processing.
In order to equally divide the QR code image to be identified after the graying treatment according to the column number n =16, redundant pixel points are inserted into the QR code image to be identified, so that the QR code image to be identified can be divided into an integral number of view small windows by taking row pixel points as units.
In this embodiment, since 478 row pixels cannot be evenly divided by the number n of columns, 2 redundant pixels with a gray value of 122 are added to the end of each row pixel to complete the row pixels, and the problem of universality of the algorithm when processing images with irregular resolutions is solved on the premise of not affecting the QR code effective information with the gray value of the original image of 0 and 255. And dividing row pixel points in the QR code image into 30 view widgets.
Step 2, determining a binarization threshold value corresponding to the view small window according to pixel points contained in the view small window and all rows of pixel points in the QR code image to be identified corresponding to the view small window;
further, the step 2 specifically includes:
step 21, calculating a first gray average value of pixel points contained in the view small window, and calculating a first gray threshold value of the view small window according to a preset correction coefficient and the first gray average value;
specifically, according to row pixel points, pixel points in a QR code image to be identified are temporarily stored, 30 generated view widgets are sequentially selected, the gray value of the pixel points in each view widget is counted, and according to the number of the pixel points in the view widgets, a first gray average value is calculated and recorded as gMean win The first gray threshold value TH corresponding to the current view small window is calculated by multiplying the preset correction coefficient theta 1 The corresponding calculation formula is:
in the formula, g i For the gray value of the pixel point of the ith pixel point in the current view small window, the value of the preset correction coefficient theta can be set to be 0.87, N is the total number of the pixel points in the view small window, and N =16.
Step 22, calculating a second gray level average value of all row pixel points in the QR code image to be identified corresponding to the view small window, and calculating a second gray level threshold value of the row pixel points according to a preset correction coefficient and the second gray level average value;
specifically, according to the line pixel points, temporarily storing the pixel points in the QR code image to be identified, counting the pixel gray values of all the pixel points in the line in the current line pixel points line by line, calculating a second gray average value according to the number of the pixel points of the line pixel points, and recording the second gray average value as gMean line The gray scale value is multiplied by a preset correction coefficient theta, and a second gray scale mean value TH corresponding to the pixel point of the current row is calculated 2 The corresponding calculation formula is:
in the formula, g j The value of the preset correction coefficient theta is set to be 0.87 for the pixel gray value of the jth pixel point in the current row of pixel points, and M is the total number of the pixel points in the row of pixel points.
Step 23, calculating a third gray threshold value according to the first gray threshold value and the second gray threshold value by adopting a weighting algorithm;
further, in step 23, a third grayscale threshold is calculated, specifically:
setting the first weight value to be larger than the second weight value;
calculating a third gray threshold according to a weighting calculation formula, the first weight, the second weight, the first gray threshold and the second gray threshold, wherein the weighting calculation formula is as follows:
in the formula, TH crct Is a third gray scale threshold, w 1 Is the first weight, TH 1 Is a first gray scale threshold value, w 2 Is the second weight, TH 2 Is a second gray scale threshold.
Preferably, the first weight w 1 A value of 9, a second weight w 2 Is 1.
Step 24, determining a binarization threshold value according to the gray value variance of the pixel points in the view small window, wherein the binarization threshold value is one of a first gray threshold value and a third gray threshold value;
specifically, in the conventional binarization processing process, a same-color region with extremely small pixel gray level difference is usually encountered, wherein the definition of the same-color region is that the pixel gray levels in the region are distributed around the region gray level mean value and obey sigma 2 Very small normal distribution N (mu, sigma) 2 ) The area of (a). It is highly probable that the gray values in the same color region are equal in the ideal case, butThe method comprises the steps of shooting an area with difference in gray level after sampling, and determining a binarization threshold value according to the size relationship between the area and the threshold value, wherein the possibility that black and white are alternated after binarization exists.
