CN114419043B - Method and system for detecting new printing material by optical means - Google Patents

Method and system for detecting new printing material by optical means Download PDF

Info

Publication number
CN114419043B
CN114419043B CN202210320084.1A CN202210320084A CN114419043B CN 114419043 B CN114419043 B CN 114419043B CN 202210320084 A CN202210320084 A CN 202210320084A CN 114419043 B CN114419043 B CN 114419043B
Authority
CN
China
Prior art keywords
printing
index
image
obtaining
sequence
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
Application number
CN202210320084.1A
Other languages
Chinese (zh)
Other versions
CN114419043A (en
Inventor
陆逸平
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Nantong People Color Printing Co ltd
Original Assignee
Nantong People Color Printing Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Nantong People Color Printing Co ltd filed Critical Nantong People Color Printing Co ltd
Priority to CN202210320084.1A priority Critical patent/CN114419043B/en
Publication of CN114419043A publication Critical patent/CN114419043A/en
Application granted granted Critical
Publication of CN114419043B publication Critical patent/CN114419043B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR 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
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
    • G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/90—Determination of colour characteristics
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10024—Color image
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR 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
    • G06T2207/30108—Industrial image inspection
    • G06T2207/30144—Printing quality

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Human Resources & Organizations (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Economics (AREA)
  • Strategic Management (AREA)
  • Development Economics (AREA)
  • Educational Administration (AREA)
  • Quality & Reliability (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Game Theory and Decision Science (AREA)
  • Marketing (AREA)
  • Operations Research (AREA)
  • Tourism & Hospitality (AREA)
  • General Business, Economics & Management (AREA)
  • Image Analysis (AREA)
  • Spectrometry And Color Measurement (AREA)

Abstract

The invention relates to the technical field of new material product detection, in particular to a method and a system for detecting a new printing material by using an optical means. The method comprises the steps of obtaining a printing image of a new material printing product by utilizing image acquisition equipment comprising a visible light source, and detecting printing quality through an integral printing index obtained by a first printing index and a second printing index. The invention amplifies the image characteristics by optical means, and realizes the analysis and measurement of new materials by optical means.

