CN117252886A - Invoice identification method and system based on image segmentation - Google Patents

Invoice identification method and system based on image segmentation Download PDF

Info

Publication number
CN117252886A
CN117252886A CN202311171722.9A CN202311171722A CN117252886A CN 117252886 A CN117252886 A CN 117252886A CN 202311171722 A CN202311171722 A CN 202311171722A CN 117252886 A CN117252886 A CN 117252886A
Authority
CN
China
Prior art keywords
preset
image
invoice
area
condition
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.)
Pending
Application number
CN202311171722.9A
Other languages
Chinese (zh)
Inventor
程爱珺
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.)
Guangdong Yuanheng Software Technology Co ltd
Original Assignee
Guangdong Yuanheng Software Technology 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 Guangdong Yuanheng Software Technology Co ltd filed Critical Guangdong Yuanheng Software Technology Co ltd
Priority to CN202311171722.9A priority Critical patent/CN117252886A/en
Publication of CN117252886A publication Critical patent/CN117252886A/en
Pending legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR 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; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T3/00—Geometric image transformation in the plane of the image
    • G06T3/60—Rotation of a whole image or part thereof
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/60—Analysis of geometric attributes
    • G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
    • 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

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Geometry (AREA)
  • Image Analysis (AREA)

Abstract

The invention relates to the technical field of invoice information identification, in particular to an invoice identification system based on image segmentation, which comprises the following steps: step S1, acquiring a black-and-white invoice image; step S2, detecting the gray value of the invoice image by the gray scanning component, and judging the validity of the obtained invoice image by the central control module; step S3, the central control module adjusts the inclination angle of the image acquisition assembly, or carries out secondary judgment on the definition of the invoice image according to the noise area occupation ratio of the invoice image; step S4, after the secondary judgment, the central control module adjusts the sensitivity of the image acquisition assembly, or adjusts the training frequency of the data training system according to the edge missing area of the invoice image; and S5, the central control module adjusts the single block segmentation area of the invoice image according to the extraction duration of the invoice image information, and the identification efficiency and the identification effectiveness of the invoice are improved.

