CN108197642B - Seal identification method and device - Google Patents
Seal identification method and device Download PDFInfo
- Publication number
- CN108197642B CN108197642B CN201711418942.1A CN201711418942A CN108197642B CN 108197642 B CN108197642 B CN 108197642B CN 201711418942 A CN201711418942 A CN 201711418942A CN 108197642 B CN108197642 B CN 108197642B
- Authority
- CN
- China
- Prior art keywords
- image
- seal
- difference
- determining
- target
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 38
- 238000009826 distribution Methods 0.000 claims description 12
- 238000003709 image segmentation Methods 0.000 claims description 7
- 238000000605 extraction Methods 0.000 claims description 6
- 239000000126 substance Substances 0.000 claims description 3
- 230000008569 process Effects 0.000 description 12
- 239000002184 metal Substances 0.000 description 10
- 239000000463 material Substances 0.000 description 6
- 238000010586 diagram Methods 0.000 description 4
- 238000003860 storage Methods 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 238000010276 construction Methods 0.000 description 2
- 239000006185 dispersion Substances 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000003825 pressing Methods 0.000 description 2
- 230000006399 behavior Effects 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000000717 retained effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
- G06V10/751—Comparing pixel values or logical combinations thereof, or feature values having positional relevance, e.g. template matching
-
- 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
- G06T7/00—Image analysis
- G06T7/30—Determination of transform parameters for the alignment of images, i.e. image registration
-
- 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
- G06T2207/10004—Still image; Photographic image
Abstract
The invention provides a seal identification method and a device, and the method can comprise the following steps: extracting a red region in a target image to form a first image; segmenting a second image comprising a stamp to be authenticated from the first image; and identifying the seal to be identified according to the second image and a preset standard seal image, wherein the seal to be identified corresponds to the standard seal image. The scheme can automatically identify the seal.
Description
Technical Field
The invention relates to the technical field of computers, in particular to a seal identification method and a seal identification device.
Background
With the continuous deepening of the internet and the government affair service and the internet and the administrative examination and approval, the construction requirement of the intelligent examination and approval government affair service platform is quickened, the construction of the intelligent examination and approval government affair service platform is promoted, the repeated workload in various filling materials and examination can be reduced to the maximum extent, and the people can handle the affairs more conveniently and quickly. In examining various materials, the authentication of a stamp is essential in order to authenticate the authenticity of the material.
At present, the seal in the material is mainly identified manually. However, because the materials to be identified are numerous, the number of the seals to be identified is very large, and if the identification is carried out manually, a large amount of manpower and material resources are required. As can be seen from the above description, how to implement automatic identification of a stamp becomes a problem to be solved urgently today.
Disclosure of Invention
The embodiment of the invention provides a seal identification method and a seal identification device, which can automatically identify a seal.
In a first aspect, an embodiment of the present invention provides a stamp identification method, including:
extracting a red region in a target image to form a first image;
segmenting a second image comprising a stamp to be authenticated from the first image;
and identifying the seal to be identified according to the second image and a preset standard seal image, wherein the seal to be identified corresponds to the standard seal image.
Preferably, the first and second electrodes are formed of a metal,
the extracting a red region in a target image to form a first image includes:
converting the target image from an RGB color space to an HSV color space;
for each pixel point in the target image, determining an H value, an S value and a V value corresponding to the current pixel point; determining whether the H value, the S value, and the V value corresponding to the current pixel point are within a range of (0, 8) U (156, 180), (43, 255), and (43, 255); if yes, setting the current pixel point as a white pixel point; otherwise, setting the current pixel point as a black pixel point;
and forming the first image by each white pixel point and each black pixel point.
Preferably, the first and second electrodes are formed of a metal,
the segmenting of the second image including the stamp to be authenticated from the first image includes:
forming a plurality of outlines according to the distribution of the pixel points in the first image;
determining at least one target contour of which the circumscribed rectangle is a square;
aiming at each target contour, calculating the area of the current target contour, calculating the area of an inscribed circle of a circumscribed square of the current target contour, and calculating the difference value between the area of the current target contour and the area of the inscribed circle;
determining a target difference value with the minimum absolute value from the calculated difference values, wherein the target contour corresponding to the target difference value is the contour of the outermost layer of the seal to be identified;
and segmenting the second image formed by the circumscribed square of the target outline corresponding to the target difference from the first image.
Preferably, the first and second electrodes are formed of a metal,
the identifying the seal to be identified according to the second image and a preset standard seal image comprises the following steps:
calculating HU moment characteristics corresponding to the second image and the standard seal image respectively;
calculating the Euclidean distance between the two HU moment features;
determining whether the calculated Euclidean distance is higher than a preset distance threshold value;
and when the calculated Euclidean distance is higher than the distance threshold value, determining that the seal to be identified is a false seal.
Preferably, the first and second electrodes are formed of a metal,
further comprising:
when it is determined that the calculated Euclidean distance is not higher than the distance threshold, performing:
respectively converting the second image and the standard seal image into polar coordinate images;
determining a sum image of the two polar images;
determining a difference image of the sum image and each of the polar images;
for each of the two difference images, determining the number of rows in the difference image that satisfy a condition one and the number of columns that satisfy a condition two; wherein the first condition is:
wherein r isiRepresenting the number of different points in the ith row in the difference image; c characterizing the total number of columns in the difference image; a characterizing a first similarity threshold;
the second condition is as follows:
wherein, ciRepresenting the number of different points in the j column in the difference image;r represents the total number of rows in the difference image; a characterizing the first similarity threshold;
calculating the similarity between the second image and the standard stamp image according to a first formula, wherein the first formula is as follows:
the S represents the similarity between the second image and the standard seal image; n represents the number of rows in one of the difference images that satisfy the condition one; m represents the number of columns meeting the second condition in the difference image corresponding to n; u characterizes the number of rows in the other said difference image that satisfy said condition one; v represents the number of columns meeting the second condition in the difference image corresponding to u; r represents the total number of rows in the difference image; c characterizing the total number of columns in the difference image; α, β, η, ζ, p and q are constants;
judging whether the calculated similarity is lower than a preset second similarity threshold value or not;
if so, determining that the seal to be identified is a false seal; otherwise, determining the seal to be identified as a true seal.
Preferably, the first and second electrodes are formed of a metal,
before the converting the second image and the standard stamp image into polar coordinate images, the method further includes:
determining the thickness and the circle center of the seal to be identified; the thickness is the radius difference between an outer layer circle and an inner layer circle in the seal to be identified;
sequentially forming a plurality of circles from the outer edge of the second image inwards by taking the thickness as a unit;
extracting an annular region between two adjacent target circles from the formed circles, and inverting pixel points in the annular region to form a third image;
forming a plurality of outlines according to the distribution of the pixel points in the third image;
determining a minimum bounding rectangle for each of the contours;
determining a target minimum bounding rectangle with the largest area from all the minimum bounding rectangles;
determining the rotation angle of the seal to be identified according to the center of the target minimum circumscribed rectangle and the circle center;
rotating the second image according to the rotation angle;
the converting the second image and the standard stamp image into polar coordinate images respectively includes:
and respectively converting the second image after being straightened and the standard seal image into the polar coordinate image.
In a second aspect, an embodiment of the present invention provides a stamp identifying apparatus, including: a red region extracting unit, an image dividing unit and a stamp discriminating unit, wherein,
the red region extraction unit is used for extracting a red region in the target image to form a first image;
the image segmentation unit is used for segmenting a second image comprising a seal to be identified from the first image;
the seal identification unit is used for identifying the seal to be identified according to the second image and a preset standard seal image, wherein the seal to be identified corresponds to the standard seal image.
Preferably, the first and second electrodes are formed of a metal,
the red region extraction unit is used for converting the target image from an RGB color space to an HSV color space; for each pixel point in the target image, determining an H value, an S value and a V value corresponding to the current pixel point; determining whether the H value, the S value, and the V value corresponding to the current pixel point are within a range of (0, 8) U (156, 180), (43, 255), and (43, 255); if yes, setting the current pixel point as a white pixel point; otherwise, setting the current pixel point as a black pixel point; and forming the first image by each white pixel point and each black pixel point.
Preferably, the first and second electrodes are formed of a metal,
the image segmentation unit is used for forming a plurality of outlines according to the distribution of pixel points in the first image; determining at least one target contour of which the circumscribed rectangle is a square; aiming at each target contour, calculating the area of the current target contour, calculating the area of an inscribed circle of a circumscribed square of the current target contour, and calculating the difference value between the area of the current target contour and the area of the inscribed circle; determining a target difference value with the minimum absolute value from the calculated difference values, wherein the target contour corresponding to the target difference value is the contour of the outermost layer of the seal to be identified; and segmenting the second image formed by the circumscribed square of the target outline corresponding to the target difference from the first image.
Preferably, the first and second electrodes are formed of a metal,
the seal identification unit is used for calculating HU moment characteristics corresponding to the second image and the standard seal image respectively; calculating the Euclidean distance between the two HU moment features; determining whether the calculated Euclidean distance is higher than a preset distance threshold value; and when the calculated Euclidean distance is higher than the distance threshold value, determining that the seal to be identified is a false seal.
Preferably, the first and second electrodes are formed of a metal,
the seal identification unit is further configured to execute, when it is determined that the calculated euclidean distance is not higher than the distance threshold: respectively converting the second image and the standard seal image into polar coordinate images; determining a sum image of the two polar images; determining a difference image of the sum image and each of the polar images; for each of the two difference images, determining the number of rows in the difference image that satisfy a condition one and the number of columns that satisfy a condition two; calculating the similarity between the second image and the standard seal image according to a formula I; judging whether the calculated similarity is lower than a preset second similarity threshold value or not; if so, determining that the seal to be identified is a false seal; otherwise, determining the seal to be identified as a true seal; wherein the content of the first and second substances,
the first condition is as follows:
wherein r isiRepresenting the number of different points in the ith row in the difference image; c characterizing the total number of columns in the difference image; a characterizing a first similarity threshold;
the second condition is as follows:
wherein, ciRepresenting the number of different points in the j column in the difference image; r represents the total number of rows in the difference image; a characterizing the first similarity threshold;
the first formula is as follows:
the S represents the similarity between the second image and the standard seal image; n represents the number of rows in one of the difference images that satisfy the condition one; m represents the number of columns meeting the second condition in the difference image corresponding to n; u characterizes the number of rows in the other said difference image that satisfy said condition one; v represents the number of columns meeting the second condition in the difference image corresponding to u; r represents the total number of rows in the difference image; c characterizing the total number of columns in the difference image; α, β, η, ζ, p, and q are constants.
Preferably, the first and second electrodes are formed of a metal,
further comprising: a seal registration unit;
the seal registering unit is used for determining the thickness and the circle center of the seal to be identified before the seal identifying unit respectively converts the second image and the standard seal image into polar coordinate images; the thickness is the radius difference between an outer layer circle and an inner layer circle in the seal to be identified; sequentially forming a plurality of circles from the outer edge of the second image inwards by taking the thickness as a unit; extracting an annular region between two adjacent target circles from the formed circles, and inverting pixel points in the annular region to form a third image; forming a plurality of outlines according to the distribution of the pixel points in the third image; determining a minimum bounding rectangle for each of the contours; determining a target minimum bounding rectangle with the largest area from all the minimum bounding rectangles; determining the rotation angle of the seal to be identified according to the center of the target minimum circumscribed rectangle and the circle center; rotating the second image according to the rotation angle;
the seal identification unit is used for respectively converting the second image and the standard seal image which are aligned by the seal registration unit into the polar coordinate image.
The embodiment of the invention provides a seal identification method and a seal identification device, when a seal to be identified in a target image needs to be identified, because the seal to be identified is red, a red area in the target image is firstly extracted, so that the red area and a non-red area in the target image are distinguished through a formed first image, namely the red area has a corresponding pattern in the first image, the non-red area in the target image becomes a blank area in the first image, then a second image comprising the seal to be identified is separated from the formed first image, and then the seal to be identified in the second image can be identified by utilizing a corresponding standard seal image. The whole process does not need to be identified manually, but automatically segments the seal to be identified according to the target image and identifies automatically. Therefore, the scheme can automatically identify the seal.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
FIG. 1 is a flow chart of a method of stamp authentication provided in accordance with one embodiment of the present invention;
FIG. 2 is a schematic diagram of a second image provided by one embodiment of the present invention;
FIG. 3 is a schematic diagram of a third image provided by an embodiment of the invention;
FIG. 4 is a schematic structural diagram of a stamp identification device according to an embodiment of the present invention;
fig. 5 is a schematic structural diagram of a stamp identification apparatus according to another embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer and more complete, the technical solutions in the embodiments of the present invention will be described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention, and based on the embodiments of the present invention, all other embodiments obtained by a person of ordinary skill in the art without creative efforts belong to the scope of the present invention.
As shown in fig. 1, an embodiment of the present invention provides a stamp identification method, which may include the following steps:
step 101: a red region in the target image is extracted to form a first image.
Step 102: a second image including a stamp to be authenticated is segmented from the first image.
Step 103: and identifying the seal to be identified according to the second image and a preset standard seal image, wherein the seal to be identified corresponds to the standard seal image.
The embodiment of the invention provides a seal identification method, when a seal to be identified in a target image needs to be identified, because the seal to be identified is red, a red area in the target image is firstly extracted, so that the red area and a non-red area in the target image are distinguished through a formed first image, namely the red area has a corresponding pattern in the first image, the non-red area in the target image becomes a blank area in the first image, then a second image including the seal to be identified is segmented from the formed first image, and then the seal to be identified in the second image of a corresponding standard seal can be used for identification. The whole process does not need to be identified manually, but automatically segments the seal to be identified according to the target image and identifies automatically. Therefore, the scheme can automatically identify the seal.
In an embodiment of the present invention, since the stamp to be authenticated in the target image is red, in order to segment the stamp to be authenticated later, first extracting all red regions in the target image, where a specific implementation manner of the step 101 may include:
converting the target image from an RGB color space to an HSV color space;
for each pixel point in the target image, determining an H value, an S value and a V value corresponding to the current pixel point; determining whether the H value, the S value, and the V value corresponding to the current pixel point are within a range of (0, 8) U (156, 180), (43, 255), and (43, 255); if yes, setting the current pixel point as a white pixel point; otherwise, setting the current pixel point as a black pixel point;
and forming the first image by each white pixel point and each black pixel point. Only the red stamp to be authenticated may be present in the partial target image, and not only the red stamp to be authenticated may be present in the partial target image, for example, the target image is a license (a red national emblem pattern is provided at an upper middle position of the license). Specifically, the extracted red region in the target image can be converted into a binarized image, that is, when the H value, the S value and the V value of a pixel point in the target image are in each preset interval range, a certain pixel point of the red region is determined at first, then binarization processing is performed, that is, the pixel point is set as a white pixel point, if three values corresponding to certain pixel points in the target image are not in each interval range, it is determined that the pixel points are not the pixel points of the red region, and all the pixel points are set as black pixel points, so that after extraction, the red region corresponds to the white pixel points in the first image, and the non-red region corresponds to the black pixel points in the first image, thereby forming the binarized first image. For example, if only a red stamp to be authenticated exists in the target image, the formed first image has the stamp to be authenticated, which is composed of white pixel points, and non-red areas in the target image are all black pixel points in the first image, that is, only the red area in the target image is extracted; if the target image is a business license, the formed first image has not only the seal to be identified composed of white pixel points, but also the national emblem pattern composed of other white pixel points, and other non-red areas in the business license are all black pixel points in the first image, that is, the extracted red area includes both the seal to be identified and the national emblem pattern.
In an embodiment of the present invention, in order to separate the stamp to be authenticated from the stamp to be authenticated, the specific implementation manner of the step 102 may include:
forming a plurality of outlines according to the distribution of the pixel points in the first image;
determining at least one target contour of which the circumscribed rectangle is a square;
aiming at each target contour, calculating the area of the current target contour, calculating the area of an inscribed circle of a circumscribed square of the current target contour, and calculating the difference value between the area of the current target contour and the area of the inscribed circle;
determining a target difference value with the minimum absolute value from the calculated difference values, wherein the target contour corresponding to the target difference value is the contour of the outermost layer of the seal to be identified;
and segmenting the second image formed by the circumscribed square of the target outline corresponding to the target difference from the first image.
For example, after the stamp to be identified in the target image is a circular stamp, after the first image is formed, a plurality of outlines are formed in the first image, for example, a five-pointed star outline (the area of the five-pointed star outline is almost the same as the area of the five-pointed star) is formed for a five-pointed star in the stamp to be identified, a circular outline is formed for the outer side of the stamp to be identified, a corresponding outline is formed for each Chinese character and number in the stamp to be identified, if the first image further comprises a national emblem pattern, each outline is formed for the national emblem pattern, for example, an outline comprising an arc shape but not a circle is formed for the outermost side of the national emblem pattern (specifically, the national emblem pattern can be referred to), because the circumscribed rectangle at the outermost side of the circular stamp is a square, all outlines which are not squares (for example, the circumscribed rectangles corresponding to the Chinese character and number outlines are circumscribed rectangles are both eliminated in order to improve the identification efficiency), then, in each contour of the remaining circumscribed rectangles which are squares (for example, the circumscribed rectangle of the contour corresponding to the five-pointed star is a square, the circumscribed rectangle of the circular contour is a square, and the circumscribed rectangle of the outermost side of the national emblem pattern is also a square), then, by calculating the area of the inscribed circle of the contour and performing difference calculation with the area of the contour, the contour of the outer side of the circular stamp can be determined (because the outermost side of the national emblem pattern is non-circular, the calculated difference is relatively large, and the area difference between the contour of the five-pointed star corresponding to the five-pointed star and the corresponding inscribed circle is also relatively large, only the inscribed circle area of the circumscribed square corresponding to the circular contour is closest to the corresponding circle contour area), so that the stamp to be identified can be subsequently divided from the first image, specifically, in one way, the stamp to be identified is divided from the first image according to the determined outline of the outer layer of the circular stamp, alternatively, when a circumscribed square of the outline of the circle outside the circular stamp is determined, the coordinates of the four vertices of the square are returned, and then the square can be segmented from the first image according to the coordinates of the four vertices, as shown in fig. 2, so that a second image including the stamp to be authenticated can also be obtained. In the actual operation process, the second mode is easier to realize and has higher processing speed than the first mode, so that the second mode can be selected preferentially, and other patterns are filtered out from the obtained second image, and only the stamp to be identified exists.
