CN110807342B - Bar code positioning method, bar code positioning device, computer equipment and storage medium - Google Patents
Bar code positioning method, bar code positioning device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN110807342B CN110807342B CN201910995165.XA CN201910995165A CN110807342B CN 110807342 B CN110807342 B CN 110807342B CN 201910995165 A CN201910995165 A CN 201910995165A CN 110807342 B CN110807342 B CN 110807342B
- Authority
- CN
- China
- Prior art keywords
- bar code
- area
- straight line
- quantization
- region
- 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
Classifications
-
- 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
- G06K7/1413—1D bar codes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- 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
- G06K7/1439—Methods for optical code recognition including a method step for retrieval of the optical code
- G06K7/1443—Methods for optical code recognition including a method step for retrieval of the optical code locating of the code in an image
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Toxicology (AREA)
- General Health & Medical Sciences (AREA)
- Electromagnetism (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Image Analysis (AREA)
Abstract
The application relates to a bar code positioning method, a bar code positioning device, computer equipment and a storage medium. The method comprises the following steps: acquiring an image to be identified; calculating gradient amplitude and angle of each pixel point of the image to be identified; carrying out gradient quantization on the image to be identified according to the gradient amplitude of each pixel point to obtain a plurality of quantization areas; performing region growing on each quantization region according to the angle of each pixel point to obtain a plurality of region straight lines; clustering the straight lines of each region to obtain a bar code region and a center point of the bar code; and calculating the angle of the bar code according to the straight line of each area in the bar code area. The method can effectively improve the positioning accuracy and has smaller calculated amount.
Description
Technical Field
The present application relates to the field of image processing technologies, and in particular, to a barcode positioning method, a barcode positioning device, a computer device, and a storage medium.
Background
The bar codes are widely applied at present, and have wide application in the fields of commodity equipment labels, mobile payment and the like. The bar code mainly comprises a one-dimensional bar code and a two-dimensional code, wherein the one-dimensional bar code is a mark formed by a group of regularly arranged bars, empty and corresponding characters, the bar refers to a part with lower light reflectivity, the empty refers to a part with higher light reflectivity, and data formed by the bars and the empty express certain information and can be read by specific equipment and converted into binary and decimal information compatible with a computer. The code is generally unique for each article, and for a common one-dimensional bar code, the corresponding relationship between the bar code and commodity information is also established through a database, and when the data of the bar code is transmitted to a computer, an application program on the computer operates and processes the data.
At present, the bar code scanning equipment mainly scans the bar code by actively aiming at the bar code, and the bar code scanning equipment is convenient, but the mode needs scanning laser auxiliary positioning, is sensitive to the angle and deformation of the bar code, and can scan the bar code failure if the angle is unsuitable. Therefore, the success rate of decoding can be directly affected by the quality of bar code positioning, and at present, a bar code positioning method based on digital image processing is also used for solving the problems of angles and deformation, but the common positioning method has large calculation amount, such as a watershed positioning method and a contour analysis method, so that the industrial requirement can be met only on a chip with higher performance, and the method cannot be implemented on a small embedded chip.
Disclosure of Invention
In view of the foregoing, it is desirable to provide a barcode positioning method, apparatus, computer device, and storage medium capable of reducing the amount of calculation and accurately positioning a barcode.
A method of bar code positioning, the method comprising:
acquiring an image to be identified;
calculating gradient amplitude and angle of each pixel point of the image to be identified;
carrying out gradient quantization on the image to be identified according to the gradient amplitude of each pixel point to obtain a plurality of quantization areas;
Performing region growing on each quantization region according to the angle of each pixel point to obtain a plurality of region straight lines;
clustering the straight lines of each region to obtain a bar code region and a center point of the bar code;
and calculating the angle of the bar code according to the straight line of each area in the bar code area.
In one embodiment, the step of performing gradient quantization on the image to be identified according to the gradient amplitude of each pixel point to obtain a plurality of quantization areas includes:
gradient division is carried out on each pixel point in the image to be identified according to a preset gradient division standard, so that a plurality of gradient areas are obtained;
and quantizing the pixel points in each gradient region to obtain quantized regions.
In one embodiment, the step of performing region growing on each quantization region according to the angle of each pixel point to obtain a plurality of region lines includes:
randomly selecting a pixel point from the quantization area as a reference point;
performing main direction consistency judgment on other pixel points in the quantization area where the reference points are located according to the reference points;
removing pixels which do not meet the main direction consistency from the quantization area;
carrying out main direction consistency judgment on four adjacent pixel points around each pixel point meeting the main direction consistency and other pixel points in the quantization area;
Extracting pixel points meeting the main direction consistency from adjacent pixel points to a quantization area, and removing the pixel points from the original quantization area;
and traversing each quantization region to obtain a plurality of region lines.
In one embodiment, the step of clustering the straight lines of each region to obtain the barcode region and the center point of the barcode includes:
calculating the transverse-longitudinal ratio of the straight line of each region;
determining the transverse and longitudinal directions of the regional straight line according to the transverse and longitudinal ratio of the regional straight line;
determining the coordinates of end point pixel points corresponding to the two ends of the area straight line, the coordinates of the middle point of the area straight line and the inclination angle of the area straight line according to the transverse and longitudinal directions of the area straight line;
sequentially extracting any one regional straight line as a reference straight line, and calculating clustering parameters of the reference straight line and each other regional straight lines; the clustering parameter is the product of the distance between the midpoint of the reference straight line and the midpoint of any other regional straight line and the angle difference between the reference straight line and the regional straight line;
judging whether the clustering parameters of the reference straight line and the rest of each regional straight line are smaller than a preset threshold value, if so, accumulating the clustering parameters to obtain a clustering parameter accumulated value when each regional straight line is respectively used as the reference straight line, and if so, eliminating the corresponding regional straight line to obtain a regional straight line set corresponding to the clustering parameter accumulated value; and determining an area formed by the area straight line set with the smallest cluster parameter accumulated value as a bar code area, wherein the midpoint of the reference straight line corresponding to the area straight line set with the smallest cluster parameter accumulated value is the center point of the bar code.