Description

Invoice identification method and system based on image segmentation
Technical Field
The invention relates to the technical field of invoice information identification, in particular to an invoice identification method and system based on image segmentation.
Background
With the development of science and technology, in the current stage, commercial invoices are mainly drawn by a machine, and traditional invoice statistics work is to check and examine each invoice manually, so that the efficiency is low and the invoice statistics work is influenced by human factors. In the prior art, the computer is used for identifying the invoice number and the invoice code, and the character identification information of the target area is obtained through optical character identification, so that the invoice statistics and examination work tasks are greatly reduced.
Chinese patent publication No.: CN114694162a discloses an invoice image recognition method and system based on image processing, comprising: obtaining a difference image only containing the machine-made content; according to the gradient histogram of the edge pixel points in the difference image; selecting an edge pixel point in a preset gradient direction as a corner point, and screening to obtain a first corner point; obtaining a character area, wherein the character area is the minimum circumscribed rectangle of a complete machine-typing character string; screening the first corner points around each character in all character areas by utilizing the structural parameters among the first corner points to obtain structural corner points of all characters in the character areas; the method and the system for identifying the invoice image based on the image processing have the following problems that the characters are segmented and identified according to the coordinates of the structural corner points belonging to each character in the character area: the accuracy of invoice recognition is reduced due to the fact that the illumination intensity of the light source is too strong.
Disclosure of Invention
Therefore, the invention provides an invoice recognition method and system based on image segmentation, which are used for solving the problem that the accuracy of invoice recognition is reduced due to the fact that the illumination intensity of a light source is too strong in the prior art.
In order to achieve the above object, the present invention provides an invoice recognition method based on image segmentation, comprising: step S1, an invoice image is acquired by using an image acquisition component, and the invoice image is converted into a black-white invoice image by a central control module; step S2, the central control module controls a gray scanning assembly connected with the image acquisition assembly to detect gray values of the invoice image and calculate gray value difference quantity between the invoice image and the standard image so as to judge the effectiveness of the acquired invoice image; step S3, when the effectiveness of image acquisition is judged to be lower than the allowable range, the central control module adjusts the inclination angle of the image acquisition assembly to a corresponding angle, or carries out secondary judgment on the definition of the invoice image according to the noise area occupation ratio of the invoice image; step S4, after the definition of the invoice image is secondarily judged to be lower than the allowable range, the central control module adjusts the sensitivity of the image acquisition assembly to a corresponding value, or adjusts the training frequency of the data training system to a corresponding frequency according to the edge missing area of the invoice image; and S5, when the training frequency of the data training system is adjusted, the central control module adjusts the single block segmentation area of the invoice image to a corresponding area according to the extraction duration of the invoice image information.
Further, the central control module determines three judging methods of whether the effectiveness of image acquisition is within an allowable range according to the gray value difference between the invoice image and the standard image, wherein,
the first judging method is that the central control module judges that the effectiveness of image acquisition is in an allowable range under the condition of presetting a first difference;
the second judging method is that the central control module judges that the effectiveness of image acquisition is lower than the allowable range under the condition of a preset second difference amount, and adjusts the inclination angle of the image acquisition assembly to a corresponding angle by calculating the difference value between the gray value difference amount of the invoice image and the standard image and the preset first difference amount;
the third judging method is that the central control module judges that the effectiveness of image acquisition is lower than the allowable range under the condition of presetting a third difference, preliminarily judges that the definition of the invoice image is lower than the allowable range, and judges whether the definition of the invoice image is lower than the allowable range for the second time according to the noise area occupation ratio of the invoice image;
the first difference amount preset condition is that the gray value difference amount of the invoice image and the standard image is smaller than or equal to the first difference amount preset; the condition of the preset second difference is that the gray value difference of the invoice image and the standard image is larger than the preset first difference and smaller than or equal to the preset second difference; the third difference amount preset condition is that the gray value difference amount of the invoice image and the standard image is larger than the second difference amount preset, and the first difference amount preset is smaller than the second difference amount preset.
Further, the central control module determines two adjusting methods for the inclination angle of the image acquisition component according to the difference value of the gray value difference quantity of the invoice image and the standard image and the preset first difference quantity under the condition of the preset second difference quantity, wherein,
the first angle adjusting method is that the central control module adjusts the inclination angle of the image acquisition assembly to a first angle by using a preset first angle adjusting coefficient under the condition of a preset first difference value;
the second angle adjusting method is that the central control module adjusts the inclination angle of the image acquisition assembly to a second angle by using a preset second angle adjusting coefficient under the condition of a preset second difference value;
the difference value of the gray value difference value of the invoice image and the standard image is smaller than or equal to the difference value of the preset difference value; the difference value condition of the preset second difference value is that the difference value of the gray value difference value of the invoice image and the standard image is larger than the difference value of the preset first difference value; the preset first angle adjustment coefficient is smaller than the preset second angle adjustment coefficient.
Further, the central control module determines whether the definition of the invoice image is within the allowable range according to the noise area ratio of the invoice image under the condition of presetting a third difference, wherein,
The first secondary judging method is that the central control module judges that the definition of the invoice image is in an allowable range under the condition of presetting a first area occupation ratio;
the second secondary judgment method is that the central control module judges that the definition of the invoice image is lower than the allowable range under the condition of a preset second area occupation ratio, and the sensitivity of the image acquisition assembly is adjusted to a corresponding value by calculating the difference value between the noise area occupation ratio of the invoice image and the preset first area occupation ratio;
the third secondary judging method is that the central control module judges that the definition of the invoice image is lower than the allowable range under the condition of a preset third area, primarily judges that the integrity of the invoice information is lower than the allowable range, and carries out secondary judgment on the integrity of the invoice information according to the edge missing area of the invoice image;
the preset first area occupation ratio condition is that the noise point area occupation ratio of the invoice image is smaller than or equal to the preset first area occupation ratio; the preset second area occupation ratio is that the noise point area occupation ratio of the invoice image is larger than the preset first area occupation ratio and smaller than or equal to the preset second area occupation ratio; the third area occupation ratio is preset, the noise area occupation ratio of the invoice image is larger than the second area occupation ratio, and the first area occupation ratio is smaller than the second area occupation ratio.
Further, the central control module determines two adjusting methods for the sensitivity of the image acquisition component according to the difference value between the noise area ratio of the invoice image and the preset first area ratio under the condition of the preset second area ratio, wherein,
the first sensitivity adjustment method is that the central control module adjusts the sensitivity of the image acquisition component to a first value by using a preset first sensitivity adjustment coefficient under the condition of a preset first area occupation ratio difference value;