The description of the values is that some target images may have some very small red dispersion points, and these dispersion points are also retained in the first image when the red region is extracted, so after each contour is formed for the first image, some contours with a contour area smaller than a preset area threshold value can be kicked out, and thus the efficiency of seal authentication can be further improved.
In an embodiment of the present invention, in order to determine whether the stamp to be authenticated is a false stamp, a specific implementation manner of step 103 may include:
calculating HU moment characteristics corresponding to the second image and the standard seal image respectively;
calculating the Euclidean distance between the two HU moment features;
determining whether the calculated Euclidean distance is higher than a preset distance threshold value;
and when the calculated Euclidean distance is higher than the distance threshold value, determining that the seal to be identified is a false seal.
In an embodiment of the present invention, in order to further determine whether the seal to be authenticated is authentic, the method may further include:
when it is determined that the calculated Euclidean distance is not higher than the distance threshold, performing:
respectively converting the second image and the standard seal image into polar coordinate images;
determining a sum image of the two polar images;
determining a difference image of the sum image and each of the polar images;
for each of the two difference images, determining the number of rows in the difference image that satisfy a condition one and the number of columns that satisfy a condition two; wherein the first condition is:
wherein r isiRepresenting the number of different points in the ith row in the difference image; c characterizing the total number of columns in the difference image; a characterizing a first similarity threshold;
the second condition is as follows:
wherein, ciRepresenting the number of different points in the j column in the difference image; r represents the total number of rows in the difference image; a characterizing the first similarity threshold;
calculating the similarity between the second image and the standard stamp image according to a first formula, wherein the first formula is as follows:
the S represents the similarity between the second image and the standard seal image; n represents the number of rows in one of the difference images that satisfy the condition one; m represents the number of columns meeting the second condition in the difference image corresponding to n; u characterizes the number of rows in the other said difference image that satisfy said condition one; v represents the number of columns meeting the second condition in the difference image corresponding to u; r represents the total number of rows in the difference image; c characterizing the total number of columns in the difference image; α, β, η, ζ, p and q are constants;
judging whether the calculated similarity is lower than a preset second similarity threshold value or not;
if so, determining that the seal to be identified is a false seal; otherwise, determining the seal to be identified as a true seal.
The value of the first similarity threshold a may be 0.1, and the total number of rows and the total number of columns in the two obtained difference images may be the same.
In the embodiment of the invention, the second image and the standard seal image are both binary valuesAnd (4) forming an image. For example, if the different points are white pixel points, the total number of rows in each difference image is 100 rows, and the total number of columns is 360 columns, then for each row in each difference image, it is necessary to determine whether the difference image is a similar row, and for each column in each difference image, it is necessary to determine whether the difference image is a similar column, and for each column in each difference image, with the first behavior example, assuming that there are 10 white pixel points in the row, since there are 360 columns, there are 360 pixel points in each row, then there are 10 white pixel points in the row, and so on
That is, the row is a similar row when the condition one is satisfied, the row number of the similar row in each difference image can be determined through the same determination process, the calculation process for the column is similar to the determination process for the row, which is not described herein again, and reference may be made to the determination process for the row. Assuming that 60 lines in the first difference image satisfy the first condition, 280 columns in the first difference image satisfy the second condition, 80 lines in the second image satisfy the first condition, and 240 columns satisfy the second condition, the similarity between the second image and the standard stamp image is calculated as formula one
And finally, comparing the calculated similarity with a preset second similarity threshold value to determine the authenticity of the seal to be identified.
The second image and the standard seal image are respectively converted into polar coordinate images, and then the sum image of the two polar coordinate images is calculated, so that the incomplete part in the second image can be covered by the standard seal image, the influence caused by factors such as uneven pressing force degree of the seal, less inkpad and the like is properly reduced, and the accuracy of seal identification to be identified is improved.
In an embodiment of the present invention, in order to align the non-aligned to-be-authenticated stamp, before converting the second image and the standard stamp image into polar coordinate images, the method further includes:
determining the thickness and the circle center of the seal to be identified; the thickness is the radius difference between an outer layer circle and an inner layer circle in the seal to be identified;
sequentially forming a plurality of circles from the outer edge of the second image inwards by taking the thickness as a unit;
extracting an annular region between two adjacent target circles from the formed circles, and inverting pixel points in the annular region to form a third image;
forming a plurality of outlines according to the distribution of the pixel points in the third image;
determining a minimum bounding rectangle for each of the contours;
determining a target minimum bounding rectangle with the largest area from all the minimum bounding rectangles;
determining the rotation angle of the seal to be identified according to the center of the target minimum circumscribed rectangle and the circle center;
rotating the second image according to the rotation angle;
the converting the second image and the standard stamp image into polar coordinate images respectively includes:
and respectively converting the second image after being straightened and the standard seal image into the polar coordinate image.
For example, the second image segmented from the first image is a square, and the inscribed circle of the square is the outer circle of the circular stamp. Assuming that the side length of the square is x, establishing a coordinate system by taking the top left corner vertex of the square as the center of a circle, so that the seal to be identified is positioned in the first quadrant, and obtaining the center of the seal to be identified as the center of the circle
Then first of all
Scanning downwards as starting point, when 5 black pixel points can be continuously scanned, thenCalculating the thickness of the seal to be identified by taking the adjacent white pixel point on the 1 st black pixel point as an end point, and then taking the adjacent white pixel point as an end point
As starting point, scan right, and from
The scanning principle is the same, the thickness of the seal to be identified is calculated, and
scanning to left as starting point, calculating the thickness of the seal to be identified, and finally, using
The upward scan is performed as a starting point to calculate the thickness of the stamp to be authenticated, so that a total of 4 thicknesses are calculated for the stamp to be authenticated, and as known from the current stamp manufacturing specifications, the ratio of the thickness to the diameter of the circular stamp is approximately 0.027, and therefore the thickness closest to 0.027x is taken out of the calculated 4 thicknesses.