In one embodiment, the step of linearly calculating the angle of the bar code from the respective areas within the bar code area comprises:
randomly sampling the straight line midpoints of the bar code area to obtain local points;
and performing straight line fitting on the local inner points, calculating the angle of the fitted straight line, and determining the angle of the fitted straight line as the angle of the bar code.
In one embodiment, the method further comprises:
determining a start-stop symbol of the bar code along the angle of the bar code according to the center point of the bar code;
calculating each vertex coordinate of the bar code area according to the start-stop sign of the bar code;
fitting a perspective transformation matrix according to each vertex coordinate;
a bar code without angular tilt is generated from the perspective transformation matrix map.
In one embodiment, the method further comprises:
determining the type of the bar code according to the start-stop sign of the bar code;
determining a corresponding decoding mode according to the type of the bar code;
and decoding the bar code according to the decoding mode to obtain the code value of the bar code.
A bar code positioning device, the device comprising:
the image acquisition module is used for acquiring an image to be identified;
the gradient calculation module is used for calculating the gradient amplitude and the angle of each pixel point of the image to be identified;
The region quantization module is used for carrying out gradient quantization on the image to be identified according to the gradient amplitude of each pixel point to obtain a plurality of quantization regions;
the region growing module is used for carrying out region growing on each quantization region according to the angle of each pixel point to obtain a plurality of region lines;
the clustering module is used for carrying out clustering treatment on the straight lines of each area to obtain a bar code area and a center point of the bar code;
and the bar code angle calculation module is used for linearly calculating the angle of the bar code according to each area in the bar code area.
A computer device comprising a memory storing a computer program and a processor which when executing the computer program performs the steps of:
acquiring an image to be identified;
calculating a direction gradient histogram of the image to be identified;
carrying out gradient quantization on the image to be identified according to the direction gradient histogram to obtain a plurality of quantization areas;
performing region growing on each quantization region to obtain a plurality of region lines;
clustering the straight lines of each region to obtain a bar code region and a center point of the bar code;
and calculating the angle of the bar code according to the straight line of each area in the bar code area.
A computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of:
acquiring an image to be identified;
calculating a direction gradient histogram of the image to be identified;
carrying out gradient quantization on the image to be identified according to the direction gradient histogram to obtain a plurality of quantization areas;
performing region growing on each quantization region to obtain a plurality of region lines;
clustering the straight lines of each region to obtain a bar code region and a center point of the bar code;
and calculating the angle of the bar code according to the straight line of each area in the bar code area.
According to the bar code positioning method, the bar code positioning device, the computer equipment and the storage medium, gradient quantization processing is carried out on the image to be identified by calculating the gradient amplitude and the angle of each pixel point of the image to be identified, region growing processing is carried out on each quantization region to obtain a plurality of region straight lines, clustering processing is carried out on each region straight line to obtain a bar code region and a center point of the bar code, the angle of the bar code is calculated according to each region straight line in the bar code region, the bar code in the image to be identified is positioned, region growing optimization is utilized, irrelevant regions are removed by clustering processing, positioning accuracy is effectively improved, and the calculated amount is small.
Drawings
FIG. 1 is a diagram of an application environment for a barcode locating method in one embodiment;
FIG. 2 is a flow chart of a bar code positioning method according to an embodiment;
FIG. 3 is a flowchart illustrating steps of performing gradient quantization on an image to be identified according to a gradient magnitude of each pixel point to obtain a plurality of quantization areas in an embodiment;
FIG. 4 is a flow chart of a step of obtaining a plurality of area lines by performing area growth on each quantization area according to an angle of each pixel point in one embodiment;
FIG. 5 is a flowchart of a step of clustering the lines of each region to obtain a barcode region and a center point of the barcode in one embodiment;
FIG. 6 is a flow chart illustrating the steps of linearly calculating the angles of a bar code from each region within the bar code region, in one embodiment;
FIG. 7 is a flow chart of a bar code extraction step in one embodiment;
FIG. 8 is a flow chart illustrating a decoding process for a bar code according to one embodiment;
FIG. 9 is a block diagram of a bar code positioning device in one embodiment;
FIG. 10 is an internal block diagram of a computer device, in one embodiment.
Detailed Description
The present application will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present application more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the application.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein in the description of the application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application.
The bar code identification method provided by the application can be applied to an application environment shown in figure 1. The barcode is identified by the terminal 100, wherein the terminal 100 may be, but is not limited to, various personal computers, notebook computers, smartphones, tablet computers, portable wearable devices, and code scanners.
In one embodiment, as shown in fig. 2, a barcode positioning method is provided, and the method is applied to the terminal in fig. 1 for illustration, and includes the following steps:
step S210, an image to be identified is acquired.
The image to be identified is an acquired image containing the bar code to be identified, and besides the bar code to be identified, the image to be identified may also have some content irrelevant to the bar code, so that a complex background is formed, and the background content may overlap with the bar code during identification, so that the identification difficulty is increased.
The terminal 100 may acquire the image to be recognized by photographing, and may acquire the image to be recognized from other terminals or servers through network communication.
Step S220, calculating the gradient amplitude and the gradient angle of each pixel point of the image to be identified.
The gradient Gx in the horizontal direction and the gradient Gy in the vertical direction of the pixel point are calculated respectively, and when the gradient Gx in the horizontal direction and the gradient Gy in the vertical direction of the pixel point are calculated, a sobel operator can be adopted for calculation, and Fx= [ -1,0,1 can also be adopted for calculation]And Fy= [ -1,0,1] T And calculating, and then calculating the amplitude and the angle according to the gradient Gx in the horizontal direction and the gradient Gy in the vertical direction of the pixel point.