the second sensitivity adjustment method is that the central control module adjusts the sensitivity of the image acquisition component to a second numerical value by using a preset second sensitivity adjustment coefficient under the condition of a preset second area occupation ratio difference value;
the condition of the preset first area occupation ratio difference value is that the difference value between the noise point area occupation ratio of the invoice image and the preset first area occupation ratio is smaller than or equal to the preset area occupation ratio difference value; the condition of the preset second area occupation ratio difference is that the difference between the noise area occupation ratio of the invoice image and the preset first area occupation ratio is larger than the preset area occupation ratio difference, and the preset first sensitivity adjustment coefficient is smaller than the preset second sensitivity adjustment coefficient.
Further, the central control module determines whether the integrity of the invoice information is within the allowable range according to the edge missing area of the invoice image under the preset third area condition, wherein,
The first integrity secondary judging method is that the central control module judges that the integrity of invoice information is in an allowable range under the condition of a preset first area;
the second method for judging the integrity secondarily comprises the steps that the central control module judges that the integrity of invoice information is lower than an allowable range under the condition of a preset second area, and the training frequency of the data training system is adjusted to a corresponding frequency by calculating the difference value between the edge missing area of an invoice image and the preset area;
the first area condition is that the edge missing area of the invoice image is smaller than or equal to the preset area; and the preset second area condition is that the invoice image edge missing area is larger than the preset area.
Further, the central control module determines two adjusting methods for training frequency of the data training system according to the difference value between the edge missing area of the invoice image and the preset area under the preset second area condition, wherein,
the first frequency adjustment method is that the central control module adjusts the training frequency to a first frequency by using a preset first frequency adjustment coefficient under the condition of a preset first area difference value;
the second frequency adjusting method is that the central control module adjusts the training frequency to a second frequency by using a preset second frequency adjusting coefficient under the condition of a preset second area difference value;
The preset first area difference value condition is that the difference value between the edge missing area of the invoice image and the preset area is smaller than or equal to the preset area difference value; the preset second area difference value condition is that the difference value between the edge missing area of the invoice image and the preset area is larger than the preset area difference value, and the preset first frequency adjustment coefficient is smaller than the preset second frequency adjustment coefficient.
Further, the central control module determines two judging methods of whether the effectiveness of image segmentation is within an allowable range according to the extraction time of invoice image information, wherein,
the first validity judging method is that the central control module judges that the image segmentation validity is within an allowable range under the condition of presetting a first time strip;
the second validity judging method is that the central control module judges that the image segmentation validity is lower than the allowable range under the condition of the preset second duration, and the single segmentation area of the invoice image is adjusted to the corresponding area by calculating the difference value between the extraction duration of the invoice image information and the preset duration;
the first preset time-long condition is that the extraction duration of invoice image information is less than or equal to preset duration; and the condition of the preset second time length is that the extraction time length of the invoice image information is longer than the preset time length.
Further, the central control module determines two adjustment modes for the single block dividing area of the invoice image according to the difference value between the extraction time length of the invoice image information and the preset time length under the condition of the preset second time length, wherein,
the first dividing area adjusting mode is that the central control module adjusts the single dividing area of the invoice image to a first area by using a preset second area adjusting coefficient under the condition of a preset first time length difference value;
the second dividing area adjusting mode is that the central control module adjusts the single dividing area of the invoice image to a second area by using a preset first area adjusting coefficient under the condition of a preset second time length difference value;
the first preset time difference condition is that the difference value between the extraction time length of invoice image information and the preset time length is smaller than or equal to the preset time length difference value; the preset second time length difference condition is that the difference value between the extraction time length of invoice image information and the preset time length is larger than the preset time length difference value, and the preset first area adjustment coefficient is smaller than the preset second area adjustment coefficient.
The invention also provides an invoice recognition system based on the image segmentation invoice recognition method, which comprises the following steps:
The information acquisition module is used for acquiring the first-level invoice characteristic data and invoice information, wherein the invoice information comprises the invoice image acquired by the image acquisition component; the invoice primary characteristic data comprise an invoice image gray value, an invoice image noise area, an invoice image integral area and an invoice image edge missing area which are acquired by the gray scanning component;
the data processing module is connected with the data acquisition module and is used for calculating the primary invoice characteristic data to output secondary invoice characteristic parameters, wherein the secondary invoice characteristic parameters comprise gray value difference of an invoice image and a standard image, noise point area occupation ratio of the invoice image and extraction duration of invoice image information;
a central control module which is respectively connected with the data acquisition module and the data processing module and is used for adjusting the inclination angle of the image acquisition assembly to a corresponding angle when the effectiveness of image acquisition is judged to be lower than an allowable range according to the gray value difference of the invoice image and the standard image, or adjusting the sensitivity of the image acquisition assembly to a corresponding value according to the noise area ratio of the invoice image,
adjusting the training frequency of the data training system to a corresponding frequency according to the edge missing area of the invoice image;
And adjusting the single block segmentation area of the invoice image to a corresponding area according to the difference value between the extraction time length of the invoice image information and the preset time length.
Compared with the prior art, the method has the advantages that the invoice image is acquired by the central control module and is subjected to image segmentation and identification through the setting steps S1-S5, so that the invoice can be effectively identified, the effectiveness of image acquisition is judged after the gray value of the invoice image is acquired and the difference of a standard image is acquired by the central control module, the influence on the effectiveness of image acquisition due to the illumination angle problem is reduced by adjusting the inclination angle of the image acquisition assembly, the inclination angle of the image acquisition assembly is adjusted to help reduce the gray value of the invoice image, the definition of the invoice image is secondarily judged after the noise area of the invoice image is acquired, the sensitivity of the image acquisition assembly is adjusted according to the noise area of the invoice image, the definition of a picture is further improved by increasing the sensitivity of the image acquisition assembly of the identification system, or the completeness of the acquired image information is judged and the training frequency is adjusted according to the edge deletion area of the invoice image, the completeness of the invoice is further reduced by increasing the training frequency, and the completeness of the invoice information is further reduced, and the identification efficiency and the identification effectiveness of the invoice is improved are realized.
Further, according to the method, the central control module judges the effectiveness of image acquisition by setting the preset first difference condition, the preset second difference condition and the preset third difference condition, the gray value difference of the invoice image and the standard image shows the influence of illumination on invoice image acquisition, and the central control module adjusts the inclination angle of the image acquisition assembly by setting the preset first difference condition, the preset second difference condition, the preset first angle adjustment coefficient and the preset second angle adjustment coefficient, so that the influence of illumination intensity on invoice image acquisition is effectively avoided by adjusting the inclination angle, and the identification efficiency and the identification effectiveness of the invoice are further improved.