After the thickness of the stamp to be identified is determined, taking the second image shown in fig. 2 as an example, a plurality of circles are formed from the outermost side in fig. 2 inwards in sequence, that is, the distance between two adjacent circles is the determined thickness, and as can be known from the current stamp manufacturing specifications, the annular region formed by the 4 th circle and the 5 th circle of the formed plurality of circles includes a blank region below the stamp (taking fig. 2 as an example, namely, a blank region between "electricity" and "use"), then the annular region between the 4 th circle and the 5 th circle (referring to the number from the outside) can be extracted from the plurality of circles, the annular region includes a part of some characters, and as the parts are white pixel points, black pixel points are obtained after inversion, and the black pixel points in the annular region become white pixel points, so that a third image shown in fig. 3 can be obtained, as can be seen from fig. 3, the area of the minimum circumscribed rectangle corresponding to the region formed by the continuous longest white pixel points is the largest, and then, as long as the center of the minimum circumscribed rectangle with the largest area is found, and then the center and the circle center are connected, the rotation angle can be determined, and if the calculated rotation angle is θ with reference to the downward direction, the corresponding second image needs to be rotated counterclockwise by θ degrees, so that the second image is aligned.
The description of the value is that, in order to reduce the error, after the aligned second image is obtained, according to the aligned second image, a fourth image that swings a certain angle (e.g., 1 to 5 degrees) to the right and a fifth image that swings a certain angle to the left are obtained, and then the aligned second image, fourth image and fifth image can be respectively identified with the standard stamp image, and the maximum similarity that can be calculated finally is taken as the criterion, and then the maximum similarity is compared with the preset second similarity threshold, so as to determine the authenticity of the corresponding stamp to be identified.
In an embodiment of the present invention, as shown in fig. 4, an embodiment of the present invention provides a stamp identifying apparatus, including: a red region extraction unit 401, an image segmentation unit 402, and a stamp identification unit 403, wherein,
the red region extracting unit 401 is configured to extract a red region in the target image to form a first image;
the image segmentation unit 402 is configured to segment a second image including a stamp to be authenticated from the first image;
the stamp identifying unit 403 is configured to identify the stamp to be identified according to the second image and a preset standard stamp image, where the stamp to be identified corresponds to the standard stamp image.
In an embodiment of the present invention, the red region extracting unit is configured to convert the target image from an RGB color space to an HSV color space; for each pixel point in the target image, determining an H value, an S value and a V value corresponding to the current pixel point; determining whether the H value, the S value, and the V value corresponding to the current pixel point are within a range of (0, 8) U (156, 180), (43, 255), and (43, 255); if yes, setting the current pixel point as a white pixel point; otherwise, setting the current pixel point as a black pixel point; and forming the first image by each white pixel point and each black pixel point.
In an embodiment of the present invention, the image segmentation unit is configured to form a plurality of contours according to distribution of pixel points in the first image; determining at least one target contour of which the circumscribed rectangle is a square; aiming at each target contour, calculating the area of the current target contour, calculating the area of an inscribed circle of a circumscribed square of the current target contour, and calculating the difference value between the area of the current target contour and the area of the inscribed circle; determining a target difference value with the minimum absolute value from the calculated difference values, wherein the target contour corresponding to the target difference value is the contour of the outermost layer of the seal to be identified; and segmenting the second image formed by the circumscribed square of the target outline corresponding to the target difference from the first image.
In an embodiment of the present invention, the stamp identifying unit is configured to calculate HU moment features corresponding to the second image and the standard stamp image respectively; calculating the Euclidean distance between the two HU moment features; determining whether the calculated Euclidean distance is higher than a preset distance threshold value; and when the calculated Euclidean distance is higher than the distance threshold value, determining that the seal to be identified is a false seal.
In an embodiment of the present invention, the seal identification unit is further configured to, when it is determined that the calculated euclidean distance is not higher than the distance threshold, perform: respectively converting the second image and the standard seal image into polar coordinate images; determining a sum image of the two polar images; determining a difference image of the sum image and each of the polar images; for each of the two difference images, determining the number of rows in the difference image that satisfy a condition one and the number of columns that satisfy a condition two; calculating the similarity between the second image and the standard seal image according to a formula I; judging whether the calculated similarity is lower than a preset second similarity threshold value or not; if so, determining that the seal to be identified is a false seal; otherwise, determining the seal to be identified as a true seal; wherein the content of the first and second substances,
the first condition is as follows:
wherein r isiRepresenting the number of different points in the ith row in the difference image; c characterizing the total number of columns in the difference image; a characterizing a first similarity threshold;
the second condition is as follows:
wherein, ciRepresenting the number of different points in the j column in the difference image; r represents the total number of rows in the difference image; a characterizing the first similarity threshold;
the first formula is as follows:
the S represents the similarity between the second image and the standard seal image; n represents the number of rows in one of the difference images that satisfy the condition one; m represents the number of columns meeting the second condition in the difference image corresponding to n; u characterizes the number of rows in the other said difference image that satisfy said condition one; v represents the number of columns meeting the second condition in the difference image corresponding to u; r represents the total number of rows in the difference image; c characterizing the total number of columns in the difference image; α, β, η, ζ, p, and q are constants.
As shown in fig. 5, in an embodiment of the present invention, the method may further include: a stamp registration unit 401;
the seal registering unit 501 is configured to determine the thickness and the center of a circle of the seal to be authenticated before the seal authenticating unit 403 converts the second image and the standard seal image into polar coordinate images, respectively; the thickness is the radius difference between an outer layer circle and an inner layer circle in the seal to be identified; sequentially forming a plurality of circles from the outer edge of the second image inwards by taking the thickness as a unit; extracting an annular region between two adjacent target circles from the formed circles, and inverting pixel points in the annular region to form a third image; forming a plurality of outlines according to the distribution of the pixel points in the third image; determining a minimum bounding rectangle for each of the contours; determining a target minimum bounding rectangle with the largest area from all the minimum bounding rectangles; determining the rotation angle of the seal to be identified according to the center of the target minimum circumscribed rectangle and the circle center; rotating the second image according to the rotation angle;
the stamp identifying unit 403 is configured to convert the second image and the standard stamp image after being aligned by the stamp registering unit 501 into the polar coordinate images, respectively.