Wherein the gradient amplitude G may be according to formula g= |g x |+|G y The i calculation may also be according to the formula:and (5) calculating. The angle is +.>And (5) calculating. The angle ranges from 0 DEG to 360 deg.
Step S230, carrying out gradient quantization on the image to be identified according to the gradient amplitude of each pixel point to obtain a plurality of quantization areas.
The analog image is spatially discretized into pixel points after being sampled, but the pixel values (namely gray values) obtained by sampling are still continuous quantities, the gradient amplitude and the angle calculated by using the pixel values are also continuous quantities, the analog quantity is required to be converted into discrete quantities, the gradient amplitude of the sampled image pixel points is converted into discrete quantities from the analog quantity, namely gradient quantization, the quantized gradient is changed into an integer value, and the calculated quantity can be reduced for subsequent image processing.
In some embodiments, uniform quantization or non-uniform quantization may be employed. The uniform quantization is to divide and quantize the gradient amplitude of each pixel at equal intervals, and the quantization method can obtain smaller quantization error for the image with the pixel gray value more uniformly distributed in the black-white range. The non-uniform quantization is performed according to a probability density function of specific gray value distribution of an image and a principle of minimum total quantization error, specifically, a relatively smaller quantization interval is taken for a gray value range in which pixel gray values frequently appear in the image, and a larger quantization interval is taken for a range in which pixel gray values rarely appear.
The quantization region is a region obtained by quantizing each divided region obtained by dividing the gradient amplitude at intervals.
Step S240, performing region growing on each quantization region according to the angle of each pixel point to obtain a plurality of region lines.
Region growing, also known as region growing, is a method of image segmentation. The method generally has two modes, namely, a small block or seed region (seed point) in a target object to be segmented in a given image is firstly set, and then, the surrounding pixel points are continuously added into the target object according to a certain rule on the basis of the seed region, so that the aim of finally combining all the pixel points representing the object into one region is fulfilled; the other is to divide the image into a plurality of small areas with stronger consistency, such as the same pixel gray values in the areas, and then fuse the small areas into a large area according to a certain rule, so as to achieve the purpose of dividing the image. One skilled in the art can select a region growing method to divide the image according to the need, so as to obtain a region straight line.
And S250, clustering the straight lines of each region to obtain a bar code region and a center point of the bar code.
Clustering is the partitioning of a data set into different classes or clusters according to some specific criteria (e.g., distance criteria, i.e., distance between data points), such that the similarity of data objects within the same cluster is as large as possible, while the variability of data objects that are not in the same cluster is also as large as possible. It is specifically understood that the data of the same class after clustering are gathered together as much as possible, and the data of different classes are separated as much as possible.
Because of the particularity of the bar code images, the directions of lines are consistent, the concentration is high, the clustering treatment is carried out on the straight lines of each region, the straight lines of the unrelated regions can be removed, and the bar code regions and the center point of the bar code are finally determined. In some embodiments, the linear clustering processing of each region can be implemented by adopting a k-means clustering algorithm, a hierarchical clustering algorithm, an FCM clustering algorithm and other clustering algorithms.
Step S260, the angle of the bar code is calculated according to the straight line of each area in the bar code area.
Since the bar code has the same line direction, the angle of the bar code can be calculated according to the area straight line.
According to the bar code positioning method, gradient quantization processing is carried out on the image to be identified by calculating the gradient amplitude and the angle of each pixel point of the image to be identified, region growing processing is carried out on each quantized region to obtain a plurality of region straight lines, clustering processing is carried out on each region straight line to obtain a bar code region and a center point of the bar code, the angle of the bar code is calculated according to each region straight line in the bar code region, the bar code in the image to be identified is positioned, region growing optimization is utilized, irrelevant regions are removed by clustering processing, positioning accuracy is effectively improved, and calculated amount is small.
In one embodiment, as shown in fig. 3, the step of performing gradient quantization on the image to be identified according to the gradient amplitude of each pixel point to obtain a plurality of quantization areas includes:
step S231, gradient division is carried out on each pixel point in the image to be identified according to a preset gradient division standard, and a plurality of gradient areas are obtained.
Gradient division criteria, i.e., gradient magnitude intervals, in one embodiment, since the bar code is an image with pixel gray values more uniformly distributed in the black-to-white range, gradient division may be performed with equal intervals. In one embodiment, if the image to be identified has other interference factors besides the bar code, so that the bar code is placed in a complex background, gradient division can be performed at non-uniform intervals, so that the amount of processing data can be reduced.
Step S232, the pixel points in each gradient region are quantized, and a quantized region is obtained.
The maximum value of the gradient amplitude of the pixel point is max_mag, the quantized region quantity is n (n is an empirical data value, generally 128, or other values can be adjusted according to the actual situation), the quantization mode is bin=mag (i) ×n/max_mag, i represents the i-th point, mag (i) represents the amplitude of the i-th pixel point, all points are traversed in sequence, and bin represents the quantized value of the gradient amplitude of each pixel point.
In one embodiment, as shown in fig. 4, the step of performing region growing on each quantized region according to the angle of each pixel point to obtain a plurality of region lines includes:
in step S241, a pixel point is randomly selected from the quantization area as a reference point.
Starting from any one quantization region, performing region growing by taking any one pixel point in the current quantization region as a reference point.
In step S242, main direction consistency determination is performed on other pixel points in the quantization area according to the reference points.