Description

Method and system for detecting new printing material by optical means
Technical Field
The invention relates to the technical field of new material product detection, in particular to a method and a system for detecting a new printing material by using an optical means.
Background
Compared with the production product of the traditional material, the new material has higher performance and lower cost. The new material is used for producing products, so that effective economic benefits can be brought, the product performance can be improved, and the product quality is improved.
The new printing material has high production value in the aspects of product packaging, product protection and the like. Such as ink made of new materials, printing cloth or printing paper made of new materials, etc. The novel printing material not only can bring excellent color expression to products, but also can play a role in prolonging the service life of the products, providing effective protection for the products and the like.
In the production process of printing new materials, the product needs to be subjected to defect detection, so that the printing quality is ensured. The efficiency of defect detection through electronic equipment or people for carrying out among the prior art is not high, and because the phenomenon such as false retrieval hourglass examine can appear in the operational environment influence, can't realize effectively detecting and measuring the automation of printing product quality.
Disclosure of Invention
In order to solve the above technical problems, an object of the present invention is to provide a method and a system for detecting a new printing material by an optical means, wherein the technical scheme is as follows:
the invention provides a method for detecting a new printing material by an optical means, which comprises the following steps:
collecting a printing image of a new material printing product by using image collecting equipment; the image acquisition equipment comprises a camera and a visible light source;
constructing a pixel value sequence according to the pixel value of each pixel point in the printing image; reconstructing the sequence of pixel values into a plurality of reconstruction vectors; labeling the elements according to the positions of the elements in each reconstruction vector; sorting the elements of the reconstruction vector according to the pixel value, and taking the sorted label sequence as a sorting sequence; obtaining a first printing index according to the sort of the sorting sequence and the entropy of the sorting sequence;
acquiring a standard printing image; fitting the sequence of pixel values of the standard printed image to obtain a standard fit curve; obtaining a fitting curve corresponding to the printing image; obtaining the relative entropy of the fitted curve and the standard fitted curve; obtaining a second printing index according to the discrete point number of the fitting curve and the relative entropy;
obtaining an overall printing index according to the first printing index and the second printing index; and judging the printing quality of the new material according to the integral printing index.
Further, after the image acquisition device is used for acquiring the printing image of the new material printing product, the method further comprises the following steps:
and carrying out gamma conversion processing on the printing image.
Further, the reconstructing the sequence of pixel values into a plurality of reconstruction vectors comprises:
reconstructing the pixel value sequence into high-dimensional spatial data according to a preset embedding dimension and a preset time delay; the high-dimensional spatial data includes a plurality of the reconstruction vectors.
Further, the obtaining a first printing index according to the sort of the sorting sequence and the entropy of the sorting sequence comprises:
and obtaining the first printing index according to a first printing index formula. The first print indicator formula comprises:
Figure 100002_DEST_PATH_IMAGE002
wherein the content of the first and second substances,
Figure 100002_DEST_PATH_IMAGE004
for the purpose of the first printing index,
Figure 100002_DEST_PATH_IMAGE006
for the kind of said ordered sequence it is possible to select,
Figure 100002_DEST_PATH_IMAGE008
is as follows
Figure 100002_DEST_PATH_IMAGE010
The number of occurrences of each of said ordered sequences,
Figure 100002_DEST_PATH_IMAGE012
for the number of said ordered sequences to be,
Figure 100002_DEST_PATH_IMAGE014
parameters are fitted to the first model.
Further, the acquiring a standard print image includes:
selecting a plurality of high quality print images in a historical database; and taking the high-quality printing image with the maximum first printing index as the standard printing image.
Further, said fitting said sequence of pixel values of said standard printed image to obtain a standard fit curve comprises:
acquiring channel images of a plurality of color channels of the standard printing image; and fitting the pixel value sequence of each channel image to obtain the standard fitting curve corresponding to the channel image.
Further, the obtaining a second printing index according to the discrete point number and the relative entropy of the fitted curve comprises:
acquiring the initial second printing index under each color channel; taking the mean value of the initial second printing indexes as the second printing indexes.
Further, the obtaining the initial second printing index for each of the color channels comprises:
obtaining the initial second print metric according to a second print metric formula, the second print metric formula comprising:
Figure 100002_DEST_PATH_IMAGE016
wherein the content of the first and second substances,
Figure 100002_DEST_PATH_IMAGE018
is a first
Figure 100002_DEST_PATH_IMAGE020
The initial second print index for each of the color channels,
Figure 100002_DEST_PATH_IMAGE022
is as follows
Figure 95758DEST_PATH_IMAGE020
The number of discrete points of said fitted curve for each of said color channels,
Figure 100002_DEST_PATH_IMAGE024
is a first
Figure 56761DEST_PATH_IMAGE020