Further, the method comprises the steps that the preset first area condition, the preset second area condition and the preset third area condition are set, the central control module carries out secondary judgment on the definition of the invoice image according to the noise area ratio of the invoice image, the preset first area difference value condition, the preset second area difference value condition, the preset first sensitivity adjustment coefficient and the preset second sensitivity adjustment coefficient are set, the central control module adjusts the sensitivity of the image acquisition assembly, the smoothness of the image is increased by increasing the sensitivity of the image acquisition assembly, the definition of the invoice image is further improved, and the recognition efficiency and the recognition effectiveness of the invoice are further improved.
Further, the method comprises the steps that the central control module judges the integrity of invoice information by setting a preset first area condition and a preset second area condition, the recognition effectiveness of the invoice due to the fact that the image information is lost after the image is segmented is reduced due to image acquisition, and the central control module adjusts the training frequency of the data training system by setting the preset first area difference value condition, the preset second area difference value condition, the preset first frequency adjustment coefficient and the preset second frequency adjustment coefficient, so that the integrity of the image is improved by increasing the training frequency, and the recognition efficiency and the recognition effectiveness of the invoice are further improved.
Further, the method judges the image segmentation effectiveness by setting the preset first time length condition and the preset second time length condition, and adjusts the single block segmentation area of the invoice image by setting the preset first time length difference value condition, the preset second time length difference value condition, the preset first area adjustment coefficient and the preset second area adjustment coefficient, so that the speed of image information analysis is improved by reducing the single block segmentation area of the invoice image, and the recognition efficiency and the recognition effectiveness of the invoice are further improved.
Drawings
FIG. 1 is an overall flow chart of an invoice recognition method based on image segmentation in an embodiment of the invention;
FIG. 2 is a block diagram of the overall structure of an invoice recognition system based on image segmentation according to an embodiment of the present invention;
FIG. 3 is a block diagram of a specific structure of a data acquisition module of an invoice recognition system based on image segmentation according to an embodiment of the present invention;
fig. 4 is a block diagram of a connection structure of a data acquisition module and a central control module of an invoice recognition system based on image segmentation according to an embodiment of the invention.
Detailed Description
In order that the objects and advantages of the invention will become more apparent, the invention will be further described with reference to the following examples; it should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
Preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are merely for explaining the technical principles of the present invention, and are not intended to limit the scope of the present invention.
Referring to fig. 1, fig. 2, fig. 3, and fig. 4, which are an overall flowchart of an invoice recognition method based on image segmentation, an overall structure block diagram of an invoice recognition system based on image segmentation, a specific structure block diagram of a data acquisition module, and a connection structure block diagram of the data acquisition module connected with a central control module according to an embodiment of the present invention, respectively; the invention discloses an invoice identification method based on image segmentation, which comprises the following steps:
Step S1, an invoice image is acquired by using an image acquisition component, and the invoice image is converted into a black-white invoice image by a central control module;
step S2, the central control module controls a gray scanning assembly connected with the image acquisition assembly to detect gray values of the invoice image and calculate gray value difference quantity between the invoice image and the standard image so as to judge the effectiveness of the acquired invoice image;
step S3, when the effectiveness of image acquisition is judged to be lower than the allowable range, the central control module adjusts the inclination angle of the image acquisition assembly to a corresponding angle, or carries out secondary judgment on the definition of the invoice image according to the noise area occupation ratio of the invoice image;
step S4, after the definition of the invoice image is secondarily judged to be lower than the allowable range, the central control module adjusts the sensitivity of the image acquisition assembly to a corresponding value, or adjusts the training frequency of the data training system to a corresponding frequency according to the edge missing area of the invoice image;
and S5, when the training frequency of the data training system is adjusted, the central control module adjusts the single block segmentation area of the invoice image to a corresponding area according to the extraction duration of the invoice image information.
Specifically, the gray value difference between the invoice image and the standard image is the difference of the gray value of the invoice image minus the gray value of the standard invoice image.
Specifically, the image acquisition assembly comprises a base, a supporting rod connected with the base and used for supporting the image acquisition assembly, a rotating shaft arranged on the supporting rod and used for adjusting the inclination angle of the image acquisition assembly, and a camera connected with the rotating shaft and used for acquiring invoice images.
Specifically, the invoice image information includes a business name, a tax payment identification number, and a business address.
According to the method, the invoice image is acquired by the central control module and is subjected to image segmentation and identification through the steps S1-S5, so that effective identification of the invoice is achieved, the central control module judges the effectiveness of image acquisition after acquiring the difference of the gray value of the invoice image and the standard image, the influence on the effectiveness of image acquisition due to the problem of illumination angle is reduced by adjusting the inclination angle of the image acquisition assembly, the gray value of the invoice image is reduced by adjusting the inclination angle of the image acquisition assembly, secondary judgment is carried out on the definition of the invoice image after the noise area of the invoice image is acquired, the sensitivity of the image acquisition assembly is adjusted according to the noise area of the invoice image, the definition degree of a picture is further improved through increasing the sensitivity of the image acquisition assembly of the identification system, or the integrity of the acquired image information is judged and the training frequency is adjusted according to the edge area of the invoice image, the edge area of the invoice is further reduced, the integrity degree of the invoice information is improved, and the invoice identification efficiency and the invoice identification effectiveness is improved.
With continued reference to fig. 1, the central control module determines whether the effectiveness of image acquisition is within an allowable range according to the gray value difference between the invoice image and the standard image, wherein,
the first judging method is that the central control module judges that the effectiveness of image acquisition is in an allowable range under the condition of presetting a first difference;
the second judging method is that the central control module judges that the effectiveness of image acquisition is lower than the allowable range under the condition of a preset second difference amount, and adjusts the inclination angle of the image acquisition assembly to a corresponding angle by calculating the difference value between the gray value difference amount of the invoice image and the standard image and the preset first difference amount;
the third judging method is that the central control module judges that the effectiveness of image acquisition is lower than the allowable range under the condition of presetting a third difference, preliminarily judges that the definition of the invoice image is lower than the allowable range, and judges whether the definition of the invoice image is lower than the allowable range for the second time according to the noise area occupation ratio of the invoice image;
the first difference amount preset condition is that the gray value difference amount of the invoice image and the standard image is smaller than or equal to the first difference amount preset; the condition of the preset second difference is that the gray value difference of the invoice image and the standard image is larger than the preset first difference and smaller than or equal to the preset second difference; the third difference amount preset condition is that the gray value difference amount of the invoice image and the standard image is larger than the second difference amount preset, and the first difference amount preset is smaller than the second difference amount preset.