Assuming that the angle of the reference point A is the initial main direction, judging any pixel point A1 outside the reference point in the current quantization area, judging whether the absolute value of the angle difference between the pixel point A1 and the main direction is larger than a preset threshold range T, if so, keeping the pixel point A1 in the current quantization area for meeting the consistency of the main direction; judging any one of the other pixel points A2 in the current quantization area, judging whether the absolute value of the angle difference between the pixel point A2 and the main direction is larger than a preset threshold range T, wherein the main direction is the average value of the angle of the pixel point A and the angle of the pixel point A1 at the moment, if the absolute value is smaller than the average value, the pixel point A2 meets the main direction consistency, and the pixel point A2 is reserved in the current quantization area; until the last pixel point An in the quantization area is traversed, judging whether the absolute value of the angle difference between the pixel point An and the main direction is larger than a preset threshold range T, wherein the main direction is the average value of the angle sums from the pixel point A to the pixel point A (n-1), if the angle sums are smaller than the average value, the pixel point An meets the main direction consistency, and the pixel point An is reserved in the current quantization area.
In step S243, pixels that do not satisfy the main direction consistency are removed from the quantization area.
If the absolute value of the angle difference between the pixel point A1 and the main direction is larger than T, the pixel point A1 does not meet the main direction consistency, the pixel point A1 is removed from the current quantization area, the pixel point A1 is placed in the pixel point set without the area, and the main direction consistency judgment with other quantization areas is performed when the area growth is performed on the other quantization areas. The other pixels are the same.
In step S244, main direction consistency determination is performed on four adjacent pixels around each pixel satisfying the main direction consistency and other pixels in the quantization area.
After judging whether the pixel point A1 meets the consistency, if the pixel point A1 meets the consistency of the main direction, carrying out 4 neighborhood expansion on the pixel point A1, namely, judging whether adjacent pixel points B1, C1, D1 and E1 of the pixel point A1 in the four directions of up, down, left and right in the image to be recognized meet the consistency of the main direction of the current quantized region, taking the pixel point B1 as an example, judging whether the absolute value of the angle difference between the pixel point B1 and the main direction is larger than a preset threshold range T, and taking the main direction at the moment as the angle average value of all the pixel points which are judged to meet the consistency of the main direction in the current quantized region, namely, if the pixel points which are judged to meet the consistency of the main direction in the current quantized region comprise A, A1, the current direction is the angle average value of the pixel point A and the pixel point A1, and if the absolute value of the angle difference between the pixel point B1 and the main direction is smaller than the preset threshold range T, and the consistency of the main direction is met. The step of performing 4-neighborhood expansion on each pixel point meeting the main direction consistency may be performed after the pixel point meets the main direction consistency, or may be performed after all the pixel points in the current quantization area are traversed.
And step S245, extracting pixel points meeting the main direction consistency from adjacent pixel points to a quantization area, and eliminating the pixel points from the original quantization area.
If the pixel point B1 meets the main direction consistency, the pixel point B1 is extracted from the original quantization area to the current quantization area, the original quantization area does not contain the pixel point B1 any more, and the pixel point B1 is not judged when the original quantization area is increased. Other pixels in other quantization areas are the same.
Step S246, traversing each quantization region to obtain a plurality of region lines.
After all the quantized areas are subjected to area growth, a plurality of area straight lines are reached, and each quantized area after area growth is an area straight line.
In one embodiment, as shown in fig. 5, the step of clustering the straight lines of each region to obtain a barcode region and a center point of the barcode includes:
in step S251, the aspect ratio of each area straight line is calculated.
Calculating the leftmost point a (xleft, yleft), the rightmost point b (xright, ydight), the uppermost point c (xtop, ytop), and the bottommost point d (xbottom, ybottom) of each area straight line; calculating aspect ratio:
Step S252, determining the transverse and longitudinal directions of the area straight line according to the transverse and longitudinal ratio of the area straight line.
If r >1, the regional straight line is transverse; if r <1, the area straight line is longitudinal.
In step S253, the coordinates of the end points pixel points corresponding to the two ends of the area straight line, the coordinates of the middle point of the area straight line, and the inclination angle of the area straight line are determined according to the horizontal and vertical directions of the area straight line.
If the area straight line is transverse, obtaining two endpoints of the straight line as a (xleft, yleft) and b (xright, ydight) respectively; if the region straight line is longitudinal, two endpoints of the straight line are respectively c (xtop, ytop) and d (xbottom, ybottom).
And calculating the midpoint coordinates and the inclination angle of the regional straight line according to the endpoint pixel point coordinates.
Step S254, sequentially extracting any one area straight line as a reference straight line, and calculating clustering parameters of the reference straight line and each other area straight line; the clustering parameter is the product of the distance between the midpoint of the reference straight line and the midpoint of any one of the rest of the area straight lines and the angle difference between the reference straight line and the area straight line.
The linear variable i parallel to the bar code direction is set, any one area straight line is sequentially taken as the linear variable, the distance between each linear variable i and each other area straight line (namely, the distance between the midpoints of the two straight lines) is calculated, and the other area straight line variable is set as j. Calculating a distance dis=sqrt ((Cxi-Cyi) ×cxi (Cxj) + (Cyi-Cyj) ×cyi-Cyj)) between a center (Cxj, cyj) of a straight line j outside the straight line i, where i, j=1,..; the angles corresponding to the straight lines i, j are respectively angi, angj, and a clustering parameter t=dis ABS (angi-angj) is calculated.
Step S255, judging whether the clustering parameters of the reference straight line and the rest of each regional straight line are smaller than a preset threshold value, if so, accumulating the clustering parameters to obtain a clustering parameter accumulated value when each regional straight line is respectively used as the reference straight line, and if so, rejecting the corresponding regional straight line to obtain a regional straight line set corresponding to the clustering parameter accumulated value; and determining an area formed by the area straight line set with the smallest cluster parameter accumulated value as a bar code area, wherein the midpoint of the reference straight line corresponding to the area straight line set with the smallest cluster parameter accumulated value is the center point of the bar code.