Because the information interaction, execution process, and other contents between the units in the device are based on the same concept as the method embodiment of the present invention, specific contents may refer to the description in the method embodiment of the present invention, and are not described herein again.
The embodiment of the invention provides a computer-readable medium, which comprises a computer execution instruction, wherein when a processor of a storage controller executes the computer execution instruction, the storage controller executes the seal identification method in any embodiment.
An embodiment of the present invention provides a memory controller, including: a processor, a memory, and a bus;
the memory is used for storing computer execution instructions, the processor is connected with the memory through the bus, and when the memory controller runs, the processor executes the computer execution instructions stored in the memory, so that the memory controller executes the seal identification method according to any one of the embodiments.
In summary, the embodiments of the present invention have at least the following advantages:
1. in the embodiment of the invention, when the stamp to be identified in the target image needs to be identified, because the stamp to be identified is red, the red region in the target image is firstly extracted, so that the red region and the non-red region in the target image are distinguished through the formed first image, namely the red region has a corresponding pattern in the first image, the non-red region in the target image becomes a blank region in the first image, then the second image including the stamp to be identified is divided from the formed first image, and then the stamp to be identified in the second image can be identified by using the corresponding standard stamp image. The whole process does not need to be identified manually, but automatically segments the seal to be identified according to the target image and identifies automatically. Therefore, the scheme can automatically identify the seal.
2. In the embodiment of the invention, the second image and the standard seal image are respectively converted into the polar coordinate images, and then the sum image of the two polar coordinate images is calculated, so that the incomplete part in the second image can be covered by using the standard seal image, the influence caused by factors such as uneven pressing force of the seal, less inkpad and the like is properly reduced, and the accuracy of identifying the seal to be identified is improved.
3. In the embodiment of the invention, before the second image is converted into the polar coordinate image, the rotation angle of the seal to be identified is determined, and then the seal to be identified is rotated, so that the second image after being aligned can be obtained, and the accuracy of the identification of the seal to be identified can be improved.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising a" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
Those of ordinary skill in the art will understand that: all or part of the steps for realizing the method embodiments can be completed by hardware related to program instructions, the program can be stored in a computer readable storage medium, and the program executes the steps comprising the method embodiments when executed; and the aforementioned storage medium includes: various media that can store program codes, such as ROM, RAM, magnetic or optical disks.
Finally, it is to be noted that: the above description is only a preferred embodiment of the present invention, and is only used to illustrate the technical solutions of the present invention, and not to limit the protection scope of the present invention. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention shall fall within the protection scope of the present invention.
Claims (2)
1. A method of authenticating a seal, comprising:
extracting a red region in a target image to form a first image;
segmenting a second image comprising a stamp to be authenticated from the first image;
identifying the seal to be identified according to the second image and a preset standard seal image, wherein the seal to be identified corresponds to the standard seal image;
the extracting a red region in a target image to form a first image includes:
converting the target image from an RGB color space to an HSV color space;
for each pixel point in the target image, determining an H value, an S value and a V value corresponding to the current pixel point; determining whether the H value, the S value, and the V value corresponding to the current pixel point are within a range of (0, 8) U (156, 180), (43, 255), and (43, 255); if yes, setting the current pixel point as a white pixel point; otherwise, setting the current pixel point as a black pixel point;
each white pixel point and each black pixel point form the first image;
and/or the presence of a gas in the gas,
the segmenting of the second image including the stamp to be authenticated from the first image includes:
forming a plurality of outlines according to the distribution of the pixel points in the first image;
determining at least one target contour of which the circumscribed rectangle is a square;
aiming at each target contour, calculating the area of the current target contour, calculating the area of an inscribed circle of a circumscribed square of the current target contour, and calculating the difference value between the area of the current target contour and the area of the inscribed circle;
determining a target difference value with the minimum absolute value from the calculated difference values, wherein the target contour corresponding to the target difference value is the contour of the outermost layer of the seal to be identified;
segmenting the second image formed by a circumscribed square of the target contour corresponding to the target difference from the first image;
the identifying the seal to be identified according to the second image and a preset standard seal image comprises the following steps:
calculating HU moment characteristics corresponding to the second image and the standard seal image respectively;
calculating the Euclidean distance between the two HU moment features;
determining whether the calculated Euclidean distance is higher than a preset distance threshold value;
when the calculated Euclidean distance is higher than the distance threshold value, determining that the seal to be identified is a false seal;
further comprising:
when it is determined that the calculated Euclidean distance is not higher than the distance threshold, performing:
respectively converting the second image and the standard seal image into polar coordinate images;
determining a sum image of the two polar images;
determining a difference image of the sum image and each of the polar images;
for each of the two difference images, determining the number of rows in the difference image that satisfy a condition one and the number of columns that satisfy a condition two; wherein the first condition is:
wherein r isiRepresenting the number of different points in the ith row in the difference image; c characterizing the total number of columns in the difference image; a characterizing a first similarity threshold;
the second condition is as follows:
wherein, ciRepresenting the number of different points in the j column in the difference image; r represents the total number of rows in the difference image; a characterizing the first similarity threshold;
calculating the similarity between the second image and the standard stamp image according to a first formula, wherein the first formula is as follows:
the S represents the similarity between the second image and the standard seal image; n represents the number of rows in one of the difference images that satisfy the condition one; m represents the number of columns meeting the second condition in the difference image corresponding to n; u characterizes the number of rows in the other said difference image that satisfy said condition one; v represents the number of columns meeting the second condition in the difference image corresponding to u; r represents the total number of rows in the difference image; c characterizing the total number of columns in the difference image; α, β, η, ζ, p and q are constants;
judging whether the calculated similarity is lower than a preset second similarity threshold value or not;
if so, determining that the seal to be identified is a false seal; otherwise, determining the seal to be identified as a true seal;
before the converting the second image and the standard stamp image into polar coordinate images, the method further includes:
determining the thickness and the circle center of the seal to be identified; the thickness is the radius difference between an outer layer circle and an inner layer circle in the seal to be identified;
sequentially forming a plurality of circles from the outer edge of the second image inwards by taking the thickness as a unit;
extracting an annular region between two adjacent target circles from the formed circles, and inverting pixel points in the annular region to form a third image;
forming a plurality of outlines according to the distribution of the pixel points in the third image;
determining a minimum bounding rectangle for each of the contours;
determining a target minimum bounding rectangle with the largest area from all the minimum bounding rectangles;
determining the rotation angle of the seal to be identified according to the center of the target minimum circumscribed rectangle and the circle center;
rotating the second image according to the rotation angle;
the converting the second image and the standard stamp image into polar coordinate images respectively includes:
and respectively converting the second image after being straightened and the standard seal image into the polar coordinate image.
2. A stamp authentication apparatus, comprising: a red region extracting unit, an image dividing unit and a stamp discriminating unit, wherein,
the red region extraction unit is used for extracting a red region in the target image to form a first image;
the image segmentation unit is used for segmenting a second image comprising a seal to be identified from the first image;
the seal identification unit is used for identifying the seal to be identified according to the second image and a preset standard seal image, wherein the seal to be identified corresponds to the standard seal image;
the red region extraction unit is used for converting the target image from an RGB color space to an HSV color space; for each pixel point in the target image, determining an H value, an S value and a V value corresponding to the current pixel point; determining whether the H value, the S value, and the V value corresponding to the current pixel point are within a range of (0, 8) U (156, 180), (43, 255), and (43, 255); if yes, setting the current pixel point as a white pixel point; otherwise, setting the current pixel point as a black pixel point; each white pixel point and each black pixel point form the first image;
and/or the presence of a gas in the gas,
the image segmentation unit is used for forming a plurality of outlines according to the distribution of pixel points in the first image; determining at least one target contour of which the circumscribed rectangle is a square; aiming at each target contour, calculating the area of the current target contour, calculating the area of an inscribed circle of a circumscribed square of the current target contour, and calculating the difference value between the area of the current target contour and the area of the inscribed circle; determining a target difference value with the minimum absolute value from the calculated difference values, wherein the target contour corresponding to the target difference value is the contour of the outermost layer of the seal to be identified; segmenting the second image formed by a circumscribed square of the target contour corresponding to the target difference from the first image;
the seal identification unit is used for calculating HU moment characteristics corresponding to the second image and the standard seal image respectively; calculating the Euclidean distance between the two HU moment features; determining whether the calculated Euclidean distance is higher than a preset distance threshold value; when the calculated Euclidean distance is higher than the distance threshold value, determining that the seal to be identified is a false seal;
the seal identification unit is further configured to execute, when it is determined that the calculated euclidean distance is not higher than the distance threshold: respectively converting the second image and the standard seal image into polar coordinate images; determining a sum image of the two polar images; determining a difference image of the sum image and each of the polar images; for each of the two difference images, determining the number of rows in the difference image that satisfy a condition one and the number of columns that satisfy a condition two; calculating the similarity between the second image and the standard seal image according to a formula I; judging whether the calculated similarity is lower than a preset second similarity threshold value or not; if so, determining that the seal to be identified is a false seal; otherwise, determining the seal to be identified as a true seal; wherein the content of the first and second substances,
the first condition is as follows:
wherein r isiRepresenting the number of different points in the ith row in the difference image; c characterizing the total number of columns in the difference image; a characterizing a first similarity threshold;
the second condition is as follows:
wherein, ciRepresenting the number of different points in the j column in the difference image; r represents the total number of rows in the difference image; a characterizing the first similarity threshold;
the first formula is as follows:
the S represents the similarity between the second image and the standard seal image; n represents the number of rows in one of the difference images that satisfy the condition one; m represents the number of columns meeting the second condition in the difference image corresponding to n; u characterizes the number of rows in the other said difference image that satisfy said condition one; v represents the number of columns meeting the second condition in the difference image corresponding to u; r represents the total number of rows in the difference image; c characterizing the total number of columns in the difference image; α, β, η, ζ, p and q are constants;
further comprising: a seal registration unit;
the seal registering unit is used for determining the thickness and the circle center of the seal to be identified before the seal identifying unit respectively converts the second image and the standard seal image into polar coordinate images; the thickness is the radius difference between an outer layer circle and an inner layer circle in the seal to be identified; sequentially forming a plurality of circles from the outer edge of the second image inwards by taking the thickness as a unit; extracting an annular region between two adjacent target circles from the formed circles, and inverting pixel points in the annular region to form a third image; forming a plurality of outlines according to the distribution of the pixel points in the third image; determining a minimum bounding rectangle for each of the contours; determining a target minimum bounding rectangle with the largest area from all the minimum bounding rectangles; determining the rotation angle of the seal to be identified according to the center of the target minimum circumscribed rectangle and the circle center; rotating the second image according to the rotation angle;
the seal identification unit is used for respectively converting the second image and the standard seal image which are aligned by the seal registration unit into the polar coordinate image.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711418942.1A CN108197642B (en) | 2017-12-25 | 2017-12-25 | Seal identification method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711418942.1A CN108197642B (en) | 2017-12-25 | 2017-12-25 | Seal identification method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108197642A CN108197642A (en) | 2018-06-22 |
| CN108197642B true CN108197642B (en) | 2021-11-30 |
Family
ID=62583900
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711418942.1A Active CN108197642B (en) | 2017-12-25 | 2017-12-25 | Seal identification method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108197642B (en) |
Families Citing this family (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109636825B (en) * | 2018-11-01 | 2023-07-18 | 平安科技（深圳）有限公司 | Seal pattern segmentation method, device and computer readable storage medium |
| CN111353485B (en) * | 2018-12-20 | 2023-09-05 | 中国移动通信集团辽宁有限公司 | Seal identification method, device, equipment and medium |
| CN109767436B (en) * | 2019-01-07 | 2021-03-02 | 深圳市安印科技有限公司 | Method and device for identifying authenticity of seal |
| CN110059722A (en) * | 2019-03-16 | 2019-07-26 | 平安城市建设科技(深圳)有限公司 | Checking method, device, equipment and the readable storage medium storing program for executing of seal image |
| CN110001224B (en) * | 2019-05-15 | 2023-07-21 | 南京信息工程大学 | Automatic equipment for large-scale bill stamping and checking |
| CN110472623B (en) * | 2019-06-29 | 2022-08-09 | 华为技术有限公司 | Image detection method, device and system |
| CN111291757B (en) * | 2020-02-17 | 2023-08-15 | 江苏诚印科技有限公司 | Method for uniquely identifying seal |
| CN111882570A (en) * | 2020-07-28 | 2020-11-03 | 浙江水晶光电科技股份有限公司 | Edge positioning method and device, storage medium and electronic equipment |
| CN112784900A (en) * | 2021-01-22 | 2021-05-11 | 深圳壹账通智能科技有限公司 | Image target comparison method and device, computer equipment and readable storage medium |
| CN113177961B (en) * | 2021-06-07 | 2022-07-01 | 重庆傲雄在线信息技术有限公司 | Multi-mode depth model training method for seal image-text comparison |
| CN113705330B (en) * | 2021-07-08 | 2023-12-01 | 厦门科路德科技有限公司 | Seal authenticity identification method and system |
| CN114240405B (en) * | 2022-02-24 | 2022-06-07 | 深圳市关贸云科技有限公司 | Intelligent customs management system based on data analysis |
| CN114419655A (en) * | 2022-03-31 | 2022-04-29 | 北京惠朗时代科技有限公司 | Seal verification method, seal verification device, seal verification medium and seal verification equipment |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101162506A (en) * | 2007-11-02 | 2008-04-16 | 北京大学 | Seal imprint image search method of circular stamp |
| CN101894260A (en) * | 2010-06-04 | 2010-11-24 | 北京化工大学 | Method for identifying forgery seal based on feature line randomly generated by matching feature points |
| CN102054168A (en) * | 2010-12-23 | 2011-05-11 | 武汉大学苏州研究院 | Method for recognizing circular seal on valuable bill |
| CN107180479A (en) * | 2017-05-15 | 2017-09-19 | 深圳怡化电脑股份有限公司 | A kind of bill discrimination method, device, equipment and storage medium |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP4273619B2 (en) * | 2000-03-16 | 2009-06-03 | 沖電気工業株式会社 | Seal verification device |
| CN101533517B (en) * | 2009-04-15 | 2012-05-23 | 北京联合大学 | Structure feature based on Chinese painting and calligraphy seal image automatic extracting method |
| US8342414B2 (en) * | 2010-04-30 | 2013-01-01 | Chapman Bryan P | Multiface document |
| CN101894268B (en) * | 2010-07-16 | 2012-05-23 | 西安理工大学 | Seal authenticity identification method capable of eliminating receipt interference |
| CN102842035B (en) * | 2012-07-11 | 2015-06-24 | 京北方信息技术股份有限公司 | Rectangular seal positioning method and device aiming at certificate image |
| CN103617673B (en) * | 2013-12-10 | 2016-01-20 | 江苏国光信息产业股份有限公司 | A kind of check distinguishing method between true and false based on ultraviolet image feature |
| CN103729656A (en) * | 2014-01-22 | 2014-04-16 | 河北远东通信系统工程有限公司 | Seal imprint identification method and identification system |
-
2017
- 2017-12-25 CN CN201711418942.1A patent/CN108197642B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101162506A (en) * | 2007-11-02 | 2008-04-16 | 北京大学 | Seal imprint image search method of circular stamp |
| CN101894260A (en) * | 2010-06-04 | 2010-11-24 | 北京化工大学 | Method for identifying forgery seal based on feature line randomly generated by matching feature points |
| CN102054168A (en) * | 2010-12-23 | 2011-05-11 | 武汉大学苏州研究院 | Method for recognizing circular seal on valuable bill |
| CN107180479A (en) * | 2017-05-15 | 2017-09-19 | 深圳怡化电脑股份有限公司 | A kind of bill discrimination method, device, equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108197642A (en) | 2018-06-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108197642B (en) | Seal identification method and device | |
| JP7113657B2 (en) | Information processing device, information processing method, and program | |
| WO2018137612A1 (en) | Road sign recognition method and system | |
| Gebhardt et al. | Document authentication using printing technique features and unsupervised anomaly detection | |
| US8590794B2 (en) | Barcode recognion method and computer product thereof | |
| US20110007970A1 (en) | System and method for segmenting text lines in documents | |
| CN108985305B (en) | Laser etching industrial detonator coded image positioning and correcting method | |
| CN106326895B (en) | Image processing apparatus, image processing method, and program | |
| CN112329756A (en) | Method and device for extracting seal and recognizing characters | |
| CN110765992A (en) | Seal identification method, medium, equipment and device | |
| JP7076772B2 (en) | Authentication system and authentication method | |
| CN113435219B (en) | Anti-counterfeiting detection method and device, electronic equipment and storage medium | |
| CN111046754B (en) | Character recognition method, device and computer readable storage medium | |
| CN114863492A (en) | Method and device for repairing low-quality fingerprint image | |
| CN113076768B (en) | Distortion correction method for fuzzy recognizable two-dimensional code | |
| CN108205641B (en) | Gesture image processing method and device | |
| JP3416058B2 (en) | Character extraction method of gray image and recording medium recording the program | |
| CN110378337B (en) | Visual input method and system for drawing identification information of metal cutting tool | |
| CN115410191B (en) | Text image recognition method, device, equipment and storage medium | |
| CN115984211A (en) | Visual positioning method, robot and storage medium | |
| CN113361547A (en) | Signature identification method, device, equipment and readable storage medium | |
| KR101991461B1 (en) | Character recognition system and method using vectorization of feature points | |
| CN109472765B (en) | Method and device for detecting quality of code spraying | |
| CN109753981B (en) | Image recognition method and device | |
| CN108573253B (en) | Method for generating binary image of characters of license plate |
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 |