A function value of the standard fit curve for each of the color channels,
Figure 100002_DEST_PATH_IMAGE026
is a first
Figure 32807DEST_PATH_IMAGE020
A function value of the fitted curve for each of the color channels.
Further, the obtaining of the overall printing index from the first printing index and the second printing index comprises:
obtaining the overall printing index according to an overall printing index formula, wherein the overall printing index formula comprises:
Figure 100002_DEST_PATH_IMAGE028
wherein the content of the first and second substances,
Figure 100002_DEST_PATH_IMAGE030
in order to be an indicator of the overall printing,
Figure 100002_DEST_PATH_IMAGE032
in order to be an indicator of the second printing,
Figure 100002_DEST_PATH_IMAGE034
the parameters are fitted to the second model and,
Figure 261926DEST_PATH_IMAGE004
for the purpose of the first printing index,
Figure 100002_DEST_PATH_IMAGE036
parameters are fitted to the third model.
The invention also provides a system for detecting the new printing material by using the optical means, which comprises a memory, a processor and a computer program which is stored in the memory and can run on the processor, wherein the processor executes the computer program to realize any one of the steps of the method for detecting the new printing material by using the optical means.
The invention has the following beneficial effects:
1. in the embodiment of the invention, the image acquisition equipment comprising the visible light source is used for acquiring the image information of the new material after printing, the image characteristics of the product to be detected are amplified, the subsequently detected printing index has stronger reference, the integral printing index difference of products with different printing qualities can be effectively amplified, and the effective evaluation of the printing quality is realized.
2. According to the embodiment of the invention, through analyzing the plurality of reconstruction vectors, the whole pixel value characteristics of the image are considered, and the detailed pixel value characteristics in the image are considered through the subdivided reconstruction vectors. A first printing index representing the degree of uniformity of a printing color is obtained by an entropy analysis method. And taking the standard printing image as a reference, and obtaining a second printing index representing the printing effect through the relative entropy with the standard printing image. Further, the printing quality is effectively evaluated and judged through the whole printing index, and the analysis and the measurement of new materials by utilizing image information under visible light by an optical means are realized.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions and advantages of the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
Fig. 1 is a flowchart of a method for detecting a new printing material by optical means according to an embodiment of the present invention.
Detailed Description
To further illustrate the technical means and effects of the present invention adopted to achieve the predetermined objects, the following detailed description will be given to a method and system for detecting a new printing material by optical means according to the present invention, with reference to the accompanying drawings and preferred embodiments, and its specific implementation, structure, features and effects. In the following description, different "one embodiment" or "another embodiment" refers to not necessarily the same embodiment. Furthermore, the particular features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.
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 invention belongs.
The following describes a specific scheme of a method and a system for detecting a new printing material by an optical means, which is provided by the present invention, in detail with reference to the accompanying drawings.
Referring to fig. 1, a flowchart of a method for detecting a new printing material by optical means according to an embodiment of the present invention is shown, where the method includes:
step S1: collecting a printing image of a new material printing product by using image collection equipment; the image acquisition device includes a camera and a visible light source.
In the production process of printing a new material product, a product to be detected can be placed on a detection table, and image information of the printed surface of the product to be detected is acquired through image acquisition equipment to obtain a printed image.
In the embodiment of the invention, the camera in the image acquisition equipment is deployed right above the detection table, the height is moderate, and the camera view can contain the whole product printing surface. In order to amplify the image characteristics of the printed surface of the product, the type of the visible light source of the image acquisition device can be adjusted according to the color of the printed surface, the visible light type includes various types such as white light, pure color light and the like, and the visible light type can be set by self aiming at the printed color of the product without limitation.
It should be noted that, because the production environment of the product is complex, in the image acquisition process, the irradiation of the product to be detected by the visible light source will have uneven influence, and therefore, after the printed image is obtained, the printed image needs to be subjected to gamma conversion, so that the overall detail expression of the image is increased, the image quality is improved, and the subsequent feature detection is facilitated.
Step S2: constructing a pixel value sequence according to the pixel value of each pixel point in the printed image; reconstructing the sequence of pixel values into a plurality of reconstruction vectors; labeling the elements according to the positions of the elements in each reconstruction vector; sorting the elements of the reconstruction vector according to the pixel value, and taking the sorted label sequence as a sorting sequence; and obtaining a first printing index according to the type of the sorting sequence and the entropy of the sorting sequence.