If the clustering parameter t < Q (Q is a preset condition threshold, in one embodiment, 3000 can be taken), adding dis ABS (ranging-angj) to the accumulated value sum, and if t > Q, eliminating the regional straight line j, and traversing the straight line j in sequence; and when any one of the area straight lines I traverses all the straight lines j, re-selecting one of the other area straight lines as a straight line variable I until all the area straight lines are traversed, determining an area formed by an area straight line set I corresponding to the accumulated value sum as a bar code area, and determining the midpoint of a reference straight line I corresponding to the area straight line set I as the center point of the bar code.
In one embodiment, as shown in fig. 6, the step of calculating the angle of the bar code from the respective area lines within the bar code area includes:
Step S261, randomly sampling the area straight line midpoints in the bar code area to obtain the local points.
The area straight line in the bar code area may have a problem of deformation due to the problem of image acquisition angle, the angle of the bar code is directly calculated by all the area straight lines in the bar code area, and the accuracy may be affected. Random sampling is used to extract a number of midpoint hypotheses as intra-local points within the midpoints of the respective region lines.
In step S262, the local points are fitted with straight lines, the angle of the fitted straight lines is calculated, and the angle of the fitted straight lines is determined as the angle of the bar code.
Assuming that the local inner points can fully express the bar code, performing straight line fitting on the local inner points, and fitting out a hypothetical bar code midpoint connecting line, wherein the inclination angle of the bar code midpoint connecting line is the inclination angle of the bar code.
And positioning the bar code in the image to be identified according to the inclination angle of the bar code, the center point of the bar code and the bar code area.
In one embodiment, as shown in fig. 7, the barcode positioning method further includes:
step S310, determining the start and stop characters of the bar code along the angle of the bar code according to the center point of the bar code.
The start and stop symbols include a start symbol and a stop symbol, which mark the start and end of the bar code, and provide both code identification information and reading direction information. Searching is performed in the main direction from the center point until the start and stop characters are searched.
Step S320, each vertex coordinate of the bar code area is calculated according to the start and stop symbol of the bar code.
Since the start and stop symbols mark the beginning and end of the bar code, four vertices of the bar code can be determined in conjunction with the start and stop symbols.
Step S330, fitting a perspective transformation matrix according to the vertex coordinates.
Since the acquired images to be identified may have an inclination angle, each vertex is not necessarily on a two-dimensional plane, but in a three-dimensional space, the positioned bar code needs to be subjected to dimension reduction through a perspective transformation matrix.
Step S340, generating the bar code without angle inclination according to the perspective transformation matrix mapping.
And (3) obtaining a two-dimensional image according to the dimension reduction of the perspective transformation matrix, and obtaining the bar code without angle inclination.
In one embodiment, as shown in fig. 8, the barcode positioning method further includes:
step S350, determining the type of the bar code according to the start and stop characters of the bar code.
The start-stop symbol also provides code system identification information so that the type of bar code can be determined from the start-stop symbol.
Step S360, corresponding decoding modes are determined according to the types of the bar codes.
Different types of bar codes have corresponding decoding modes, and the bar codes need to be selected according to the determined bar code types so as to be correctly decoded.
And step S370, decoding the bar code according to the decoding mode to obtain the code value of the bar code.
And decoding the extracted bar code without the angle inclination according to the determined decoding mode to obtain the code value of the bar code.
In one embodiment, the bar code positioning method further comprises,
and transmitting the decoded code value to a host for subsequent work, or transmitting the code value to a terminal for display.
It should be understood that, although the steps in the flowcharts of fig. 2-8 are shown in order as indicated by the arrows, these steps are not necessarily performed in order as indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least some of the steps in fig. 2-8 may include multiple sub-steps or stages that are not necessarily performed at the same time, but may be performed at different times, nor does the order in which the sub-steps or stages are performed necessarily occur sequentially, but may be performed alternately or alternately with at least a portion of the sub-steps or stages of other steps or other steps.
In one embodiment, as shown in FIG. 9, there is provided a bar code positioning device comprising: an image acquisition module 410, a gradient calculation module 420, a region quantization module 430, a region growing module 440, a clustering module 450, and a barcode angle calculation module 460, wherein:
an image acquisition module 410, configured to acquire an image to be identified;
the gradient calculating module 420 is configured to calculate a gradient amplitude value and an angle of each pixel point of the image to be identified;
the region quantization module 430 is configured to perform gradient quantization on the image to be identified according to the gradient amplitude of each pixel point to obtain a plurality of quantization regions;
the region growing module 440 is configured to perform region growing on each quantization region according to the angle of each pixel point to obtain a plurality of region lines;
the clustering module 450 is used for clustering the straight lines of each region to obtain a bar code region and a center point of the bar code;
the bar code angle calculation module 460 is configured to calculate the angle of the bar code according to the straight line of each area in the bar code area.
For specific limitations of the bar code positioning device, reference may be made to the above limitations of the bar code positioning method, and no further description is given here. The various modules in the bar code positioning device described above may be implemented in whole or in part by software, hardware, and combinations thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.
In one embodiment, a computer device is provided, which may be a terminal, and an internal structure diagram thereof may be as shown in fig. 10. The computer device includes a processor, a memory, a network interface, a display screen, and an input device connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a bar code positioning method. The display screen of the computer equipment can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer equipment can be a touch layer covered on the display screen, can also be keys, a track ball or a touch pad arranged on the shell of the computer equipment, and can also be an external keyboard, a touch pad or a mouse and the like.
It will be appreciated by those skilled in the art that the structure shown in FIG. 10 is merely a block diagram of some of the structures associated with the present inventive arrangements and is not limiting of the computer device to which the present inventive arrangements may be applied, and that a particular computer device may include more or fewer components than shown, or may combine some of the components, or have a different arrangement of components.
In one embodiment, a computer device is provided comprising a memory and a processor, the memory having stored therein a computer program, the processor when executing the computer program performing the steps of:
acquiring an image to be identified;
calculating gradient amplitude and angle of each pixel point of the image to be identified;
carrying out gradient quantization on the image to be identified according to the gradient amplitude of each pixel point to obtain a plurality of quantization areas;
performing region growing on each quantization region according to the angle of each pixel point to obtain a plurality of region straight lines;
clustering the straight lines of each region to obtain a bar code region and a center point of the bar code;
and calculating the angle of the bar code according to the straight line of each area in the bar code area.
In one embodiment, the processor when executing the computer program further performs the steps of:
Gradient division is carried out on each pixel point in the image to be identified according to a preset gradient division standard, so that a plurality of gradient areas are obtained;
and quantizing the pixel points in each gradient region to obtain quantized regions.
In one embodiment, the processor when executing the computer program further performs the steps of:
randomly selecting a pixel point from the quantization area as a reference point;
performing main direction consistency judgment on other pixel points in the quantization area where the reference points are located according to the reference points;
removing pixels which do not meet the main direction consistency from the quantization area;
carrying out main direction consistency judgment on four adjacent pixel points around each pixel point meeting the main direction consistency and other pixel points in the quantization area;
extracting pixel points meeting the main direction consistency from adjacent pixel points to a quantization area, and removing the pixel points from the original quantization area;
and traversing each quantization region to obtain a plurality of region lines.
In one embodiment, the processor when executing the computer program further performs the steps of:
calculating the transverse-longitudinal ratio of the straight line of each region;
determining the transverse and longitudinal directions of the regional straight line according to the transverse and longitudinal ratio of the regional straight line;
Determining the coordinates of end point pixel points corresponding to the two ends of the area straight line, the coordinates of the middle point of the area straight line and the inclination angle of the area straight line according to the transverse and longitudinal directions of the area straight line;
sequentially extracting any one regional straight line as a reference straight line, and calculating clustering parameters of the reference straight line and each other regional straight lines; the clustering parameter is the product of the distance between the midpoint of the reference straight line and the midpoint of any other regional straight line and the angle difference between the reference straight line and the regional straight line;
judging whether the clustering parameters of the reference straight line and the rest of each regional straight line are smaller than a preset threshold value, if so, accumulating the clustering parameters to obtain a clustering parameter accumulated value when each regional straight line is respectively used as the reference straight line, and if so, eliminating the corresponding regional straight line to obtain a regional straight line set corresponding to the clustering parameter accumulated value; and determining an area formed by the area straight line set with the smallest cluster parameter accumulated value as a bar code area, wherein the midpoint of the reference straight line corresponding to the area straight line set with the smallest cluster parameter accumulated value is the center point of the bar code.
In one embodiment, the processor when executing the computer program further performs the steps of:
randomly sampling the straight line midpoints of the bar code area to obtain local points;
And performing straight line fitting on the local inner points, calculating the angle of the fitted straight line, and determining the angle of the fitted straight line as the angle of the bar code.
In one embodiment, the processor when executing the computer program further performs the steps of:
determining a start-stop symbol of the bar code along the angle of the bar code according to the center point of the bar code;
calculating each vertex coordinate of the bar code area according to the start-stop sign of the bar code;
fitting a perspective transformation matrix according to each vertex coordinate;
a bar code without angular tilt is generated from the perspective transformation matrix map.
In one embodiment, the processor when executing the computer program further performs the steps of:
determining the type of the bar code according to the start-stop sign of the bar code;
determining a corresponding decoding mode according to the type of the bar code;
and decoding the bar code according to the decoding mode to obtain the code value of the bar code.
In one embodiment, a computer readable storage medium is provided having a computer program stored thereon, which when executed by a processor, performs the steps of:
acquiring an image to be identified;
calculating gradient amplitude and angle of each pixel point of the image to be identified;
carrying out gradient quantization on the image to be identified according to the gradient amplitude of each pixel point to obtain a plurality of quantization areas;
Performing region growing on each quantization region according to the angle of each pixel point to obtain a plurality of region straight lines;
clustering the straight lines of each region to obtain a bar code region and a center point of the bar code;
and calculating the angle of the bar code according to the straight line of each area in the bar code area.
In one embodiment, the computer program when executed by the processor further performs the steps of:
gradient division is carried out on each pixel point in the image to be identified according to a preset gradient division standard, so that a plurality of gradient areas are obtained;
and quantizing the pixel points in each gradient region to obtain quantized regions.
In one embodiment, the computer program when executed by the processor further performs the steps of:
randomly selecting a pixel point from the quantization area as a reference point;
performing main direction consistency judgment on other pixel points in the quantization area where the reference points are located according to the reference points;
removing pixels which do not meet the main direction consistency from the quantization area;
carrying out main direction consistency judgment on four adjacent pixel points around each pixel point meeting the main direction consistency and other pixel points in the quantization area;
extracting pixel points meeting the main direction consistency from adjacent pixel points to a quantization area, and removing the pixel points from the original quantization area;
And traversing each quantization region to obtain a plurality of region lines.
In one embodiment, the computer program when executed by the processor further performs the steps of:
calculating the transverse-longitudinal ratio of the straight line of each region;
determining the transverse and longitudinal directions of the regional straight line according to the transverse and longitudinal ratio of the regional straight line;
determining the coordinates of end point pixel points corresponding to the two ends of the area straight line, the coordinates of the middle point of the area straight line and the inclination angle of the area straight line according to the transverse and longitudinal directions of the area straight line;
sequentially extracting any one regional straight line as a reference straight line, and calculating clustering parameters of the reference straight line and each other regional straight lines; the clustering parameter is the product of the distance between the midpoint of the reference straight line and the midpoint of any other regional straight line and the angle difference between the reference straight line and the regional straight line;
judging whether the clustering parameters of the reference straight line and the rest of each regional straight line are smaller than a preset threshold value, if so, accumulating the clustering parameters to obtain a clustering parameter accumulated value when each regional straight line is respectively used as the reference straight line, and if so, eliminating the corresponding regional straight line to obtain a regional straight line set corresponding to the clustering parameter accumulated value; and determining an area formed by the area straight line set with the smallest cluster parameter accumulated value as a bar code area, wherein the midpoint of the reference straight line corresponding to the area straight line set with the smallest cluster parameter accumulated value is the center point of the bar code.
In one embodiment, the computer program when executed by the processor further performs the steps of:
randomly sampling the straight line midpoints of the bar code area to obtain local points;
and performing straight line fitting on the local inner points, calculating the angle of the fitted straight line, and determining the angle of the fitted straight line as the angle of the bar code.
In one embodiment, the method further comprises:
determining a start-stop symbol of the bar code along the angle of the bar code according to the center point of the bar code;
calculating each vertex coordinate of the bar code area according to the start-stop sign of the bar code;
fitting a perspective transformation matrix according to each vertex coordinate;
a bar code without angular tilt is generated from the perspective transformation matrix map.
In one embodiment, the computer program when executed by the processor further performs the steps of:
determining the type of the bar code according to the start-stop sign of the bar code;
determining a corresponding decoding mode according to the type of the bar code;
and decoding the bar code according to the decoding mode to obtain the code value of the bar code.
Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in embodiments provided herein may include non-volatile and/or volatile memory. The nonvolatile memory can include Read Only Memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous Link DRAM (SLDRAM), memory bus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), among others.
The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The above examples illustrate only a few embodiments of the application, which are described in detail and are not to be construed as limiting the scope of the application. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the application, which are all within the scope of the application. Accordingly, the scope of protection of the present application is to be determined by the appended claims.
Claims (9)
1. A method of bar code positioning, the method comprising:
acquiring an image to be identified;
calculating the gradient amplitude and the angle of each pixel point of the image to be identified;
carrying out gradient quantization on the image to be identified according to the gradient amplitude of each pixel point to obtain a plurality of quantization areas;
performing region growing on each quantization region according to the angle of each pixel point to obtain a plurality of region straight lines; randomly selecting a pixel point from the quantization area as a reference point; performing main direction consistency judgment on other pixel points in the quantization area according to the reference points; removing pixels which do not meet the main direction consistency from the quantization area; carrying out main direction consistency judgment on four adjacent pixel points around each pixel point meeting main direction consistency and other pixel points in the quantization area; extracting pixel points meeting the main direction consistency from the adjacent pixel points to the quantization area, and removing the pixel points from the original quantization area; traversing each quantization area to obtain a plurality of area lines;
Clustering the straight lines of each region to obtain a bar code region and a center point of the bar code;
and calculating the angle of the bar code according to the straight line of each area in the bar code area.
2. The bar code positioning method according to claim 1, wherein the step of performing gradient quantization on the image to be identified according to the gradient magnitude of each pixel point to obtain a plurality of quantization areas comprises:
performing gradient division on each pixel point in the image to be identified according to a preset gradient division standard to obtain a plurality of gradient areas;
and quantizing the pixel points in each gradient region to obtain the quantized region.
3. The bar code positioning method according to claim 1, wherein the step of clustering the respective area straight lines to obtain a bar code area and a center point of the bar code comprises:
calculating the transverse-longitudinal ratio of the straight line of each region;
determining the transverse and longitudinal directions of the area straight line according to the transverse and longitudinal ratio of the area straight line;
determining the coordinates of endpoint pixel points corresponding to two ends of the area straight line, the coordinates of the midpoint of the area straight line and the inclination angle of the area straight line according to the transverse and longitudinal directions of the area straight line;
Sequentially extracting any one of the regional straight lines as a reference straight line, and calculating clustering parameters of the reference straight line and each of the rest regional straight lines; the clustering parameter is the product of the distance between the midpoint of the reference straight line and the midpoint of any one of the rest of the area straight lines and the angle difference between the reference straight line and the area straight line;
judging whether the clustering parameters of the reference straight line and each of the rest area straight lines are smaller than a preset threshold value, accumulating the clustering parameters if the clustering parameters are smaller than the preset threshold value, obtaining a clustering parameter accumulated value when each area straight line is respectively used as the reference straight line, and eliminating the corresponding area straight line if the clustering parameters are larger than the preset threshold value, so as to obtain an area straight line set corresponding to the clustering parameter accumulated value; and determining an area formed by the area straight line set with the smallest cluster parameter accumulated value as the bar code area, wherein the midpoint of the reference straight line corresponding to the area straight line set with the smallest cluster parameter accumulated value is the center point of the bar code.
4. The bar code positioning method of claim 1, wherein the step of calculating the angle of the bar code from the respective straight lines of the areas within the bar code area comprises:
Randomly sampling the regional straight line midpoints in the bar code region to obtain local points;
and performing straight line fitting on the local points, calculating the angle of the fitted straight line, and determining the angle of the fitted straight line as the angle of the bar code.
5. The bar code positioning method of any of claims 1 to 4, further comprising:
determining a start-stop symbol of the bar code along the bar code angle according to the center point of the bar code;
calculating each vertex coordinate of the bar code area according to the start and stop Fu Ji of the bar code;
fitting a perspective transformation matrix according to each vertex coordinate;
and generating the bar code without angle inclination according to the perspective transformation matrix mapping.
6. The bar code positioning method of claim 5, further comprising:
determining the type of the bar code according to the start-stop sign of the bar code;
determining a corresponding decoding mode according to the type of the bar code;
and decoding the bar code according to the decoding mode to obtain the code value of the bar code.
7. A bar code positioning device, the device comprising:
The image acquisition module is used for acquiring an image to be identified;
the gradient calculation module is used for calculating the gradient amplitude and the gradient angle of each pixel point of the image to be identified;
the region quantization module is used for carrying out gradient quantization on the image to be identified according to the gradient amplitude of each pixel point to obtain a plurality of quantization regions;
the region growing module is used for carrying out region growing on each quantized region according to the angle of each pixel point to obtain a plurality of region straight lines; randomly selecting a pixel point from the quantization area as a reference point; performing main direction consistency judgment on other pixel points in the quantization area according to the reference points; removing pixels which do not meet the main direction consistency from the quantization area; carrying out main direction consistency judgment on four adjacent pixel points around each pixel point meeting main direction consistency and other pixel points in the quantization area; extracting pixel points meeting the main direction consistency from the adjacent pixel points to the quantization area, and removing the pixel points from the original quantization area; traversing each quantization area to obtain a plurality of area lines;
The clustering module is used for carrying out clustering processing on the straight lines of each region to obtain a bar code region and a center point of the bar code;
and the bar code angle calculation module is used for calculating the angle of the bar code according to the straight line of each area in the bar code area.
8. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any of claims 1 to 6 when the computer program is executed.
9. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910995165.XA CN110807342B (en) | 2019-10-18 | 2019-10-18 | Bar code positioning method, bar code positioning device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910995165.XA CN110807342B (en) | 2019-10-18 | 2019-10-18 | Bar code positioning method, bar code positioning device, computer equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110807342A CN110807342A (en) | 2020-02-18 |
| CN110807342B true CN110807342B (en) | 2023-08-11 |
Family
ID=69488865
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910995165.XA Active CN110807342B (en) | 2019-10-18 | 2019-10-18 | Bar code positioning method, bar code positioning device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110807342B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112101059B (en) * | 2020-08-18 | 2023-10-10 | 深圳市优必选科技股份有限公司 | Bar code positioning method, bar code positioning device, terminal equipment and storage medium |
| CN112950540B (en) * | 2021-02-01 | 2022-04-15 | 联宝(合肥)电子科技有限公司 | Bar code identification method and equipment |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104268498A (en) * | 2014-09-29 | 2015-01-07 | 杭州华为数字技术有限公司 | Two-dimension code recognition method and terminal |
| CN107633192A (en) * | 2017-08-22 | 2018-01-26 | 电子科技大学 | Bar code segmentation and reading method under a kind of complex background based on machine vision |
| CN107908996A (en) * | 2017-10-25 | 2018-04-13 | 福建联迪商用设备有限公司 | A kind of method and terminal for extracting bar code information |
-
2019
- 2019-10-18 CN CN201910995165.XA patent/CN110807342B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104268498A (en) * | 2014-09-29 | 2015-01-07 | 杭州华为数字技术有限公司 | Two-dimension code recognition method and terminal |
| CN107633192A (en) * | 2017-08-22 | 2018-01-26 | 电子科技大学 | Bar code segmentation and reading method under a kind of complex background based on machine vision |
| CN107908996A (en) * | 2017-10-25 | 2018-04-13 | 福建联迪商用设备有限公司 | A kind of method and terminal for extracting bar code information |
Non-Patent Citations (1)
| Title |
|---|
| 欧焕锐.QR二维码识别算法及其在新型门禁系统中应用的研究.《中国优秀硕士学位论文全文数据库》.2018,(第第6期期),第I138-1253页. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110807342A (en) | 2020-02-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110738207B (en) | Character detection method for fusing character area edge information in character image | |
| US5245674A (en) | Image processing using distance as a function of direction | |
| CN110659529B (en) | Bar code identification method, bar code identification device, computer equipment and storage medium | |
| CN110956171A (en) | Automatic nameplate identification method and device, computer equipment and storage medium | |
| CN110807342B (en) | Bar code positioning method, bar code positioning device, computer equipment and storage medium | |
| CN112241952B (en) | Brain midline identification method, device, computer equipment and storage medium | |
| US5416851A (en) | Image analysis based on location sampling | |
| CN115759148B (en) | Image processing method, device, computer equipment and computer readable storage medium | |
| Michalak et al. | Fast Binarization of Unevenly Illuminated Document Images Based on Background Estimation for Optical Character Recognition Purposes. | |
| CN111507337A (en) | License plate recognition method based on hybrid neural network | |
| CN113297870A (en) | Image processing method, image processing device, electronic equipment and computer readable storage medium | |
| CN111914890B (en) | Image block matching method between images, image registration method and product | |
| CN115908363B (en) | Tumor cell statistics method, device, equipment and storage medium | |
| CN115880362B (en) | Code region positioning method, device, computer equipment and computer readable storage medium | |
| CN112560856A (en) | License plate detection and identification method, device, equipment and storage medium | |
| CN110490020B (en) | Bar code identification method and device, computer equipment and storage medium | |
| CN111325199B (en) | Text inclination angle detection method and device | |
| CN115620321B (en) | Table identification method and device, electronic equipment and storage medium | |
| CN114511862B (en) | Form identification method and device and electronic equipment | |
| CN113705270B (en) | Method, device, equipment and storage medium for identifying two-dimensional code positioning code area | |
| CN113011132B (en) | Vertical text recognition method, device, computer equipment and storage medium | |
| CN115600619B (en) | Dot matrix two-dimensional code identification method and device, electronic equipment and storage medium | |
| Cui et al. | CMSuG: Competitive mechanism-based superpixel generation method for image segmentation | |
| CN113538291B (en) | Card image inclination correction method, device, computer equipment and storage medium | |
| CN116402842B (en) | Edge defect detection method, device, computer equipment and storage medium |
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 | ||
| CB02 | Change of applicant information |
Address after: 519000 No. 333, Kexing Road, Xiangzhou District, Zhuhai City, Guangdong Province Applicant after: ZHUHAI JIELI TECHNOLOGY Co.,Ltd. Address before: Floor 1-107, building 904, ShiJiHua Road, Zhuhai City, Guangdong Province Applicant before: ZHUHAI JIELI TECHNOLOGY Co.,Ltd. |
|
| CB02 | Change of applicant information | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |