CN120411974B - Method for generating composite label paper based on graphic and text information and composite label paper - Google Patents
Method for generating composite label paper based on graphic and text information and composite label paperInfo
- Publication number
- CN120411974B CN120411974B CN202510913078.0A CN202510913078A CN120411974B CN 120411974 B CN120411974 B CN 120411974B CN 202510913078 A CN202510913078 A CN 202510913078A CN 120411974 B CN120411974 B CN 120411974B
- Authority
- CN
- China
- Prior art keywords
- image
- surface image
- information
- information surface
- standard
- 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 OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
- G06V30/12—Detection or correction of errors, e.g. by rescanning the pattern
- G06V30/133—Evaluation of quality of the acquired characters
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
- G06T7/001—Industrial image inspection using an image reference approach
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30168—Image quality inspection
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Quality & Reliability (AREA)
- Multimedia (AREA)
- Image Analysis (AREA)
Abstract
The invention relates to the field of image processing, in particular to a method for generating composite label paper based on graphic information and the composite label paper, wherein the method comprises the following steps: S1, acquiring a standard information surface image and a standard back surface image in advance, and acquiring the information surface image and the back surface image in the generation process. S2, comparing the standard information plane image with the information plane image, and determining a plurality of problem parts in the information plane image. S3, comparing the standard back surface image with the back surface image, and determining a plurality of problem parts in the back surface image. S4, determining problem reasons corresponding to each problem part in the information surface image based on the comparison result corresponding to the information surface image and the comparison result corresponding to the rear surface image, and performing control processing on the generation process according to the problem reasons. The method and the device can know the reason for causing the problems on the composite label paper, and facilitate the optimal control of the generation process of the composite label paper.
Description
Technical Field
The invention relates to the field of image processing, in particular to a method for generating composite label paper based on graphic information and the composite label paper.
Background
Composite label paper is widely used in the fields of production and manufacture, and therefore, quality control for the production of composite label paper is necessary in the production process of composite label paper.
The Chinese patent application with the publication number of CN109934809A discloses a paper label character defect detection method which comprises the following steps of S1, classifying labels to obtain all label types and corresponding label templates, S2, setting a ROI, obtaining an ROI image in a current complete image, obtaining the current label types and the corresponding label templates, S3, matching the ROI image with the current label templates to obtain a registration image, S4, obtaining an AND or graph, setting a dynamic threshold, highlighting flaw areas of the AND or graph according to the dynamic threshold, and S5, calculating flaw area, and judging whether the current flaw area exceeds a preset flaw area threshold of the current label types. However, the above patent application can only detect flaws from the label paper, and cannot determine the cause of the flaws. Therefore, the invention provides a method for generating composite label paper based on graphic information.
Disclosure of Invention
The invention determines a plurality of problem parts in the information surface image by comparing the standard information surface image with the information surface image, determines a plurality of problem parts in the back surface image by comparing the standard back surface image with the back surface image, and determines the problem reason corresponding to each problem part in the information surface image based on the comparison result corresponding to the information surface image and the comparison result corresponding to the back surface image. The invention aims to intelligently acquire the reasons for the problems on the composite label paper.
The invention provides a method for generating composite label paper based on graphic information, which comprises the following steps:
S1, acquiring a standard information surface image corresponding to an information surface of composite label paper and a standard rear surface image corresponding to a rear surface of the composite label paper in advance, and acquiring the information surface image corresponding to the information surface of the composite label paper and the rear surface image corresponding to the rear surface of the composite label paper in a generation process;
s2, comparing the standard information surface image with the information surface image, and determining a plurality of problem parts in the information surface image;
s3, comparing the standard back surface image with the back surface image, and determining a plurality of problem parts in the back surface image;
S4, determining problem reasons corresponding to each problem part in the information surface image based on the comparison result corresponding to the information surface image and the comparison result corresponding to the rear surface image, and performing control processing on the generation process according to the problem reasons.
As a preferable technical scheme of the invention, the method for determining the problem parts in the information surface image comprises the following steps of:
S21, an image coordinate system is established on a standard information surface image by taking an image element at the upper left corner as an origin, taking a horizontal right direction as an x-axis positive direction, taking a vertical downward direction as a y-axis positive direction, an image coordinate system is established on the information surface image by the same method, the standard information surface image and the information surface image are respectively divided into a plurality of image blocks, and each image block contains the same number of image elements;
S22, determining the image blocks in the standard information surface image with the same address aiming at the image blocks in the information surface image, calculating the sum of the image element values of all the image elements contained in the image blocks in the standard information surface image, calculating the difference value of the image elements contained in the image blocks in the standard information surface image and judging the image blocks in the information surface image as problem image blocks when the difference value is larger than a specific value;
S23, forming a problem part by using a plurality of adjacent problem image blocks in the information surface image, and recording addresses of the problem part.
As a preferred technical solution of the present invention, for comparing a standard back surface image with a back surface image, determining a plurality of problem portions in the back surface image, the method includes the steps of:
S31, taking an image element at the upper right corner as an origin, taking a horizontal left direction as an x-axis positive direction, taking a vertical downward direction as a y-axis positive direction, establishing an image coordinate system on a standard back surface image, establishing an image coordinate system on the back surface image by the same method, and dividing the standard back surface image and the back surface image into a plurality of image blocks respectively by a method of dividing an information surface image;
S32, determining the image blocks in the standard back surface image with the same address aiming at the image blocks in the back surface image, calculating the sum of the image element values of all the image elements contained in the image blocks in the standard back surface image, and judging the image blocks in the back surface image to be problem image blocks under the condition that the difference value of the sum and the sum is larger than a preset value;
s33, forming a problem part by using a plurality of adjacent problem image blocks in the rear surface image, and recording addresses of the problem part.
As a preferable technical scheme of the invention, specific numerical values are set through the following steps:
S221, generating test images with different problem levels, and respectively comparing the standard information surface image with the test images with different problem levels to obtain to-be-selected specific values respectively corresponding to the test images with different problem levels;
S222, setting a problem level range, determining a plurality of to-be-selected specific values corresponding to the problem level range, and taking the smallest to-be-selected specific value in the plurality of to-be-selected specific values as the specific value;
s223, judging whether the specific numerical value needs to be reset, if yes, jumping to the S221, and if no, ending all the steps.
As a preferable technical scheme of the invention, generating test images with different question levels comprises setting a plurality of question types, generating question images with different question levels for each question type, adding a plurality of question images with the same question level into a standard information plane image by taking an image block as a basic unit to obtain test images with corresponding question levels.
As a preferred technical scheme of the invention, the standard information surface image and the test images of each problem level are respectively compared to obtain the specific numerical values to be selected corresponding to the test images of each problem level, and the method comprises the following steps:
s2211, setting a preliminary specific numerical value, and selecting a test image of the highest problem level;
S2212, comparing the standard information surface image with the selected test image, determining a plurality of problem parts in the selected test image, judging whether the plurality of problem parts comprise all problem images in the selected test image, if so, taking the preliminary specific value as the specific value to be selected, continuing the next step, and if not, continuing S2214;
S2213, judging whether to obtain the specific values to be selected corresponding to the test images of the problem levels respectively, if yes, ending all the steps, and if no, continuing the next step;
S2214, selecting a test image with the highest problem level from all test images not yet obtained with the selected specific value, reducing the initial specific value by one step length, and jumping to the S2212.
As a preferable technical scheme of the invention, the method reduces the preliminary specific value by one step length, and comprises the following steps:
S22141, determining that a test image with a specific value to be selected is acquired last time, comparing the standard information surface image with the determined test image, acquiring a plurality of differences corresponding to each image block in the determined test image, and establishing a first distribution histogram of the plurality of differences;
S22142, comparing the standard information surface image with the test image selected at this time to obtain a plurality of difference values corresponding to each image block in the test image selected at this time, and establishing a second distribution histogram of the plurality of difference values;
S22143, searching a difference value corresponding to the determined specific value to be selected corresponding to the test image in the first distribution histogram, determining a difference value corresponding to the first trough in the second distribution histogram, increasing the value represented by the step length under the condition that the difference between the two values is larger than a preset first threshold value, reducing the value represented by the step length under the condition that the difference between the two values is smaller than a preset second threshold value, and reducing the value represented by the step length to reduce the specific value by one step length.
As a preferred technical solution of the present invention, determining a problem cause corresponding to each problem portion in the information plane image based on a comparison result corresponding to the information plane image and a comparison result corresponding to the rear surface image, includes the steps of:
S41, judging whether the problem part with the same address exists in the rear surface image aiming at the problem part in the information surface image, if not, judging that the problem part in the information surface image is caused by printing reasons, and if so, continuing the next step;
s42, judging whether the scale of the problem part in the information surface image is larger than a preset threshold value, and if not, canceling the problem part in the information surface image, and if so, judging that the problem part in the information surface image is caused by the reason of the composite label paper.
The invention also provides a composite label paper comprising an information surface and a rear surface, which is produced by the method according to any one of the above.
Compared with the prior art, the invention has the following beneficial effects:
in the technical scheme provided by the invention, firstly, a standard information surface image corresponding to the information surface of the composite label paper and a standard rear surface image corresponding to the rear surface of the composite label paper are obtained in advance, and in the process of generation, the information surface image corresponding to the information surface of the composite label paper and the rear surface image corresponding to the rear surface of the composite label paper are obtained. And secondly, comparing the standard information surface image with the information surface image, and determining a plurality of problem parts in the information surface image. And thirdly, comparing the standard back surface image with the back surface image, and determining a plurality of problem parts in the back surface image. And finally, determining the problem reasons corresponding to each problem part in the information surface image based on the comparison result corresponding to the information surface image and the comparison result corresponding to the rear surface image, and performing control processing on the generation process according to the problem reasons. The invention can not only check out the problems on the composite label paper, but also automatically learn the reasons for the problems on the composite label paper, thereby being convenient for optimizing and controlling the generation process of the composite label paper.
Drawings
Fig. 1 is a schematic flow chart of a method for generating composite label paper based on graphic information.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
In the description of the present invention, the terms "first," "second," and the like are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include one or more of the described features. In the description of the present invention, the meaning of "a plurality" is two or more, unless explicitly defined otherwise.
In the description of the present invention, the term "for example" is used to mean "serving as an example, instance, or illustration. Any embodiment described as "for example" in this disclosure is not necessarily to be construed as preferred or advantageous over other embodiments. The following description is presented to enable any person skilled in the art to make and use the invention. In the following description, details are set forth for purposes of explanation. It will be apparent to one of ordinary skill in the art that the present invention may be practiced without these specific details. In other instances, well-known structures and processes have not been described in detail so as not to obscure the description of the invention with unnecessary detail. Thus, the present invention is not intended to be limited to the embodiments shown, but is to be accorded the widest scope consistent with the principles and features disclosed herein.
As shown in fig. 1, the embodiment of the invention provides a method for generating composite label paper based on graphic information, which mainly comprises the following steps:
S1, acquiring a standard information surface image corresponding to an information surface of composite label paper and a standard rear surface image corresponding to a rear surface of the composite label paper in advance, and acquiring the information surface image corresponding to the information surface of the composite label paper and the rear surface image corresponding to the rear surface of the composite label paper in a generation process;
s2, comparing the standard information surface image with the information surface image, and determining a plurality of problem parts in the information surface image;
s3, comparing the standard back surface image with the back surface image, and determining a plurality of problem parts in the back surface image;
S4, determining problem reasons corresponding to each problem part in the information surface image based on the comparison result corresponding to the information surface image and the comparison result corresponding to the rear surface image, and performing control processing on the generation process according to the problem reasons.
Specifically, in order to realize the reason of the problem caused by the acquisition while checking that the composite label paper has the problem, it is mainly proposed that S1 to S4, in S1, the standard information side image corresponding to the information side of the composite label paper and the standard rear surface image corresponding to the rear surface of the composite label paper are acquired in advance, wherein the information side of the composite label paper, that is, the front side of the composite label paper on which the graphic information has been printed, the rear surface of the composite label paper, that is, the rear side of the composite label paper, is not printed with the graphic information, and it is noted that the standard information side image and the standard rear surface image are not problematic, and that in the process of repeatedly printing the graphic information to continuously generate each composite label paper, when one composite label paper is generated, the information side image corresponding to the information side of the composite label paper and the rear surface image corresponding to the rear surface of the composite label paper are acquired, and it is noted that the information side image and the rear surface image may be problematic. In S2, the standard information plane image and the information plane image are compared, and a plurality of problem portions in the information plane image are determined, where the problem portions may be problems such as stains, foreign matters, waves, and concave-convex. In S3, the comparison processing is performed on the standard back surface image and the back surface image, so as to determine a plurality of problem portions in the back surface image, wherein the problem portions may be problems of foreign matters, concave-convex and the like, which are problems of the composite label paper, and it should be noted that the foreign matters in the embodiment refer to the foreign matters penetrating through the composite label paper. In S4, based on the comparison result corresponding to the information surface image and the comparison result corresponding to the rear surface image, that is, the plurality of problem portions in the information surface image and the plurality of problem portions in the rear surface image, the problem causes corresponding to the respective problem portions in the information surface image are determined, the problem causes include the cause of printing and the cause of the composite label paper itself, so that the control processing can be performed for the generation process according to the problem causes while discarding the generated problematic composite label paper, for example, in the case of the cause of printing, maintenance can be performed for printing equipment, and in the case of the cause of the composite label paper itself, the material quality of the composite label paper itself can be improved.
Further, comparing the standard information plane image with the information plane image to determine a plurality of problem parts in the information plane image, including the following steps:
S21, an image coordinate system is established on a standard information surface image by taking an image element at the upper left corner as an origin, taking a horizontal right direction as an x-axis positive direction, taking a vertical downward direction as a y-axis positive direction, an image coordinate system is established on the information surface image by the same method, the standard information surface image and the information surface image are respectively divided into a plurality of image blocks, and each image block contains the same number of image elements;
S22, determining the image blocks in the standard information surface image with the same address aiming at the image blocks in the information surface image, calculating the sum of the image element values of all the image elements contained in the image blocks in the standard information surface image, calculating the difference value of the image elements contained in the image blocks in the standard information surface image and judging the image blocks in the information surface image as problem image blocks when the difference value is larger than a specific value;
S23, forming a problem part by using a plurality of adjacent problem image blocks in the information surface image, and recording addresses of the problem part.
Specifically, a process of comparing a standard information plane image with an information plane image to determine a plurality of problem portions in the information plane image is introduced, in S21, an image element, that is, a pixel, in the upper left corner of the standard information plane image is taken as an origin, an image coordinate system is established in the positive x-axis direction in the right horizontal direction and in the positive y-axis direction in the downward vertical direction, and simultaneously, an image coordinate system is established on the information plane image by the same method, and then the standard information plane image and the information plane image are respectively divided into a plurality of image blocks by the same method, wherein each image block contains the same number of image elements. In S22, for the image blocks in the information plane image, the image blocks in the standard information plane image with the same address are determined, the address refers to coordinates in the coordinate system, the sum of the image element values of all the image elements included in the image blocks in the information plane image and the sum of the image element values of all the image elements included in the image blocks in the standard information plane image are calculated respectively, when the image element values are rgb values, that is, the sum of r values, the sum of g values and the sum of b values of all the image elements are calculated respectively, the difference between the r values, the sum of g values and the sum of b values is calculated, specifically, the difference between the r values, the g values and the sum of b values can be calculated by using a euclidean distance calculation formula, and if the difference is greater than a specific value, the image blocks in the information plane image are determined to be problem image blocks, and the problem image blocks may be spots, foreign matters, ripples, and concave-convex problems. In S23, a plurality of problem image blocks whose coordinates are adjacent to each other in the information plane image are formed into a problem portion, and the address of the problem portion is recorded.
Further, for the comparison processing of the standard back surface image and the back surface image, a plurality of problem parts in the back surface image are determined, and the method comprises the following steps:
S31, taking an image element at the upper right corner as an origin, taking a horizontal left direction as an x-axis positive direction, taking a vertical downward direction as a y-axis positive direction, establishing an image coordinate system on a standard back surface image, establishing an image coordinate system on the back surface image by the same method, and dividing the standard back surface image and the back surface image into a plurality of image blocks respectively by a method of dividing an information surface image;
S32, determining the image blocks in the standard back surface image with the same address aiming at the image blocks in the back surface image, calculating the sum of the image element values of all the image elements contained in the image blocks in the standard back surface image, and judging the image blocks in the back surface image to be problem image blocks under the condition that the difference value of the sum and the sum is larger than a preset value;
s33, forming a problem part by using a plurality of adjacent problem image blocks in the rear surface image, and recording addresses of the problem part.
Specifically, a process of comparing a standard back surface image with a back surface image, determining a plurality of problem portions in the back surface image is described, which is similar to a process of comparing a standard information plane image with an information plane image, determining a plurality of problem portions in the information plane image, and in S31, an image coordinate system is established with an image element in an upper right corner of the standard back surface image as an origin, a horizontal left positive direction as an x-axis, and a vertical downward positive direction as a y-axis, and an image coordinate system is established on the back surface image by the same method, and on the basis of this, the standard back surface image and the back surface image are respectively divided into a plurality of image blocks by the same method as the method of dividing the information plane image. In S32, regarding the image blocks in the rear surface image, the image blocks in the standard rear surface image with the same address are determined, and the sum of the image element values of all the image elements included in the image blocks in the rear surface image and the sum of the image element values of all the image elements included in the image blocks in the standard rear surface image are calculated, respectively, and if the difference between the two is greater than the preset value, it is determined that the image block in the rear surface image is a problem image block, and the problem image block may be a foreign object, a concave-convex problem, or the like. In S33, a plurality of adjacent problem image blocks in the rear surface image are formed into a problem portion, and addresses of the problem portion are recorded.
Further, determining a problem reason corresponding to each problem portion in the information plane image based on the comparison result corresponding to the information plane image and the comparison result corresponding to the rear surface image, including the steps of:
S41, judging whether the problem part with the same address exists in the rear surface image aiming at the problem part in the information surface image, if not, judging that the problem part in the information surface image is caused by printing reasons, and if so, continuing the next step;
s42, judging whether the scale of the problem part in the information surface image is larger than a preset threshold value, and if not, canceling the problem part in the information surface image, and if so, judging that the problem part in the information surface image is caused by the reason of the composite label paper.
Specifically, a procedure is introduced for determining the cause of the problem corresponding to each of the problem portions in the information plane image based on the comparison result corresponding to the information plane image and the comparison result corresponding to the rear surface image, and in S41, it is determined whether there is a problem portion with the same address in the rear surface image for the problem portion in the information plane image, and if not, it can be considered that the problem portion in the information plane image is caused by the print cause, and if so, S42 is continued. In S42, it is determined whether the size, i.e., the area size, of the problem portion in the information plane image is greater than a preset threshold, which is determined according to the actual application scenario, and if not, the problem portion in the information plane image is withdrawn, that is, the problem portion in the information plane image is considered to be less negatively affected, and may not be considered as a problem portion, so that the number of discarded composite label sheets may be reduced to some extent, and if greater than or equal to this, the problem portion in the information plane image may be considered to be caused by the composite label sheet itself.
Further, a specific value is set by:
S221, generating test images with different problem levels, and respectively comparing the standard information surface image with the test images with different problem levels to obtain to-be-selected specific values respectively corresponding to the test images with different problem levels;
S222, setting a problem level range, determining a plurality of to-be-selected specific values corresponding to the problem level range, and taking the smallest to-be-selected specific value in the plurality of to-be-selected specific values as the specific value;
s223, judging whether a specific numerical value needs to be reset, if yes, jumping to S221, and if no, ending all the steps;
Further, generating test images with different question levels includes setting a plurality of question types, generating question images with different question levels for each question type, adding a plurality of question images with the same question level into a standard information plane image by taking an image block as a basic unit, and obtaining test images with corresponding question levels.
Specifically, the process of setting the specific value is described, and it is conceivable that the process of setting the preset value is similar to the process of setting the specific value, so that the specific value may be directly used without further description. In S221, test images with different problem levels are generated, and the test images with different problem levels are respectively compared with the test images with different problem levels for the purpose of obtaining the to-be-selected specific numerical values respectively corresponding to the test images with different problem levels, wherein the specific method for generating the test images with different problem levels is that a plurality of problem types, such as stain, concave-convex, ripple, foreign matters and the like, are set, the problem images with different problem levels are generated for each problem type, for example, for the stain type, the stain image with high problem level is heavier, the problem image takes an image block as a basic unit, the scale of the image block is the same as that of the image block mentioned above, a plurality of problem images with the same problem level are added into the standard information surface image for obtaining the test images with corresponding problem levels, for example, 4 problem types exist, and the problem images with high problem level, medium problem level and low problem level are simultaneously added into the standard information surface image for obtaining the test image with high problem level. In S222, a problem level range is set, specifically, the problem level range may be set according to the tolerance degree of the problem occurring on the composite label paper, for example, the problem level range is a high problem level and a medium problem level, a plurality of specific values to be selected corresponding to the problem level range are determined, and the smallest specific value to be selected in the plurality of specific values to be selected is regarded as a specific value. In S223, it is determined whether the specific value needs to be reset, if so, for example, when the problem type or the problem level needs to be increased, the execution is continued by jumping S221, so that the specific value can be dynamically changed according to the application requirement, and if not, all the steps are ended.
Further, the comparison processing is respectively carried out on the standard information surface image and the test images of each problem level to obtain the to-be-selected specific numerical values respectively corresponding to the test images of each problem level, and the method comprises the following steps:
s2211, setting a preliminary specific numerical value, and selecting a test image of the highest problem level;
S2212, comparing the standard information surface image with the selected test image, determining a plurality of problem parts in the selected test image, judging whether the plurality of problem parts comprise all problem images in the selected test image, if so, taking the preliminary specific value as the specific value to be selected, continuing the next step, and if not, continuing S2214;
S2213, judging whether to obtain the specific values to be selected corresponding to the test images of the problem levels respectively, if yes, ending all the steps, and if no, continuing the next step;
S2214, selecting a test image with the highest problem level from all test images not yet obtained with the selected specific value, reducing the initial specific value by one step length, and jumping to S2212.
Specifically, a process of comparing the standard information plane image with the test images of each problem level to obtain the candidate specific values corresponding to the test images of each problem level is introduced, in S2211, a preliminary specific value is set, the preliminary specific value is set as a maximum value at first, and the test image of the highest problem level is selected from the test images of different problem levels. In S2212, the comparison processing is performed on the standard information plane image and the selected test image, and a plurality of problem portions in the selected test image are determined, where the process of the comparison processing is the same as the process of the comparison processing performed on the standard information plane image and the information plane image, so that details are not repeated, it is determined whether the plurality of problem portions include all problem images in the selected test image, if yes, the preliminary specific value is used as the specific value to be selected, and the next step is continued, and if no, S2214 is continued. In S2213, it is determined whether or not the candidate specific values corresponding to the test images of all the problem levels are obtained, if so, all the steps are ended, and if not, S2214 is continued. In S2214, from all the test images for which the specific value to be selected is not yet obtained, the test image of the highest problem level is selected, and the preliminary specific value is reduced by one step, and step S2212 is skipped, and it is noted that the value represented by the step is already preliminarily set, for example, the value represented by the preliminary set step is 2, before the execution of step S2211 is started, the preliminary specific value is reduced by one step each time, that is, by 2, before the specific value to be selected corresponding to the test image of the highest problem level is obtained, and the description will be continued hereinafter, and after the specific value to be selected corresponding to the test image of the highest problem level is obtained, how to dynamically adjust the value represented by the step for which the preliminary specific value is reduced.
Further, the step of reducing the preliminary specific value by one step comprises the following steps:
S22141, determining that a test image with a specific value to be selected is acquired last time, comparing the standard information surface image with the determined test image, acquiring a plurality of differences corresponding to each image block in the determined test image, and establishing a first distribution histogram of the plurality of differences;
S22142, comparing the standard information surface image with the test image selected at this time to obtain a plurality of difference values corresponding to each image block in the test image selected at this time, and establishing a second distribution histogram of the plurality of difference values;
S22143, searching a difference value corresponding to the determined specific value to be selected corresponding to the test image in the first distribution histogram, determining a difference value corresponding to the first trough in the second distribution histogram, increasing the value represented by the step length under the condition that the difference between the two values is larger than a preset first threshold value, reducing the value represented by the step length under the condition that the difference between the two values is smaller than a preset second threshold value, and reducing the value represented by the step length to reduce the specific value by one step length.
Specifically, a process of reducing the preliminary specific value by one step after obtaining the specific value to be selected corresponding to the test image with the highest problem level is introduced, in S22141, the test image with the specific value to be selected is determined to be obtained last time, the comparison processing is performed on the standard information plane image and the determined test image, and the process of the comparison processing is the same as the process of the comparison processing performed on the standard information plane image and the information plane image, so that a plurality of difference values corresponding to each image block in the determined test image are obtained through the comparison processing, a first distribution histogram of the plurality of difference values is established, the horizontal axis of the first distribution histogram represents the difference value, and the vertical axis represents the occurrence number of the difference value. In S22142, the comparison process is performed on the standard information plane image and the test image selected this time, where the process of the comparison process is the same as the process of the comparison process performed on the standard information plane image and the information plane image, so that details are not repeated, a plurality of differences corresponding to each image block in the test image selected this time are obtained through the comparison process, a second distribution histogram of the plurality of differences is created, the horizontal axis of the second distribution histogram also represents the differences, and the vertical axis also represents the occurrence times of the differences. In S22143, the difference value corresponding to the determined specific value to be selected corresponding to the test image is found in the first distribution histogram, the difference value may be the same as or may be similar to the specific value to be selected corresponding to the determined test image, the difference value corresponding to the first trough is determined in the second distribution histogram, because there is no problem image in most of the range of the selected test image, so that the number of difference values with smaller values is large, it may be determined that all problem images in the selected test image are possible according to the difference value corresponding to the first trough, the difference between the two is calculated, if the difference value is larger than the preset first threshold, the preset first threshold is determined according to the actual application condition, in order to shorten the time for obtaining the specific value to be selected corresponding to the selected test image, for example, the value represented by the step size should be increased from 2 to 4, then the preliminary specific value is decreased by one step size, namely by 4, if the difference between the two is smaller than the preset second threshold, the second threshold is determined according to the actual application condition, the preset second threshold is smaller than the preset first threshold is smaller, it is guaranteed that the specific value corresponding to be able to obtain the specific value to be decreased from 1, for example, the preliminary step size should be decreased by 1.
The invention also provides a composite label paper, which comprises an information surface and a rear surface, wherein the composite label paper is produced by using any one of the methods, the information surface is facial tissue, the rear surface is a hot melt adhesive film, and the facial tissue and the hot melt adhesive film are firmly covered together.
Specifically, the facial tissue may be plain paper or coated paper. The hot melt adhesive film is a film made of hot melt adhesive materials, the thickness is generally between 0.02 and 0.05mm, the film can be melted into liquid glue after the hot melt adhesive film is heated to the melting temperature, the film has good viscosity in the bonding process, the heating temperature and the heating time are required to be adjusted according to the thickness and the melting temperature index difference of the hot melt adhesive film, the label is heated for 15 to 30 seconds at the temperature of 80 to 150 ℃ generally, and the hot melt adhesive film on the back of the label paper can be labeled after being in the melting state. If the object to be labeled is a high-temperature object with the temperature of 80-150 ℃, the label can be directly labeled without heating. After the label is pasted, the label is further firm along with the reduction of temperature and is not easy to tear. In the production process, after being preheated, the facial tissue paper is covered with the hot-melt film material, passes through the middle of the heating roller and the pressure roller, and is firmly covered with the facial tissue paper and the hot-melt film under the dual actions of heating and pressure, and after being cooled by cold air, the facial tissue paper and the hot-melt film are cut according to the size of a target label, so that a label paper product is obtained.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (5)
1. The method for generating the composite label paper based on the graphic information is characterized by comprising the following steps of:
S1, acquiring a standard information surface image corresponding to an information surface of composite label paper and a standard rear surface image corresponding to a rear surface of the composite label paper in advance, and acquiring the information surface image corresponding to the information surface of the composite label paper and the rear surface image corresponding to the rear surface of the composite label paper in a generation process;
s2, comparing the standard information surface image with the information surface image, and determining a plurality of problem parts in the information surface image;
s3, comparing the standard back surface image with the back surface image, and determining a plurality of problem parts in the back surface image;
S4, determining problem reasons corresponding to each problem part in the information surface image based on the comparison result corresponding to the information surface image and the comparison result corresponding to the rear surface image, and performing control processing on the generation process according to the problem reasons;
comparing the standard information surface image with the information surface image to determine a plurality of problem parts in the information surface image, comprising the following steps:
S21, an image coordinate system is established on a standard information surface image by taking an image element at the upper left corner as an origin, taking a horizontal right direction as an x-axis positive direction, taking a vertical downward direction as a y-axis positive direction, an image coordinate system is established on the information surface image by the same method, the standard information surface image and the information surface image are respectively divided into a plurality of image blocks, and each image block contains the same number of image elements;
S22, determining the image blocks in the standard information surface image with the same address aiming at the image blocks in the information surface image, calculating the sum of the image element values of all the image elements contained in the image blocks in the standard information surface image, calculating the difference value of the image elements contained in the image blocks in the standard information surface image and judging the image blocks in the information surface image as problem image blocks when the difference value is larger than a specific value;
S23, forming a problem part by using a plurality of adjacent problem image blocks in the information surface image, and recording addresses of the problem part;
The specific value is set by the following steps:
S221, generating test images with different problem levels, and respectively comparing the standard information surface image with the test images with different problem levels to obtain to-be-selected specific values respectively corresponding to the test images with different problem levels;
S222, setting a problem level range, determining a plurality of to-be-selected specific values corresponding to the problem level range, and taking the smallest to-be-selected specific value in the plurality of to-be-selected specific values as the specific value;
s223, judging whether a specific numerical value needs to be reset, if yes, jumping to the S221, and if no, ending all the steps;
Respectively comparing the standard information surface image with the test images of all the problem levels to obtain to-be-selected specific values respectively corresponding to the test images of all the problem levels, wherein the method comprises the following steps:
s2211, setting a preliminary specific numerical value, and selecting a test image of the highest problem level;
S2212, comparing the standard information surface image with the selected test image, determining a plurality of problem parts in the selected test image, judging whether the plurality of problem parts comprise all problem images in the selected test image, if so, taking the preliminary specific value as the specific value to be selected, continuing the next step, and if not, continuing S2214;
S2213, judging whether to obtain the specific values to be selected corresponding to the test images of the problem levels respectively, if yes, ending all the steps, and if no, continuing the next step;
S2214, selecting a test image with the highest problem level from all test images which do not acquire the specific value to be selected, reducing the initial specific value by one step length, and jumping to the S2212;
Reducing the preliminary specific value by one step, comprising the steps of:
S22141, determining that a test image with a specific value to be selected is acquired last time, comparing the standard information surface image with the determined test image, acquiring a plurality of differences corresponding to each image block in the determined test image, and establishing a first distribution histogram of the plurality of differences;
S22142, comparing the standard information surface image with the test image selected at this time to obtain a plurality of difference values corresponding to each image block in the test image selected at this time, and establishing a second distribution histogram of the plurality of difference values;
S22143, searching a difference value corresponding to the determined specific value to be selected corresponding to the test image in the first distribution histogram, determining a difference value corresponding to the first trough in the second distribution histogram, increasing the value represented by the step length under the condition that the difference between the two values is larger than a preset first threshold value, reducing the value represented by the step length under the condition that the difference between the two values is smaller than a preset second threshold value, and reducing the value represented by the step length to reduce the specific value by one step length.
2. The method for generating composite label stock based on graphic information according to claim 1, wherein the comparing process is performed for the standard back surface image and the back surface image to determine a plurality of problem portions in the back surface image, comprising the steps of:
S31, taking an image element at the upper right corner as an origin, taking a horizontal left direction as an x-axis positive direction, taking a vertical downward direction as a y-axis positive direction, establishing an image coordinate system on a standard back surface image, establishing an image coordinate system on the back surface image by the same method, and dividing the standard back surface image and the back surface image into a plurality of image blocks respectively by a method of dividing an information surface image;
S32, determining the image blocks in the standard back surface image with the same address aiming at the image blocks in the back surface image, calculating the sum of the image element values of all the image elements contained in the image blocks in the standard back surface image, and judging the image blocks in the back surface image to be problem image blocks under the condition that the difference value of the sum and the sum is larger than a preset value;
s33, forming a problem part by using a plurality of adjacent problem image blocks in the rear surface image, and recording addresses of the problem part.
3. The method for generating composite label paper based on graphic information according to claim 2, wherein generating test images with different question levels comprises setting a plurality of question types, generating a question image with different question levels for each question type, adding the plurality of question images with the same question level to a standard information plane image in a unit of image block to obtain the test image with the corresponding question level.
4. A method of generating a composite label sheet based on graphic information as recited in claim 3, wherein the problem cause corresponding to each problem portion in the information face image is determined based on the comparison result corresponding to the information face image and the comparison result corresponding to the rear surface image, comprising the steps of:
S41, judging whether the problem part with the same address exists in the rear surface image aiming at the problem part in the information surface image, if not, judging that the problem part in the information surface image is caused by printing reasons, and if so, continuing the next step;
s42, judging whether the scale of the problem part in the information surface image is larger than a preset threshold value, and if not, canceling the problem part in the information surface image, and if so, judging that the problem part in the information surface image is caused by the reason of the composite label paper.
5. A composite label sheet comprising an information side and a rear surface, wherein the composite label sheet is produced by the method of any one of claims 1-4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202510913078.0A CN120411974B (en) | 2025-07-03 | 2025-07-03 | Method for generating composite label paper based on graphic and text information and composite label paper |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202510913078.0A CN120411974B (en) | 2025-07-03 | 2025-07-03 | Method for generating composite label paper based on graphic and text information and composite label paper |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN120411974A CN120411974A (en) | 2025-08-01 |
| CN120411974B true CN120411974B (en) | 2025-11-11 |
Family
ID=96512391
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202510913078.0A Active CN120411974B (en) | 2025-07-03 | 2025-07-03 | Method for generating composite label paper based on graphic and text information and composite label paper |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN120411974B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109934809A (en) * | 2019-03-08 | 2019-06-25 | 深慧视(深圳)科技有限公司 | A kind of paper labels character defect inspection method |
| CN115830004A (en) * | 2022-12-27 | 2023-03-21 | 凌云光技术股份有限公司 | Surface defect detection method, device, computer equipment and storage medium |
| CN119574560A (en) * | 2024-11-26 | 2025-03-07 | 湖南远大包装科技有限公司 | A method for detecting defects in printed images of packaging boxes |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103310211B (en) * | 2013-04-26 | 2016-04-06 | 四川大学 | A kind ofly fill in mark recognition method based on image procossing |
| CN112101317B (en) * | 2020-11-17 | 2021-02-19 | 深圳壹账通智能科技有限公司 | Page direction identification method, device, equipment and computer readable storage medium |
| CN119399554B (en) * | 2024-12-31 | 2025-03-11 | 北京茄豆网络科技有限公司 | Label defect detection method and system based on image processing |
-
2025
- 2025-07-03 CN CN202510913078.0A patent/CN120411974B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109934809A (en) * | 2019-03-08 | 2019-06-25 | 深慧视(深圳)科技有限公司 | A kind of paper labels character defect inspection method |
| CN115830004A (en) * | 2022-12-27 | 2023-03-21 | 凌云光技术股份有限公司 | Surface defect detection method, device, computer equipment and storage medium |
| CN119574560A (en) * | 2024-11-26 | 2025-03-07 | 湖南远大包装科技有限公司 | A method for detecting defects in printed images of packaging boxes |
Also Published As
| Publication number | Publication date |
|---|---|
| CN120411974A (en) | 2025-08-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114937055B (en) | Image self-adaptive segmentation method and system based on artificial intelligence | |
| WO2003019274A1 (en) | Method for sorting ununiformity of liquid crystal display panel, sorting apparatus, and information recorded medium with recorded program for executing this sorting | |
| CN108388885A (en) | The identification in real time of more people's features towards large-scale live scene and automatic screenshot method | |
| CN110667146A (en) | Film thickness acquisition method of film section image | |
| CN118150596B (en) | RFID smart card defect detection method and system | |
| CN108960235A (en) | A method of answer card filling block for identification | |
| CN109030502A (en) | A kind of welding point defect detection system based on machine vision | |
| CN120411974B (en) | Method for generating composite label paper based on graphic and text information and composite label paper | |
| CN113628161A (en) | Defect detection method, defect detection device and computer-readable storage medium | |
| CN107310133B (en) | BOPP film method for controlling thickness based on image procossing | |
| CN120182560A (en) | A method and system for intelligent planning of concrete 3D printing paths based on machine vision | |
| CN117475205A (en) | Defect type identification method, defect type identification device, control device and storage medium | |
| CN114919792B (en) | System and method for detecting abnormality of film sticking of steel belt | |
| CN113960071B (en) | Quality detection method and system for color printing products | |
| CN103605973A (en) | Image character detection and identification method | |
| CN114926403B (en) | SFR-based flexible printing ghost detection method and device | |
| JP7081718B2 (en) | Electric pipe welding monitoring method, electric pipe manufacturing method, electric pipe welding monitoring device, and electric pipe manufacturing equipment | |
| CN115984160A (en) | A Machine Vision System Based on Functional Integration and Association | |
| CN120805510B (en) | Online surface activation treatment method for biaxially oriented PET (polyethylene terephthalate) highlight film | |
| KR20050052064A (en) | Method for detecting regular mura in a light-related plate element for a flat panel | |
| CN116359250B (en) | CCS welding and hot-pressing riveting synchronous detection method and system | |
| JP3118828B2 (en) | Judgment method of image quality in transfer printing method | |
| JP3252555B2 (en) | Paint surface dripping measuring device and paint film thickness measuring device | |
| CN214408733U (en) | A pole piece defect detection and coding integrated machine device | |
| CN119403054A (en) | Intelligent solder paste adding method for fully automatic visual printing machine based on visual interactive recognition |
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 |