One printed image can be regarded as a matrix of a plurality of pixel values, and therefore the pixel value matrix is converted to obtain a corresponding pixel value sequence of the printed image. In the embodiment of the invention, the printed image is converted into the gray image, namely the gray value of each pixel point is the pixel value, and the pixel value sequence is formed by arranging the pixel values of the pixel points in the printed image from left to right and from top to bottom.
To further analyze the image details, the sequence of pixel values of the printed image is reconstructed into a plurality of reconstruction vectors. The method specifically comprises the following steps:
according to a preset embedding dimension m and a preset time delay
Figure DEST_PATH_IMAGE038
Reconstructing the sequence of pixel values into high-dimensional spatial data
Figure DEST_PATH_IMAGE040
：
Figure DEST_PATH_IMAGE042
Wherein the content of the first and second substances,
Figure 843080DEST_PATH_IMAGE040
is the data of a high-dimensional space,
Figure DEST_PATH_IMAGE044
is as follows
Figure 912667DEST_PATH_IMAGE010
The number of the reconstructed vectors is determined,
Figure 562960DEST_PATH_IMAGE012
for reconstructing the number of vectors, i.e. one high-dimensional spatial data comprising
Figure 376195DEST_PATH_IMAGE012
And reconstructing the vector.
Figure DEST_PATH_IMAGE046
Wherein, in the step (A),
Figure DEST_PATH_IMAGE048
is the number of elements within the sequence of pixel values.
It should be noted that the sequence of pixel values can be expressed as:
Figure DEST_PATH_IMAGE050
，
Figure DEST_PATH_IMAGE052
is as follows
Figure DEST_PATH_IMAGE054
A pixel value. The reconstruction vector may be represented as:
Figure DEST_PATH_IMAGE056
。
in an embodiment of the invention, the embedding dimension is set to 4 and the time delay is set to 2. The phase space reconstruction of sequences is a well-known technique for those skilled in the art, and the reconstruction principle is not described in detail here.
According to the reconstruction result, the length of one reconstruction vector is small, so that the local detail information in the image can be represented. If the product is printed in uniform color, the reconstructed vector has certain repeatability and similarity in the printed image. In order to analyze the repeatability of the reconstruction vectors conveniently, labeling the elements according to the positions of the elements in each reconstruction vector, sequencing the elements of the reconstruction vectors according to the pixel values, and taking the sequenced label sequence as a sequencing sequence; if color difference exists in the color, the pixel value in the reconstructed vector fluctuates, so that the sorting sequence changes, namely, the more kinds of the sorting sequence indicate that the color difference is not uniform in printing. Further combining the entropy of the sorting sequence to obtain a first printing index representing the uniformity degree of the printing color, specifically comprising:
and obtaining a first printing index according to the first printing index formula. The first print index formula includes:
Figure DEST_PATH_IMAGE002A
wherein the content of the first and second substances,
Figure 343014DEST_PATH_IMAGE004
as a first print index, the index of the first print,
Figure 114661DEST_PATH_IMAGE006
in order to sort the sequence of the sequence,
Figure 485206DEST_PATH_IMAGE008
is as follows
Figure 367712DEST_PATH_IMAGE010
The number of times that the sequence of sequences occurs,
Figure 454616DEST_PATH_IMAGE012
in order to order the number of sequences to be ordered,
Figure 193902DEST_PATH_IMAGE014
parameters are fitted to the first model. In an embodiment of the present invention, the first fitting parameter is set to 5.
In the first print index formula,
Figure DEST_PATH_IMAGE058
the entropy of the sequencing sequence is represented, and the larger the entropy value is, the more disordered the sequencing sequence is, the more uneven the printing color is, and the smaller the first printing index is. The larger the first print indicator, the more uniform the printing of the product.
Step S3: acquiring a standard printing image; fitting the pixel value sequence of the standard printing image to obtain a standard fitting curve; obtaining a fitting curve corresponding to the printing image; obtaining the relative entropy of the fitting curve and the standard fitting curve; and obtaining a second printing index according to the number of the discrete points and the relative entropy of the fitted curve.
For the printing effect of the printed product, the closer to the printing template indicates the better the printing effect. Therefore, the standard printing image is obtained and is the image of the product with high-quality printing effect, and the standard printing image is used as the reference, so that the quality of the printing effect of the product to be detected at present can be analyzed.
Preferably, a plurality of high quality print images are selected in the historical database for reference to obtain a better standard print image. And taking the high-quality printing image with the maximum first printing index as a standard printing image.
The pixel value sequence is transmitted into a two-dimensional space to obtain a plurality of scattered points, and curve fitting is carried out on the scattered points to obtain a standard fitting curve of a standard printing image and a fitting curve of a printing image of a product to be detected. The print effect can be analyzed by correlation between the standard fitted curve and the fitted curve. The correlation can be expressed by the relative entropy between the standard fitted curve and the fitted curve function value, i.e. the correlation is worse the larger the relative entropy.
For a high-quality printed image, the pixel value distribution of the high-quality printed image has certain regularity, namely scattered points in a two-dimensional space are distributed near a fitting curve as intensively as possible, if the fitting curve has the scattered points, the color distribution is disordered and the printing effect is poor, so that a second printing index can be obtained through the number of the scattered points and the relative entropy.
Preferably, since the printed effect of the product is rich in color, the image is analyzed individually according to the color channels when analyzing the printed effect. The method comprises the steps of obtaining channel images of a plurality of color channels of a standard printing image, fitting a pixel value sequence of each channel image, and obtaining a standard fitting curve corresponding to the channel images. Note that the print image is also subjected to the same processing, and a fitting curve under each color channel is obtained.
In the embodiment of the present invention, R, G, B three color channels are selected as the color channels, that is, each image includes channel values of three color channels, and three fitting curves.
And acquiring an initial second printing index under each color channel, and taking the mean value of the initial second printing indexes as a second printing index. The acquiring of the initial second printing index specifically includes:
obtaining an initial second print index according to a second print index formula, the second print index formula comprising:
Figure 100002_DEST_PATH_IMAGE016A
wherein the content of the first and second substances,
Figure 38361DEST_PATH_IMAGE018
is as follows
Figure 193399DEST_PATH_IMAGE020
An initial second print index for each color channel,
Figure 462707DEST_PATH_IMAGE022
is as follows
Figure 576156DEST_PATH_IMAGE020
The number of discrete points of the fitted curve under each color channel,
Figure 235807DEST_PATH_IMAGE024
is as follows
Figure 381487DEST_PATH_IMAGE020
The function values of the standard fit curves for each color channel,
Figure 177405DEST_PATH_IMAGE026
is as follows
Figure 461755DEST_PATH_IMAGE020
Function values of the fitted curve under each color channel.
In the second print index formula, the first print index formula,
Figure DEST_PATH_IMAGE060
is the relative entropy between the value of the standard fitted curve and the fitted curve function. The larger the relative entropy, the larger the number of discrete points, the smaller the second printing index, and the worse the printing effect.
In the embodiment of the invention, the scattered points with the distance between the scattered points in the two-dimensional space and the fitted curve being more than 5 are taken as the scattered points.
Step S4: obtaining an overall printing index according to the first printing index and the second printing index; and judging the printing quality of the new material according to the overall printing index.
The first print index indicates print color uniformity in the printed image and the second print index indicates how good the printed image is to print. Therefore, the overall printing index of the printed image can be obtained together according to the first printing index and the second printing index, and the overall printing index comprises the following specific steps:
obtaining an overall printing index according to an overall printing index formula, wherein the overall printing index formula comprises:
Figure DEST_PATH_IMAGE028A
wherein the content of the first and second substances,
Figure 77545DEST_PATH_IMAGE030
in order to be an index for the overall printing,
Figure 839964DEST_PATH_IMAGE032
in order to be a second print target,
Figure 21547DEST_PATH_IMAGE034
the parameters are fitted to the second model in order,
Figure 7957DEST_PATH_IMAGE004
as a first print index, the index of the first print,
Figure 642201DEST_PATH_IMAGE036
parameters are fitted to the third model. In an embodiment of the present invention, the second model fitting parameter is set to 0.5 and the third model fitting parameter is set to 10.
The printing quality of the current new material printing product can be judged according to the integral printing index. In the embodiment of the invention, a printing image of a printing product with the lowest printing quality standard is manually selected, the integral printing index of the printing image is obtained, the integral printing index is used as the threshold value for evaluating the printing quality, when the integral printing index of the product to be detected is smaller than the threshold value, the printing quality of the product is considered to be poor and cannot meet the factory requirements, and a worker can be informed to process or repair the low-quality product.
In summary, the embodiment of the present invention utilizes an image capturing device including a visible light source to obtain a printed image of a new material printed product. And reconstructing the pixel value sequence in the printed image into a plurality of reconstruction sequences to obtain a sequencing sequence of the reconstruction sequences, and obtaining a first printing index through the type and entropy of the sequencing sequence. And obtaining a fitting curve according to the pixel value sequence, taking the standard printing image as a reference, and obtaining a second printing index through the relative entropy of the standard fitting curve and the discrete points of the fitting curve. And judging the printing quality through the whole printing index obtained by the first printing index and the second printing index. The embodiment of the invention realizes the printing quality detection and metering of the new material printing product by amplifying the image characteristics by an optical means and extracting and quantizing the image characteristics.
The invention also provides a system for detecting the new printing material by using the optical means, which comprises a memory, a processor and a computer program which is stored in the memory and can run on the processor, wherein when the processor executes the computer program, any step of the method for detecting the new printing material by using the optical means is realized.
It should be noted that: the precedence order of the above embodiments of the present invention is only for description, and does not represent the merits of the embodiments. The processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.

Claims (7)

1. A method for optically inspecting new material for printing, the method comprising:
collecting a printing image of a new material printing product by using image collecting equipment; the image acquisition equipment comprises a camera and a visible light source;
constructing a pixel value sequence according to the pixel value of each pixel point in the printing image; reconstructing the sequence of pixel values into a plurality of reconstruction vectors; labeling the elements according to the positions of the elements in each reconstruction vector; sorting the elements of the reconstruction vector according to the pixel value, and taking the sorted label sequence as a sorting sequence; obtaining a first printing index according to the sort of the sorting sequence and the entropy of the sorting sequence; the method of obtaining the first printing index comprises:
obtaining a first printing index according to a first printing index formula; the first print metric formula includes:
Figure DEST_PATH_IMAGE002
wherein the content of the first and second substances,
Figure DEST_PATH_IMAGE004
for the purpose of the first printing index,
Figure DEST_PATH_IMAGE006
for the kind of the sorting sequence it is,
Figure DEST_PATH_IMAGE008
is as follows
Figure DEST_PATH_IMAGE010
The number of occurrences of each of said ordered sequences,
Figure DEST_PATH_IMAGE012
for the number of the ordered sequence in question,
Figure DEST_PATH_IMAGE014
fitting parameters to the first model;
acquiring a standard printing image; fitting the pixel value sequence of the standard printed image to obtain a standard fitting curve; the method for obtaining the standard fitting curve comprises the following steps: acquiring channel images of a plurality of color channels of the standard printing image; fitting the pixel value sequence of each channel image to obtain the standard fitting curve corresponding to the channel image;
obtaining a fitting curve corresponding to the printing image; obtaining the relative entropy of the fitting curve and the standard fitting curve; obtaining a second printing index according to the discrete point number of the fitting curve and the relative entropy; the method of obtaining the second printing index comprises: acquiring an initial second printing index under each color channel; taking the mean value of the initial second printing indexes as the second printing indexes; the method of obtaining the initial second printing index comprises: obtaining the initial second print metric according to a second print metric formula, the second print metric formula comprising:
Figure DEST_PATH_IMAGE016
wherein the content of the first and second substances,
Figure DEST_PATH_IMAGE018
is as follows
Figure DEST_PATH_IMAGE020
The initial second print index for each of the color channels,
Figure DEST_PATH_IMAGE022
is as follows
Figure 894711DEST_PATH_IMAGE020
The number of discrete points of said fitted curve for each of said color channels,
Figure DEST_PATH_IMAGE024
is as follows
Figure 546272DEST_PATH_IMAGE020
A function value of the standard fit curve for each of the color channels,
Figure DEST_PATH_IMAGE026
is as follows
Figure 122747DEST_PATH_IMAGE020
A function value of the fitted curve for each of the color channels;
obtaining an overall printing index according to the first printing index and the second printing index; and judging the printing quality of the new material according to the integral printing index.
2. The method for detecting the new printing material by the optical means as claimed in claim 1, wherein the step of acquiring the printing image of the new printing material by the image acquisition device further comprises: and carrying out gamma conversion processing on the printing image.
3. The method of claim 1, wherein reconstructing the sequence of pixel values into a plurality of reconstruction vectors comprises:
reconstructing the pixel value sequence into high-dimensional spatial data according to a preset embedding dimension and a preset time delay; the high-dimensional spatial data comprises a plurality of the reconstruction vectors.
4. The method for optically inspecting new printing material according to claim 1, wherein said obtaining a standard printing image comprises:
selecting a plurality of high quality print images in a historical database; and taking the high-quality printing image with the maximum first printing index as the standard printing image.
5. The method of claim 1, wherein said obtaining said initial second print index for each of said color channels comprises:
obtaining the initial second print metric according to a second print metric formula, the second print metric formula comprising:
Figure DEST_PATH_IMAGE016A
wherein the content of the first and second substances,
Figure 173748DEST_PATH_IMAGE018
is a first
Figure 722541DEST_PATH_IMAGE020
The initial second print index for each of the color channels,
Figure 545004DEST_PATH_IMAGE022
is a first
Figure 608775DEST_PATH_IMAGE020
The number of discrete points of said fitted curve for each of said color channels,
Figure 542096DEST_PATH_IMAGE024
is as follows
Figure 210974DEST_PATH_IMAGE020
A function value of the standard fit curve for each of the color channels,
Figure 876442DEST_PATH_IMAGE026
is as follows
Figure 365192DEST_PATH_IMAGE020
A function value of the fitted curve for each of the color channels.
6. The method of claim 1, wherein the obtaining the overall printing index according to the first printing index and the second printing index comprises:
obtaining the overall printing index according to an overall printing index formula, wherein the overall printing index formula comprises:
Figure DEST_PATH_IMAGE028
wherein the content of the first and second substances,
Figure DEST_PATH_IMAGE030
in order to be an indicator of the overall printing,
Figure DEST_PATH_IMAGE032
in order to be an indicator of the second printing,
Figure DEST_PATH_IMAGE034
the parameters are fitted to the second model and,
Figure 56199DEST_PATH_IMAGE004
for the purpose of the first printing index,
Figure DEST_PATH_IMAGE036
parameters are fitted to the third model.
7. A system for optically inspecting new material for printing, comprising a memory, a processor and a computer program stored in said memory and executable on said processor, wherein said processor when executing said computer program performs the steps of the method according to any one of claims 1 to 6.
CN202210320084.1A 2022-03-29 2022-03-29 Method and system for detecting new printing material by optical means Active CN114419043B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210320084.1A CN114419043B (en) 2022-03-29 2022-03-29 Method and system for detecting new printing material by optical means

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210320084.1A CN114419043B (en) 2022-03-29 2022-03-29 Method and system for detecting new printing material by optical means

Publications (2)

Publication Number Publication Date
CN114419043A CN114419043A (en) 2022-04-29
CN114419043B true CN114419043B (en) 2022-06-17

Family

ID=81263731

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210320084.1A Active CN114419043B (en) 2022-03-29 2022-03-29 Method and system for detecting new printing material by optical means

Country Status (1)

Country Link
CN (1) CN114419043B (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114771120B (en) * 2022-06-18 2022-09-02 南通人民彩印有限公司 Pressure control method and device in micro-contact printing process and artificial intelligence system

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR101281624B1 (en) * 2011-06-29 2013-07-03 목포대학교산학협력단 Imaging method of and imaging apparatus for imaging of near surface structures of a material
JP2020535324A (en) * 2017-08-31 2020-12-03 トワイン ソリューションズ リミテッド Color calibration algorithm
CN109583425B (en) * 2018-12-21 2023-05-02 西安电子科技大学 Remote sensing image ship integrated recognition method based on deep learning
CN113888536B (en) * 2021-12-01 2022-03-18 武汉市利友印务有限公司 Printed matter double image detection method and system based on computer vision

Also Published As

Publication number Publication date
CN114419043A (en) 2022-04-29

Similar Documents

Publication Publication Date Title
CN108765412B (en) Strip steel surface defect classification method
Kaur et al. Evaluation of plum fruit maturity by image processing techniques
Silvén et al. Wood inspection with non-supervised clustering
US6567538B1 (en) Real time measurement system for seed cotton or lint
CN104160409B (en) Method and system for graphical analysis
CN114419043B (en) Method and system for detecting new printing material by optical means
Behera Image-processing in textiles
CN114693676B (en) Optical detection method and device for bleaching defects of new material textiles
Liu et al. Quantitative potato tuber phenotyping by 3D imaging
CN110555395A (en) Classified evaluation method for nitrogen content grade of rape canopy
CN113298137A (en) Hyperspectral image classification method based on local similarity data gravitation
CN114372980A (en) Industrial defect detection method and system
CN116402742A (en) Visual detection method and system for surface defects of automobile sheet metal part
CN111768402A (en) MU-SVM-based method for evaluating freshness of iced pomfret
CN115424057A (en) Thing networking commodity circulation classification management recognition device based on discernment of shooing is used
CN115223164A (en) Melon maturity detection method and system based on artificial intelligence
AU2010333914A1 (en) Method and apparatus for predicting information about trees in images
CN116842210A (en) Textile printing texture intelligent retrieval method based on texture features
CN109299295B (en) Blue printing layout database searching method
CN116958960A (en) Egg dark spot detection method based on machine learning random forest algorithm
Orjuela et al. Feature extraction of the wear label of carpets by using a novel 3d scanner
CN115575790A (en) Method and equipment for detecting defects of micron light-emitting diode chip and storage medium
CN103927544A (en) Machine vision grading method for ginned cotton rolling quality
Niskanen et al. Experiments with SOM based inspection of wood
CN108764367B (en) Feature image extraction device and method based on relation regularization

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