Specifically, the gray value difference between the invoice image and the standard image is denoted as P, the preset first difference is denoted as P1, the preset second difference is denoted as P2, the difference between the gray value difference between the invoice image and the standard image and the preset first difference is denoted as Δp, and Δp=p-P1 is set.
With continued reference to fig. 1, the central control module determines two adjustment methods for the inclination angle of the image acquisition component according to the difference between the gray value difference of the invoice image and the standard image and the preset first difference under the preset second difference condition, wherein,
the first angle adjusting method is that the central control module adjusts the inclination angle of the image acquisition assembly to a first angle by using a preset first angle adjusting coefficient under the condition of a preset first difference value;
the second angle adjusting method is that the central control module adjusts the inclination angle of the image acquisition assembly to a second angle by using a preset second angle adjusting coefficient under the condition of a preset second difference value;
the difference value of the gray value difference value of the invoice image and the standard image is smaller than or equal to the difference value of the preset difference value; the difference value condition of the preset second difference value is that the difference value of the gray value difference value of the invoice image and the standard image is larger than the difference value of the preset first difference value; the preset first angle adjustment coefficient is smaller than the preset second angle adjustment coefficient.
Specifically, the preset difference value is denoted as Δp0, the preset first angle adjustment coefficient is denoted as α1, the preset second angle adjustment coefficient is denoted as α2, wherein 1 < α1 < α2, the inclination angle of the image acquisition component is denoted as a, the inclination angle of the adjusted image acquisition component is denoted as a ', a' =a×αi is set, wherein αi is the preset i-th angle adjustment coefficient, i=1, 2.
According to the method, the central control module judges the effectiveness of image acquisition by setting the preset first difference condition, the preset second difference condition and the preset third difference condition, the gray value difference of the invoice issuing image and the standard image shows the influence of illumination on invoice image acquisition, and the central control module adjusts the inclination angle of the image acquisition assembly by setting the preset first difference condition, the preset second difference condition, the preset first angle adjustment coefficient and the preset second angle adjustment coefficient, so that the influence of illumination intensity on invoice image acquisition is effectively avoided by adjusting the inclination angle, and the identification efficiency and the identification effectiveness of the invoice are further improved.
With continued reference to fig. 1, the central control module determines whether the sharpness of the invoice image is within the allowable range according to the noise area ratio of the invoice image under the condition of presetting a third difference, wherein,
The first secondary judging method is that the central control module judges that the definition of the invoice image is in an allowable range under the condition of presetting a first area occupation ratio;
the second secondary judgment method is that the central control module judges that the definition of the invoice image is lower than the allowable range under the condition of a preset second area occupation ratio, and the sensitivity of the image acquisition assembly is adjusted to a corresponding value by calculating the difference value between the noise area occupation ratio of the invoice image and the preset first area occupation ratio;
the third secondary judging method is that the central control module judges that the definition of the invoice image is lower than the allowable range under the condition of a preset third area, primarily judges that the integrity of the invoice information is lower than the allowable range, and carries out secondary judgment on the integrity of the invoice information according to the edge missing area of the invoice image;
the preset first area occupation ratio condition is that the noise point area occupation ratio of the invoice image is smaller than or equal to the preset first area occupation ratio; the preset second area occupation ratio is that the noise point area occupation ratio of the invoice image is larger than the preset first area occupation ratio and smaller than or equal to the preset second area occupation ratio; the third area occupation ratio is preset, the noise area occupation ratio of the invoice image is larger than the second area occupation ratio, and the first area occupation ratio is smaller than the second area occupation ratio.
Specifically, the noise area ratio of the invoice image is denoted as C, the preset first area is denoted as C1, the preset second area is denoted as C2, the difference between the noise area ratio of the invoice image and the preset first area is denoted as Δc, and Δc=c—c1 is set.
With continued reference to fig. 1, the central control module determines two adjustment methods for the sensitivity of the image acquisition component according to the difference between the noise area ratio of the invoice image and the preset first area ratio under the preset second area ratio condition, wherein,
the first sensitivity adjustment method is that the central control module adjusts the sensitivity of the image acquisition component to a first value by using a preset first sensitivity adjustment coefficient under the condition of a preset first area occupation ratio difference value;
the second sensitivity adjustment method is that the central control module adjusts the sensitivity of the image acquisition component to a second numerical value by using a preset second sensitivity adjustment coefficient under the condition of a preset second area occupation ratio difference value;
the condition of the preset first area occupation ratio difference value is that the difference value between the noise point area occupation ratio of the invoice image and the preset first area occupation ratio is smaller than or equal to the preset area occupation ratio difference value; the condition of the preset second area occupation ratio difference is that the difference between the noise area occupation ratio of the invoice image and the preset first area occupation ratio is larger than the preset area occupation ratio difference, and the preset first sensitivity adjustment coefficient is smaller than the preset second sensitivity adjustment coefficient.
Specifically, the preset area difference is denoted as Δc0, the preset first sensitivity adjustment coefficient is denoted as β1, the preset second sensitivity adjustment coefficient is denoted as β2, wherein 0 < β1 < β2 < 1, the sensitivity of the image acquisition assembly is denoted as R, the sensitivity of the adjusted image acquisition assembly is denoted as R ', R' =r× (1- βj), wherein βj is the preset j-th sensitivity adjustment coefficient, j=1, 2.
According to the method, the preset first area condition, the preset second area condition and the preset third area condition are set, the central control module carries out secondary judgment on the definition of the invoice image according to the noise area ratio of the invoice image, the preset first area difference value condition, the preset second area difference value condition, the preset first sensitivity adjustment coefficient and the preset second sensitivity adjustment coefficient are set, the central control module adjusts the sensitivity of the image acquisition assembly, the smoothness of the image is increased by increasing the sensitivity of the image acquisition assembly, the definition of the invoice image is further improved, and the recognition efficiency and the recognition effectiveness of the invoice are further improved.
With continued reference to fig. 1, the central control module determines whether the integrity of the invoice information is within the allowable range according to the missing area of the edge of the invoice image under the preset third area condition, wherein,
The first integrity secondary judging method is that the central control module judges that the integrity of invoice information is in an allowable range under the condition of a preset first area;
the second method for judging the integrity secondarily comprises the steps that the central control module judges that the integrity of invoice information is lower than an allowable range under the condition of a preset second area, and the training frequency of the data training system is adjusted to a corresponding frequency by calculating the difference value between the edge missing area of an invoice image and the preset area;
the first area condition is that the edge missing area of the invoice image is smaller than or equal to the preset area; and the preset second area condition is that the invoice image edge missing area is larger than the preset area.
Specifically, the invoice image edge missing area is denoted as M, the preset area is denoted as M0, the difference between the invoice image edge missing area and the preset area is denoted as Δm, and Δm=m-M0 is set.
With continued reference to fig. 1, the central control module determines two adjustment methods for training frequency of the data training system according to a difference between the invoice image edge missing area and the preset area under the preset second area condition, wherein,
the first frequency adjustment method is that the central control module adjusts the training frequency to a first frequency by using a preset first frequency adjustment coefficient under the condition of a preset first area difference value;
The second frequency adjusting method is that the central control module adjusts the training frequency to a second frequency by using a preset second frequency adjusting coefficient under the condition of a preset second area difference value;
the preset first area difference value condition is that the difference value between the edge missing area of the invoice image and the preset area is smaller than or equal to the preset area difference value; the preset second area difference value condition is that the difference value between the edge missing area of the invoice image and the preset area is larger than the preset area difference value, and the preset first frequency adjustment coefficient is smaller than the preset second frequency adjustment coefficient.
Specifically, the preset area difference is denoted as Δm0, the preset first frequency adjustment coefficient is denoted as δ1, the preset second frequency adjustment coefficient δ2, where 0 < δ1 < δ2 < 1, the training frequency is denoted as H, the adjusted training frequency is denoted as H ', H' =h× (1+δg) is set, δg is the preset g-th frequency adjustment coefficient, and g=1, 2.
According to the method, the integrity of invoice information is judged by the central control module through setting the preset first area condition and the preset second area condition, the identification effectiveness of the invoice with the missing image information is reduced due to the image acquisition reason after the image is segmented, and the training frequency of the data training system is adjusted by the central control module through setting the preset first area difference value condition, the preset second area difference value condition, the preset first frequency adjustment coefficient and the preset second frequency adjustment coefficient, so that the integrity of the image is improved through increasing the training frequency, and the identification efficiency and the identification effectiveness of the invoice are further improved.
With continued reference to fig. 1, the central control module determines two determination methods for determining whether the image segmentation effectiveness is within an allowable range according to the extraction duration of the invoice image information of the invoice effective information, wherein,
the first validity judging method is that the central control module judges that the image segmentation validity is within an allowable range under the condition of presetting a first time strip;
the second validity judging method is that the central control module judges that the image segmentation validity is lower than the allowable range under the condition of the preset second duration, and the single segmentation area of the invoice image is adjusted to the corresponding area by calculating the difference value between the extraction duration of the invoice image information and the preset duration;
the first preset time-long condition is that the extraction duration of invoice image information is less than or equal to preset duration; and the condition of the preset second time length is that the extraction time length of the invoice image information is longer than the preset time length.
Specifically, the extraction time length of the invoice image information of the effective information is denoted as T, the preset time length is denoted as T0, the difference between the extraction time length of the invoice image information and the preset time length is denoted as Δt, and Δt=t-T0 is set.
With continued reference to fig. 1, the central control module determines two adjustment modes for the single block dividing area of the invoice image according to the difference between the extraction time length of the invoice image information and the preset time length under the condition of the preset second time length, wherein,
The first dividing area adjusting mode is that the central control module adjusts the single dividing area of the invoice image to a first area by using a preset second area adjusting coefficient under the condition of a preset first time length difference value;
the second dividing area adjusting mode is that the central control module adjusts the single dividing area of the invoice image to a second area by using a preset first area adjusting coefficient under the condition of a preset second time length difference value;
the first preset time difference condition is that the difference value between the extraction time length of invoice image information and the preset time length is smaller than or equal to the preset time length difference value; the preset second time length difference condition is that the difference value between the extraction time length of invoice image information and the preset time length is larger than the preset time length difference value, and the preset first area adjustment coefficient is smaller than the preset second area adjustment coefficient.
Specifically, the preset time length difference is denoted as deltat 0, the preset first area adjustment coefficient is denoted as ζ1, the preset second area adjustment coefficient is denoted as ζ2,0 < ζ1 < ζ2 < 1, the single block dividing area of the invoice image is denoted as S, the single block dividing area of the invoice image after adjustment is denoted as S ', and S' =s×ζk is set, wherein ζk is the preset kth area adjustment coefficient, and k=1, 2.
The method judges the image segmentation effectiveness by setting the preset first time length condition and the preset second time length condition, and adjusts the single block segmentation area of the invoice image by setting the preset first time length difference value condition, the preset second time length difference value condition, the preset first area adjustment coefficient and the preset second area adjustment coefficient, so that the speed of image information analysis is improved by reducing the single block segmentation area of the invoice image, and the recognition efficiency and the recognition effectiveness of the invoice are further improved.
With continued reference to fig. 2, an invoice recognition system based on image segmentation includes:
the information acquisition module is used for acquiring the first-level invoice characteristic data and invoice information, wherein the invoice information comprises the invoice image acquired by the image acquisition component; the invoice primary characteristic data comprise an invoice image gray value, an invoice image noise area, an invoice image integral area and an invoice image edge missing area which are acquired by the gray scanning component;
the data processing module is connected with the data acquisition module and is used for calculating the primary invoice characteristic data to output secondary invoice characteristic parameters, wherein the secondary invoice characteristic parameters comprise gray value difference of an invoice image and a standard image, noise point area occupation ratio of the invoice image and extraction duration of invoice image information;
A central control module which is respectively connected with the data acquisition module and the data processing module and is used for adjusting the inclination angle of the image acquisition assembly to a corresponding angle when the effectiveness of image acquisition is judged to be lower than an allowable range according to the gray value difference of the invoice image and the standard image, or adjusting the sensitivity of the image acquisition assembly to a corresponding value according to the noise area ratio of the invoice image,
adjusting the training frequency of the data training system to a corresponding frequency according to the edge missing area of the invoice image;
and adjusting the single block segmentation area of the invoice image to a corresponding area according to the difference value between the extraction time length of the invoice image information and the preset time length.
Example 1
In this embodiment 1, the difference of the preset area is denoted as Δm0, the preset first frequency adjustment coefficient is denoted as δ1, the preset second frequency adjustment coefficient δ2, and the training frequency is denoted as H, where Δm0=3 cm 2 ，δ1＝0.2，δ2＝0.3，H＝75HZ，
In this example, ΔM=0.7 cm was obtained 2 The central control module judges that DeltaM is less than or equal to DeltaM 0 and adjusts training frequency by delta 1, and the adjusted training frequency is recorded as H' =75HZ× (1+0.2) =90HZ.
In this embodiment 1, after the Δm is obtained, the central control module determines that δ1 is required to be used to adjust the training frequency, and increases the training frequency to reduce the missing degree of the edge of the invoice image, thereby improving the recognition efficiency and the recognition effectiveness of the invoice.
Thus far, the technical solution of the present invention has been described in connection with the preferred embodiments shown in the drawings, but it is easily understood by those skilled in the art that the scope of protection of the present invention is not limited to these specific embodiments. Equivalent modifications and substitutions for related technical features may be made by those skilled in the art without departing from the principles of the present invention, and such modifications and substitutions will be within the scope of the present invention.
The foregoing description is only of the preferred embodiments of the invention and is not intended to limit the invention; various modifications and variations of the present invention will be apparent to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims (10)

1. An invoice recognition method based on image segmentation is characterized by comprising the following steps:
step S1, an invoice image is acquired by using an image acquisition component, and the invoice image is converted into a black-white invoice image by a central control module;
step S2, the central control module controls a gray scanning assembly connected with the image acquisition assembly to detect gray values of the invoice image and calculate gray value difference quantity between the invoice image and the standard image so as to judge the effectiveness of the acquired invoice image;
Step S3, when the effectiveness of image acquisition is judged to be lower than the allowable range, the central control module adjusts the inclination angle of the image acquisition assembly to a corresponding angle, or carries out secondary judgment on the definition of the invoice image according to the noise area occupation ratio of the invoice image;
step S4, after the definition of the invoice image is secondarily judged to be lower than the allowable range, the central control module adjusts the sensitivity of the image acquisition assembly to a corresponding value, or adjusts the training frequency of the data training system to a corresponding frequency according to the edge missing area of the invoice image;
and S5, when the training frequency of the data training system is adjusted, the central control module adjusts the single block segmentation area of the invoice image to a corresponding area according to the extraction duration of the invoice image information.
2. The invoice recognition method based on image segmentation according to claim 1, wherein the central control module determines whether the effectiveness of image acquisition is within an allowable range according to gray value difference between an invoice image and a standard image, wherein,
the first judging method is that the central control module judges that the effectiveness of image acquisition is in an allowable range under the condition of presetting a first difference;
The second judging method is that the central control module judges that the effectiveness of image acquisition is lower than the allowable range under the condition of a preset second difference amount, and adjusts the inclination angle of the image acquisition assembly to a corresponding angle by calculating the difference value of the gray value difference amount of the invoice image and the standard image and the preset first difference amount;
the third judging method is that the central control module judges that the effectiveness of image acquisition is lower than the allowable range under the condition of presetting a third difference, preliminarily judges that the definition of the invoice image is lower than the allowable range, and judges whether the definition of the invoice image is lower than the allowable range for the second time according to the noise area occupation ratio of the invoice image;
the first difference amount preset condition is that the gray value difference amount of the invoice image and the standard image is smaller than or equal to the first difference amount preset; the condition of the preset second difference is that the gray value difference of the invoice image and the standard image is larger than the preset first difference and smaller than or equal to the preset second difference; the third difference amount preset condition is that the gray value difference amount of the invoice image and the standard image is larger than the second difference amount preset, and the first difference amount preset is smaller than the second difference amount preset.
3. The invoice recognition method based on image segmentation according to claim 2, wherein the central control module determines two adjustment methods for the inclination angle of the image acquisition component according to the difference value of the gray value difference value of the invoice image and the standard image and the preset first difference value under the preset second difference value condition, wherein,
the first angle adjusting method is that the central control module adjusts the inclination angle of the image acquisition assembly to a first angle by using a preset first angle adjusting coefficient under the condition of a preset first difference value;
the second angle adjusting method is that the central control module adjusts the inclination angle of the image acquisition assembly to a second angle by using a preset second angle adjusting coefficient under the condition of a preset second difference value;
the difference value of the gray value difference value of the invoice image and the standard image is smaller than or equal to the difference value of the preset difference value; the difference value condition of the preset second difference value is that the difference value of the gray value difference value of the invoice image and the standard image is larger than the difference value of the preset first difference value; the preset first angle adjustment coefficient is smaller than the preset second angle adjustment coefficient.
4. The method for identifying invoice based on image segmentation according to claim 2, wherein the central control module determines whether the definition of the invoice image is within an allowable range according to the noise area ratio of the invoice image under the condition of a preset third difference, wherein,
the first secondary judging method is that the central control module judges that the definition of the invoice image is in an allowable range under the condition of presetting a first area occupation ratio;
the second secondary judgment method is that the central control module judges that the definition of the invoice image is lower than the allowable range under the condition of a preset second area occupation ratio, and the sensitivity of the image acquisition assembly is adjusted to a corresponding value by calculating the difference value between the noise area occupation ratio of the invoice image and the preset first area occupation ratio;
the third secondary judging method is that the central control module judges that the definition of the invoice image is lower than the allowable range under the condition of a preset third area, primarily judges that the integrity of the invoice information is lower than the allowable range, and carries out secondary judgment on the integrity of the invoice information according to the edge missing area of the invoice image;
the preset first area occupation ratio condition is that the noise point area occupation ratio of the invoice image is smaller than or equal to the preset first area occupation ratio; the preset second area occupation ratio is that the noise point area occupation ratio of the invoice image is larger than the preset first area occupation ratio and smaller than or equal to the preset second area occupation ratio; the third area occupation ratio is preset, the noise area occupation ratio of the invoice image is larger than the second area occupation ratio, and the first area occupation ratio is smaller than the second area occupation ratio.
5. The invoice recognition method based on image segmentation according to claim 4, wherein the central control module determines two adjustment methods for the sensitivity of the image acquisition component according to the difference between the noise area ratio of the invoice image and the preset first area ratio under the preset second area ratio condition, wherein,
the first sensitivity adjustment method is that the central control module adjusts the sensitivity of the image acquisition component to a first value by using a preset first sensitivity adjustment coefficient under the condition of a preset first area occupation ratio difference value;
the second sensitivity adjustment method is that the central control module adjusts the sensitivity of the image acquisition component to a second numerical value by using a preset second sensitivity adjustment coefficient under the condition of a preset second area occupation ratio difference value;
the condition of the preset first area occupation ratio difference value is that the difference value between the noise point area occupation ratio of the invoice image and the preset first area occupation ratio is smaller than or equal to the preset area occupation ratio difference value; the condition of the preset second area occupation ratio difference is that the difference between the noise area occupation ratio of the invoice image and the preset first area occupation ratio is larger than the preset area occupation ratio difference, and the preset first sensitivity adjustment coefficient is smaller than the preset second sensitivity adjustment coefficient.
6. The method for identifying invoice based on image segmentation according to claim 4, wherein the central control module determines whether the integrity of the invoice information is within an allowable range according to the missing area of the edge of the invoice image under the condition of a preset third area ratio, wherein,
the first integrity secondary judging method is that the central control module judges that the integrity of invoice information is in an allowable range under the condition of a preset first area;
the second method for judging the integrity secondarily comprises the steps that the central control module judges that the integrity of invoice information is lower than an allowable range under the condition of a preset second area, and the training frequency of the data training system is adjusted to a corresponding frequency by calculating the difference value between the edge missing area of an invoice image and the preset area;
the first area condition is that the edge missing area of the invoice image is smaller than or equal to the preset area; and the preset second area condition is that the invoice image edge missing area is larger than the preset area.
7. The method for identifying invoice based on image segmentation according to claim 6, wherein the central control module determines two adjustment methods for training frequency of the data training system according to a difference between an edge missing area of the invoice image and a preset area under a preset second area condition, wherein,
The first frequency adjustment method is that the central control module adjusts the training frequency to a first frequency by using a preset first frequency adjustment coefficient under the condition of a preset first area difference value;
the second frequency adjusting method is that the central control module adjusts the training frequency to a second frequency by using a preset second frequency adjusting coefficient under the condition of a preset second area difference value;
the preset first area difference value condition is that the difference value between the edge missing area of the invoice image and the preset area is smaller than or equal to the preset area difference value; the preset second area difference value condition is that the difference value between the edge missing area of the invoice image and the preset area is larger than the preset area difference value, and the preset first frequency adjustment coefficient is smaller than the preset second frequency adjustment coefficient.
8. The invoice recognition method based on image segmentation according to claim 7, wherein the central control module determines two determination methods of whether the effectiveness of image segmentation is within an allowable range according to the extraction duration of invoice image information, wherein,
the first validity judging method is that the central control module judges that the image segmentation validity is within an allowable range under the condition of presetting a first time strip;
The second validity judging method is that the central control module judges that the image segmentation validity is lower than the allowable range under the condition of the preset second duration, and the single segmentation area of the invoice image is adjusted to the corresponding area by calculating the difference value between the extraction duration of the invoice image information and the preset duration;
the first preset time-long condition is that the extraction duration of invoice image information is less than or equal to preset duration; and the condition of the preset second time length is that the extraction time length of the invoice image information is longer than the preset time length.
9. The method for identifying an invoice based on image segmentation according to claim 8, wherein the central control module determines two adjustment modes for a single segmentation area of the invoice image according to a difference value between the extraction time length of the invoice image information and the preset time length under a preset second time length condition, wherein,
the first dividing area adjusting mode is that the central control module adjusts the single dividing area of the invoice image to a first area by using a preset second area adjusting coefficient under the condition of a preset first time length difference value;
the second dividing area adjusting mode is that the central control module adjusts the single dividing area of the invoice image to a second area by using a preset first area adjusting coefficient under the condition of a preset second time length difference value;
The first preset time difference condition is that the difference value between the extraction time length of invoice image information and the preset time length is smaller than or equal to the preset time length difference value; the preset second time length difference condition is that the difference value between the extraction time length of invoice image information and the preset time length is larger than the preset time length difference value, and the preset first area adjustment coefficient is smaller than the preset second area adjustment coefficient.
10. An invoice recognition system using the image segmentation-based invoice recognition method of any one of claims 1-9, comprising:
the information acquisition module is used for acquiring the first-level invoice characteristic data and invoice information, wherein the invoice information comprises the invoice image acquired by the image acquisition component; the invoice primary characteristic data comprise an invoice image gray value, an invoice image noise area, an invoice image integral area and an invoice image edge missing area which are acquired by the gray scanning component;
the data processing module is connected with the data acquisition module and is used for calculating the primary invoice characteristic data to output secondary invoice characteristic parameters, wherein the secondary invoice characteristic parameters comprise gray value difference of an invoice image and a standard image, noise point area occupation ratio of the invoice image and extraction duration of invoice image information;
A central control module which is respectively connected with the data acquisition module and the data processing module and is used for adjusting the inclination angle of the image acquisition assembly to a corresponding angle when the effectiveness of image acquisition is judged to be lower than an allowable range according to the gray value difference of the invoice image and the standard image, or adjusting the sensitivity of the image acquisition assembly to a corresponding value according to the noise area ratio of the invoice image,
adjusting the training frequency of the data training system to a corresponding frequency according to the edge missing area of the invoice image;
and adjusting the single block segmentation area of the invoice image to a corresponding area according to the difference value between the extraction time length of the invoice image information and the preset time length.
CN202311171722.9A 2023-09-11 2023-09-11 Invoice identification method and system based on image segmentation Pending CN117252886A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202311171722.9A CN117252886A (en) 2023-09-11 2023-09-11 Invoice identification method and system based on image segmentation

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202311171722.9A CN117252886A (en) 2023-09-11 2023-09-11 Invoice identification method and system based on image segmentation

Publications (1)

Publication Number Publication Date
CN117252886A true CN117252886A (en) 2023-12-19

Family

ID=89128685

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202311171722.9A Pending CN117252886A (en) 2023-09-11 2023-09-11 Invoice identification method and system based on image segmentation

Country Status (1)

Country Link
CN (1) CN117252886A (en)

Similar Documents

Publication Publication Date Title
Parker et al. An approach to license plate recognition
JP4516778B2 (en) Data processing system
US7177483B2 (en) System and method for enhancement of document images
US7054485B2 (en) Image processing method, apparatus and system
US6483932B1 (en) Method and apparatus for rolled fingerprint capture
US7729536B2 (en) Boundary extracting method, program, and device using the same
US8749839B2 (en) Systems and methods of processing scanned data
US7545529B2 (en) Systems and methods of accessing random access cache for rescanning
US20060110029A1 (en) Pattern recognizing method and apparatus
US20030044178A1 (en) Method for the automatic detection of red-eye defects in photographic image data
CN110929720B (en) Component detection method based on LOGO matching and OCR
JPH0762606B2 (en) Pattern position recognition device
JP4749879B2 (en) Face discrimination method, apparatus, and program
CN117252886A (en) Invoice identification method and system based on image segmentation
CN110188693B (en) Improved complex environment vehicle feature extraction and parking discrimination method
JP4795737B2 (en) Face detection method, apparatus, and program
JP2000023141A (en) Moving object monitoring device
JPH09511598A (en) Method and apparatus for binarizing pixel data
CN106920398A (en) A kind of intelligent vehicle license plate recognition system
JP2000023142A (en) Picture monitoring device
JP4409713B2 (en) Document image recognition apparatus and recording medium
JPH08145642A (en) Method and apparatus for recognizing component
JP2003256771A (en) In-scene character imaging method and device therefor, and in-scene character imaging program and recording medium with the program recorded thereon
CN117894031A (en) Method for recognizing and photographing electric energy meter and readable storage medium
JP3220226B2 (en) Character string direction determination method

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