Further, the method for determining the binarization threshold in step 24 specifically includes: calculating gray value variances of all row pixel points in the QR code image to be identified corresponding to the view small window; and comparing the gray value variance with a preset variance threshold, recording the third gray value threshold as a binarization threshold when the gray value variance is judged to be less than or equal to the preset variance threshold, and recording the first gray value threshold as the binarization threshold when the gray value equation is judged to be greater than the preset variance threshold.
Specifically, the gray value variance S of all pixel points in the view small window is calculated by taking the view small window as a unit 2 Setting a predetermined variance threshold
According to the variance of grey values S 2 And a preset variance threshold +>
The binary threshold value TH is determined according to the size relationship between the two, and the corresponding calculation formula is as follows:
and 3, performing binarization processing on pixel points in the QR code image to be recognized according to a binarization threshold value to generate a QR code binarization image.
Further, step 3 specifically includes:
when the pixel gray value of the pixel point is judged to be smaller than the binary threshold, the pixel gray value of the pixel point is set to be 0, and when the pixel gray value of the pixel point is judged to be larger than or equal to the binary threshold, the pixel gray value of the pixel point is set to be 255.
Specifically, point-by-point comparison of QR codes to be recognizedGray value g of pixel point in image x And comparing the QR code image to be identified with a binarization threshold TH corresponding to the view small window, and generating a QR code binarization image, wherein the corresponding binarization formula is as follows:
in formula (II), g' x And the pixel gray value of the pixel point after the binarization processing is obtained.
In this embodiment, a greater quantity (otsu) method in a global threshold value and a Wellner improved threshold value selection method in a local adaptive threshold value are used as comparison, a Python script led into a zbar module is used for carrying out batch identification and extraction of QR code information in an image file after binarization, the extracted information is compared with information extracted from a corresponding original image, and finally, the identified rates of output results of different algorithms are counted. The comparison and verification experiment adopts 4 groups of original images which are 640 × 480 in resolution and have different characteristics and contain QR codes to test, and each group of 100 samples, the total number of 400 samples participate in the experiment. The QR code information recognition rate results are shown in table 1.
TABLE 1
Further, as shown in fig. 2, the QR code image to be recognized is set as shown in fig. 2 (a), after the processing by the binarization method in the present application, the generated QR code binarized image is as shown in fig. 2 (B), and the QR code binarized image generated by the Wellner algorithm is as shown in fig. 2 (C), so that it can be seen that the recognition rate of fig. 2 (B) is significantly higher than that of fig. 2 (C).
In summary, the binarization method in the application not only simplifies the process of solving the local adaptive threshold, but also solves the problem of information loss of the otsu algorithm when processing the image with uneven illumination, achieves the information identification rate equivalent to the Wellner algorithm under the circumstances, and also solves the problem of probability misjudgment of the pixel points in the same color region, which is easily caused by the Wellner algorithm, when the QR code image accounts for more than 80% of the image.
The technical scheme of the application is described in detail with reference to the accompanying drawings, and the application provides a special binarization method for an image containing a QR code, which comprises the following steps: step 1, dividing a QR code image to be identified into a plurality of view widgets according to a preset dimension; step 2, determining a binaryzation threshold value corresponding to the view small window according to pixel points contained in the view small window and all lines of pixel points in the QR code image to be identified corresponding to the view small window; and 3, performing binarization processing on pixel points in the QR code image to be identified according to a binarization threshold value to generate the QR code binarization image. Through the technical scheme in the application, the binarization processing effect of the QR code image under the condition of uneven illumination is optimized, and the identification capability of the QR code image is improved.
The steps in the present application may be sequentially adjusted, combined, and subtracted according to actual requirements.
The units in the device can be merged, divided and deleted according to actual requirements.
Although the present application has been disclosed in detail with reference to the accompanying drawings, it is to be understood that such description is merely illustrative and not restrictive of the application of the present application. The scope of the present application is defined by the appended claims and may include various modifications, adaptations, and equivalents of the invention without departing from the scope and spirit of the application.
Claims (4)
1. A special binarization method for an image containing a QR code is characterized by comprising the following steps:
step 1, dividing a QR code image to be identified into a plurality of view widgets according to a preset dimension;
step 2, determining a binarization threshold value corresponding to the view small window according to pixel points contained in the view small window and all rows of pixel points in the QR code image to be identified corresponding to the view small window;
step 3, carrying out binarization processing on pixel points in the QR code image to be identified according to the binarization threshold value to generate a QR code binarization image;
wherein, the step 1 specifically comprises:
step 11, carrying out graying processing on the QR code image to be identified;
step 12, generating a plurality of view widgets according to the preset dimensionality and the processed QR code image to be identified;
the step 2 specifically includes:
step 21, calculating a first gray average value of pixel points contained in the view small window, and calculating a first gray threshold value of the view small window according to a preset correction coefficient and the first gray average value;
step 22, calculating a second gray level average value of all row pixel points in the QR code image to be identified corresponding to the view small window, and calculating a second gray level threshold value of the row pixel points according to the preset correction coefficient and the second gray level average value;
step 23, calculating a third gray threshold value according to the first gray threshold value and the second gray threshold value by adopting a weighting algorithm;
step 24, determining the binarization threshold of the view small window according to the size relationship between the gray value variance of the pixel points in the view small window and a preset variance threshold, wherein the binarization threshold is one of the first gray threshold and the third gray threshold;
wherein, the calculating the third grayscale threshold in step 23 specifically includes:
setting the first weight value to be larger than the second weight value;
calculating the third gray threshold according to a weighted calculation formula, the first weight, the second weight, the first gray threshold and the second gray threshold, where the weighted calculation formula is:
in the formula, TH crct Is the third gray scale threshold value, w 1 Is the first weight, TH 1 Is the firstA gray scale threshold value, w 2 Is the second weight, TH 2 Is the second gray scale threshold;
wherein, the determining the binarization threshold value in the step 24 specifically includes:
calculating the gray value variance of all the row pixel points in the QR code image to be identified corresponding to the view small window;
and comparing the gray value variance with the preset variance threshold, recording the third gray value threshold as the binarization threshold when the gray value variance is judged to be smaller than or equal to the preset variance threshold, and recording the first gray value threshold as the binarization threshold when the gray value equation is judged to be larger than the preset variance threshold.
2. The binarization method specially adapted for QR-code-containing images as recited in claim 1, characterized in that,
the first weight value w 1 A value of 9, the second weight w 2 Is 1.
3. The binarization method special for the image containing the QR code as recited in claim 1, wherein the value of the preset correction coefficient is 0.87.
4. The binarization method special for the image containing the QR code according to claim 1, wherein the step 3 specifically comprises the following steps:
setting the pixel gray value of the pixel point to 0 when the pixel gray value of the pixel point is judged to be smaller than the binarization threshold value,
and when the pixel gray value of the pixel point is judged to be larger than or equal to the binarization threshold value, setting the pixel gray value of the pixel point to be 255.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811424622.1A CN109543692B (en) | 2018-11-27 | 2018-11-27 | Binaryzation method special for image containing QR code |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811424622.1A CN109543692B (en) | 2018-11-27 | 2018-11-27 | Binaryzation method special for image containing QR code |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109543692A CN109543692A (en) | 2019-03-29 |
| CN109543692B true CN109543692B (en) | 2023-04-07 |
Family
ID=65851010
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811424622.1A Active CN109543692B (en) | 2018-11-27 | 2018-11-27 | Binaryzation method special for image containing QR code |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109543692B (en) |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110648284B (en) * | 2019-08-02 | 2023-01-24 | 张杰辉 | Image processing method and device with uneven illumination |
| CN110569684B (en) * | 2019-09-19 | 2023-05-12 | 南京全鉴信息技术有限公司 | Image binarization method for small-capacity cache |
| CN112288754B (en) * | 2020-11-09 | 2023-12-05 | 珠海市润鼎智能科技有限公司 | Real-time binarization threshold selection method for high-speed image |
| CN113255393B (en) * | 2021-07-07 | 2021-10-15 | 江苏东大集成电路系统工程技术有限公司 | Image binarization method and device, storage medium and computer equipment |
| CN114548140B (en) * | 2022-04-26 | 2022-08-12 | 成都普什信息自动化有限公司 | Two-dimensional code decoding method, data association method, association device and use method |
| CN115618905B (en) * | 2022-10-13 | 2023-12-12 | 东莞市生海科技有限公司 | Traceability management method and traceability management system for automobile manufacturing parts |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104636118A (en) * | 2013-11-10 | 2015-05-20 | 航天信息股份有限公司 | QR two-dimensional code self-adaptation binarization processing method and device based on light balance |
| WO2017121018A1 (en) * | 2016-01-11 | 2017-07-20 | 中兴通讯股份有限公司 | Method and apparatus for processing two-dimensional code image, and terminal and storage medium |
| CN108509819A (en) * | 2018-03-07 | 2018-09-07 | 中山大学 | A kind of Quick Response Code binarization method even for uneven illumination |
-
2018
- 2018-11-27 CN CN201811424622.1A patent/CN109543692B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104636118A (en) * | 2013-11-10 | 2015-05-20 | 航天信息股份有限公司 | QR two-dimensional code self-adaptation binarization processing method and device based on light balance |
| WO2017121018A1 (en) * | 2016-01-11 | 2017-07-20 | 中兴通讯股份有限公司 | Method and apparatus for processing two-dimensional code image, and terminal and storage medium |
| CN108509819A (en) * | 2018-03-07 | 2018-09-07 | 中山大学 | A kind of Quick Response Code binarization method even for uneven illumination |
Non-Patent Citations (1)
| Title |
|---|
| 复杂光照下QR码图像二值化算法研究及应用;甘志坚等;《应用光学》;20180915(第05期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109543692A (en) | 2019-03-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109543692B (en) | Binaryzation method special for image containing QR code | |
| US10817741B2 (en) | Word segmentation system, method and device | |
| US8401293B2 (en) | Word recognition of text undergoing an OCR process | |
| CN109255390B (en) | Training image preprocessing method and module, discriminator and readable storage medium | |
| CN109214229B (en) | Bar code scanning method and device and electronic equipment | |
| US10261849B1 (en) | Preventative remediation of services | |
| CN108091033B (en) | Paper money identification method and device, terminal equipment and storage medium | |
| CN111339797B (en) | Decoding method and terminal capable of accurately identifying damaged one-dimensional bar code | |
| US8494282B2 (en) | Blur estimation | |
| CN115302963B (en) | Bar code printing control method, system and medium based on machine vision | |
| CN111311497B (en) | Bar code image angle correction method and device | |
| CN110705488A (en) | Image character recognition method | |
| CN110942067A (en) | Text recognition method and device, computer equipment and storage medium | |
| CN114241463A (en) | Signature verification method and device, computer equipment and storage medium | |
| CN112530079B (en) | Method, device, terminal equipment and storage medium for detecting bill factors | |
| US11748979B2 (en) | Method for training a neural network for recognition of a character sequence and associated recognition method | |
| US8267322B2 (en) | Method and apparatus for correcting decoding errors in machine-readable symbols | |
| US10970848B2 (en) | Font family and size aware character segmentation | |
| US9269126B2 (en) | System and method for enhancing the legibility of images | |
| CN111814780A (en) | Bill image processing method, device and equipment and storage medium | |
| CN112434700A (en) | License plate recognition method, device, equipment and storage medium | |
| CN111325658A (en) | Color image self-adaptive decolorizing method | |
| CN111598184B (en) | DenseNet-based image noise identification method and device | |
| CN110837754B (en) | Character cutting positioning method and device, computer equipment and storage medium | |
| CN116245848B (en) | Product defect detection method and related equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |