CN110956737B - Safety line identification method and device - Google Patents
Safety line identification method and device Download PDFInfo
- Publication number
- CN110956737B CN110956737B CN202010011798.5A CN202010011798A CN110956737B CN 110956737 B CN110956737 B CN 110956737B CN 202010011798 A CN202010011798 A CN 202010011798A CN 110956737 B CN110956737 B CN 110956737B
- Authority
- CN
- China
- Prior art keywords
- ref
- safety line
- dimensional
- image
- information
- 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
Images
Classifications
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07D—HANDLING OF COINS OR VALUABLE PAPERS, e.g. TESTING, SORTING BY DENOMINATIONS, COUNTING, DISPENSING, CHANGING OR DEPOSITING
- G07D7/00—Testing specially adapted to determine the identity or genuineness of valuable papers or for segregating those which are unacceptable, e.g. banknotes that are alien to a currency
- G07D7/003—Testing specially adapted to determine the identity or genuineness of valuable papers or for segregating those which are unacceptable, e.g. banknotes that are alien to a currency using security elements
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07D—HANDLING OF COINS OR VALUABLE PAPERS, e.g. TESTING, SORTING BY DENOMINATIONS, COUNTING, DISPENSING, CHANGING OR DEPOSITING
- G07D7/00—Testing specially adapted to determine the identity or genuineness of valuable papers or for segregating those which are unacceptable, e.g. banknotes that are alien to a currency
- G07D7/005—Testing security markings invisible to the naked eye, e.g. verifying thickened lines or unobtrusive markings or alterations
Abstract
The invention discloses a safety line identification method, which is characterized by comprising the following steps: acquiring safety line image coordinate information; carrying out affine transformation on the safety line coordinate information to obtain the safety line image coordinates after affine transformation; acquiring and calculating one-dimensional characteristic information of the affine safety line image according to a preset method; and matching with the one-dimensional characteristic information of the standard safety line to judge whether the safety line is abnormal. The safety line one-dimensional feature is converted into a plurality of one-dimensional features, the safety line one-dimensional features are calculated, and the calculated one-dimensional features are matched with the standard safety line one-dimensional features. The method does not depend on the image binarization effect, is not influenced by the type of a CIS, the new and old difference of paper money, a single fixed binarization threshold value and a dynamic threshold value defined according to a proportion range, has a better effect on judging the suspicious paper money conditions such as coating pencils, sticking black tapes and the like in a safety line region, and can judge whether the safety line is spliced or not by matching the one-dimensional characteristics of two lines passing through the safety line.
Description
Technical Field
The invention relates to the field of image recognition, in particular to a method and a device for recognizing a safety line.
Background
The safety line on the paper money is a commonly applied traditional technology in the anti-counterfeiting measure of the paper money. In the paper currency circulation link, illegal personnel maliciously make counterfeit money and change and splice the situation sometimes, and the currency counter needs to identify the counterfeit money and carry out interface alarm prompt. Particularly, the region of the safety line on the right side of the 2015 version 100 Yuan RMB is easy to be dug, smeared and pasted, the 2015 version 100 Yuan RMB and the 2005 version 100 Yuan RMB are easy to be spliced and changed, and the like, and the cash counter supports the safety line counterfeit discrimination, is an important aspect of the counterfeit paper money discrimination and has great significance for counterfeit paper money discrimination.
At present, the general method for identifying the safety line of the paper money is to directly carry out image binarization processing on an image containing a safety line area and then calculate the number of connected areas in the area, but the image binarization processing method has two obvious defects:
1. selecting a binarization segmentation threshold, selecting different types of Contact Image Sensors (CIS), calibrating effect difference, new and old difference of paper money, a single fixed binarization threshold and a dynamic threshold defined according to a proportion range, wherein the binarization segmentation effect is easily influenced;
2. under the condition of poor binarization segmentation effect, the calculation index of the connected domain is directly abnormal, and the false alarm of normal bank notes is caused.
These directly result in low recognition rate, which easily causes the problem that the security thread cannot be recognized accurately.
Disclosure of Invention
In view of the above, a method and apparatus for security thread identification is proposed that overcomes or at least partially solves the above mentioned problems.
A method of security thread identification, comprising:
acquiring safety line image coordinate information;
carrying out affine transformation on the safety line coordinate information to obtain the safety line image coordinates after affine transformation;
acquiring and calculating one-dimensional characteristic information of the affine safety line image according to a preset method;
and matching the acquired one-dimensional characteristic information with the one-dimensional characteristic information of the real money, and judging whether the safety line is abnormal or not.
Further, a cross sliding filtering algorithm is adopted for obtaining the safety line coordinate information, and the specific formula is as follows:
and the I, j is coordinate information corresponding to the pixel point of the safety line, and the A (I, j) is a pixel value corresponding to the pixel point with the coordinate of (i, j).
Further, the one-dimensional feature information includes: the number of rising edges and falling edges, the number of level periods, the number of normal periods and the number of abnormal periods.
Further, the rising edge calculation formula is:
(a (i, j) -Ref) + (a (i-1, j) -Ref) + (a (i-2, j) -Ref) + (a (i-3, j) -Ref) < ═ 1 and (a (i +1, j) -Ref) + (a (i +2, j) -Ref) + (a (i +3, j) -Ref) + (a (i +4, j) -Ref) > < 2; wherein, A (i, j) is the pixel value corresponding to the point with the coordinate (i, j), Ref is the reference value corresponding to the binary segmentation, the result (A (i, j) -Ref) is the logical operation result 0 or 1, and the expression meaning of the summation formula is the number of the conditions to be satisfied.
Further, the falling edge calculation formula is:
(a (i, j) -Ref) + (a (i-1, j) -Ref) + (a (i-2, j) -Ref) + (a (i-3, j) -Ref) > (2 and (a (i +1, j) -Ref) + (a (i +2, j) -Ref) + (a (i +3, j) -Ref) + (a (i +4, j) -Ref) < ═ 1, where a (i, j) is the pixel value corresponding to the point whose coordinate is (i, j), Ref is the reference value corresponding to the binarization division, (a (i, j) -Ref) is the logical operation result 0 or 1, and the summation formula expresses the number of conditions that need to be satisfied.
Further, affine transformation is carried out on the safety line coordinate information, and the affine formula is as follows:
the image coordinates (x, y) are transformed into (x ', y') by affine equations.
Further, the method for acquiring the one-dimensional feature information of the affine security line image comprises the following steps: and longitudinally scribing the safety line, transversely collecting by using a preset sampling frequency, and converting the two-dimensional image signal into a one-dimensional signal.
The invention also discloses a safety line identification device, which comprises: an image recognition module, an affine transformation module,
The device comprises a one-dimensional feature conversion and calculation module and a one-dimensional feature judgment module; wherein the content of the first and second substances,
the image identification module is used for acquiring the coordinate information of the safety line;
the affine transformation module is used for carrying out affine transformation on the safety line coordinate information to obtain an affine safety line image;
the one-dimensional characteristic acquisition module is used for acquiring and calculating one-dimensional characteristic information of the security line image after the affine according to a preset method;
and the one-dimensional characteristic judgment module prestores the one-dimensional characteristic information of the real banknote safety line, matches the one-dimensional characteristic information obtained by the one-dimensional characteristic conversion and calculation module with the one-dimensional characteristic information of the real banknote safety line, judges and judges whether the safety line is abnormal or not.
Further, the one-dimensional feature acquisition module comprises a one-dimensional feature conversion module and a one-dimensional feature calculation module;
the one-dimensional characteristic conversion module is used for longitudinally scribing the safety line, transversely collecting the safety line by using a preset sampling frequency and converting the two-dimensional image signal into a one-dimensional signal;
the one-dimensional characteristic calculation module is used for calculating the rising edge information and the falling edge information of the one-dimensional characteristic information according to the rising edge judgment formula and the falling edge judgment formula; and the device is also used for reflecting the channel image according to the distribution characteristics of the safety lines and acquiring the unit period and the period number of the preset height and width.
The invention has the beneficial effects that:
the method converts two-dimensional features of the security thread of the bank note to be detected into a plurality of one-dimensional features, calculates the one-dimensional features of the security thread, matches the calculated one-dimensional features with the one-dimensional features of the security thread of the real bank note, and judges the security thread of the bank note to be detected.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.
The technical solution of the present invention is further described in detail by the accompanying drawings and embodiments.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the principles of the invention and not to limit the invention. In the drawings:
fig. 1 is a flowchart illustrating a method for identifying a security thread according to a first embodiment of the present invention;
fig. 2 is a schematic diagram illustrating a method for converting a two-dimensional signal of a security line into a one-dimensional signal according to a first embodiment of the present invention;
fig. 3 is a 2015 version standard one-dimensional feature image according to a first embodiment of the present invention;
FIG. 4 is a one-dimensional characteristic image of a security thread when the security thread is pasted with a black tape according to a first embodiment of the present invention;
FIG. 5 illustrates a first embodiment of the present invention; when the safety line is smeared with a pencil, the safety line is a one-dimensional characteristic image;
fig. 6 is a structural diagram of a security thread identifying device according to a second embodiment of the present invention.
Detailed Description
Exemplary embodiments of the disclosed invention will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the disclosed invention are shown in the drawings, it should be understood that the disclosed invention can be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosed invention to those skilled in the art.
In order to solve the problem of the prior art, the embodiment of the invention provides a method and a device for identifying a safety line.
Example one
As shown in fig. 1, an embodiment of the present invention discloses a method for identifying a security thread, which is characterized by comprising:
s100, acquiring safety line coordinate information;
specifically, firstly, a safety line image is obtained, and an image recognition module is adopted to obtain the safety line coordinate information. In the process of obtaining the coordinate information of the safety line, certain interference exists in the obtaining of the coordinates by the fine hollow-out image-texts in the safety line area, in the embodiment, cross sliding filtering is selected to filter the interference of the pixel point information of the hollow-out image-texts according to the continuous point distribution characteristic of the hollow-out image-texts, and the effective information retention of the safety line can be ensured;
the cross sliding filter calculation formula is as follows:
wherein i, j is coordinate information corresponding to the pixel point, and A (i, j) is a pixel value (0-255) corresponding to the pixel point with the coordinate (i, j);
s200, carrying out affine transformation on the safety line coordinate information to obtain an affine safety line image;
affine Transformation (or affinity Map) is a linear Transformation from two-dimensional coordinates to two-dimensional coordinates, which maintains the "straightness" (i.e., straight lines remain straight lines after Transformation) and the "parallelism" (i.e., the relative positional relationship between two-dimensional patterns remains unchanged, parallel lines remain parallel lines, and the positional order of points on the straight lines does not change) of two-dimensional patterns. Through affine transformation, rotation, translation and scaling operations can be performed on the image.
Specifically, in this embodiment, in order to make the acquired security line vertical and facilitate the following one-dimensional feature extraction, the affine transformation formula:
from the matrix coordinates, we derive:
x′0＝a00x0+a01y0+a02
y′0＝a10x0+a11y0+a12
x′1＝a00x1+a01y1+a02
y′1＝a10x1+a11y1+a12
x′2＝a00x2+a01y2+a02
y′2＝a10x2+a11y2+a12
obtaining:
the gaussian elimination method is used to obtain the affine transformation parameter a [6] to complete image correction, and it can be understood that affine matrices are different for different affine requirements, which is not limited in this embodiment.
S300, acquiring and calculating one-dimensional characteristic information of the security line image after the affine according to a preset method;
specifically, as shown in fig. 2, the method for acquiring the one-dimensional feature information of the security thread image includes: and longitudinally scribing the safety line, transversely collecting by using a preset sampling frequency, and converting the two-dimensional image signal into a one-dimensional signal. In some preferred embodiments, the width of the current pixel is about 16 pixels, and every other column of samples is 8 pixels according to the security thread pixel width feature. After the safety line is longitudinally and transversely sampled in an interlaced mode, the size of each black block is about 8 x 10. 30 columns are transversely sampled, and one column is sampled every 3 columns, so that at least two sampling columns pass through the safety line area.
In this embodiment, the one-dimensional feature information includes: the number of rising edges and falling edges, the number of level periods, the number of normal periods and the number of abnormal periods.
In this embodiment, the method for acquiring the rising edge and the falling edge of the one-dimensional feature information is as follows:
and (3) arranging and combining the characteristics of the continuous points, and locally analyzing a section of continuous points when the rising edge information and the falling edge information of the one-dimensional characteristic information are calculated. If the position of the rising edge is required, at least three points of the first four points are low, and at least two points of the last four points are high. At the falling edge position, at least two points of the first four points are high, and at least three points of the last four points are low. Interference can be effectively filtered by adopting a permutation and combination characteristic mode, and accurate rising edge and falling edge generation points are obtained;
specifically, the rising edge calculation formula is as follows:
(a (i, j) -Ref) + (a (i-1, j) -Ref) + (a (i-2, j) -Ref) + (a (i-3, j) -Ref) < ═ 1 and (a (i +1, j) -Ref) + (a (i +2, j) -Ref) + (a (i +3, j) -Ref) + (a (i +4, j) -Ref) > < 2;
specifically, the falling edge calculation formula is as follows:
(a (i, j) -Ref) + (a (i-1, j) -Ref) + (a (i-2, j) -Ref) + (a (i-3, j) -Ref) > (2 and (a (i +1, j) -Ref) + (a (i +2, j) -Ref) + (a (i +3, j) -Ref) + (a (i +4, j) -Ref) < ═ 1, where a (i, j) is the pixel value corresponding to the point whose coordinate is (i, j), Ref is the reference value corresponding to the binarization division, (a (i, j) -Ref) is the logical operation result 0 or 1, and the summation formula expresses the number of conditions that need to be satisfied.
The analysis method for obtaining the periodic rule of the one-dimensional characteristic information comprises the following steps:
and reflecting the channel image according to the distribution characteristic of the safety line, and acquiring the unit period and the period number of the preset height and width according to the distribution characteristic of the safety line and the reflected channel image. As shown in fig. 3, the horizontal axis of the coordinate represents the serial number of consecutive points, and the unit period of the preset height and width is 12 and the number of the unit period is 5 according to fig. 3.
S400, matching the acquired one-dimensional characteristic information with standard one-dimensional characteristic information, and judging whether the safety line is abnormal or not.
In this embodiment, the standard one-dimensional feature information may be real banknote one-dimensional feature information, which may be obtained through steps S100 to S300 or may be imported from the outside in advance, and the real banknote one-dimensional feature information is stored in the standard database. Taking 2015 version hundred-yuan bank notes as an example, after the steps of S100-S300, as shown in fig. 3, obtaining 2015 version hundred-yuan bank note one-dimensional feature map, and obtaining 2015 version hundred-yuan bank note one-dimensional feature information rising edge and falling edge numbers, level periods, normal periods and abnormal periods numbers through fig. 3. As shown in fig. 3, specifically, there are 5 windowing security lines for hundreds of dollar banknotes in version 2015, so that there are five peaks in fig. 3 when banknotes are longitudinally acquired. Because the method of acquiring the one-dimensional characteristic information of the security thread image in S300 is adopted, 2 threads cross the security thread, so the upper and lower graphs in fig. 3 respectively represent the one-dimensional characteristic data of the security thread through which two threads pass, and when the upper and lower graphs are completely matched, the security thread is represented by a non-splicing behavior.
It can be understood that there are different standard one-dimensional characteristics for different real banknotes, so that the one-dimensional characteristic data of the real banknotes circulating on the market can be stored in the standard database through the steps S100-S300.
In some embodiments, when the banknote security thread to be tested is black rubberized, the one-dimensional security thread feature is as shown in fig. 4, and when the black rubberized thread is obtained through fig. 4, the one-dimensional security thread feature is stored in the standard one-dimensional feature database.
In some embodiments, when the banknote security thread to be tested is coated with a pencil, the one-dimensional security thread feature is as shown in fig. 5, and when the black rubberized fabric is attached, the one-dimensional security thread feature is obtained through fig. 5 and stored in the standard one-dimensional feature database.
And after the real banknote standard one-dimensional characteristic database is obtained, acquiring the one-dimensional characteristic of the to-be-detected banknote through the S100-S300 method, matching the acquired one-dimensional characteristic information of the to-be-detected banknote with the one-dimensional characteristic information of the real banknote, and judging whether the safety line is abnormal or not.
It can be understood that when the one-dimensional feature data of the to-be-detected banknote is matched with the one-dimensional feature data in fig. 3, the to-be-detected banknote is judged to be a true banknote, otherwise, the to-be-detected banknote is judged to be a false banknote; when the one-dimensional characteristic data of the bank note to be detected is matched with the one-dimensional characteristic data of the graph 4, the bank note to be detected is judged to be a suspicious bank note of which the safety line is pasted with the black adhesive tape; when the one-dimensional characteristic data of the bank note to be detected is matched with the one-dimensional characteristic data of the graph 5, the bank note to be detected is judged to be a suspicious bank note of which the safety line is smeared with a pencil; and when the one-dimensional characteristic data of the two lines passing through the safety line of the bank note to be detected are different, judging that the safety line of the bank note to be detected is spliced by different bank notes. In this embodiment, only the safety line is coated with the black tape and the pencil, and for other situations, the matching principle is the same, and the details are not repeated again.
The method converts two-dimensional features of the security thread of the bank note to be detected into a plurality of one-dimensional features, calculates the one-dimensional features of the security thread, matches the calculated one-dimensional features with the one-dimensional features of the security thread of the real bank note, and judges the security thread of the bank note to be detected.
Example two
The invention also discloses a safety line identification device, which comprises: the system comprises an image identification module, an affine transformation module, a one-dimensional feature acquisition module and a one-dimensional feature judgment module; wherein the content of the first and second substances,
the image identification module is used for acquiring the image coordinate information of the safety line; and the image identification module acquires the safety line coordinate information. In the process of obtaining the coordinate information of the safety line, certain interference exists in the obtaining of the coordinates by the fine hollow-out image-texts in the safety line area, in the embodiment, cross sliding filtering is selected to filter the interference of the pixel point information of the hollow-out image-texts according to the continuous point distribution characteristic of the hollow-out image-texts, and the effective information retention of the safety line can be ensured;
the cross sliding filter calculation formula is as follows:
wherein i, j is coordinate information corresponding to the pixel point, and A (i, j) is a pixel value (0-255) corresponding to the pixel point with the coordinate (i, j);
the affine transformation module is used for carrying out affine transformation on the safety line coordinate information to obtain the safety line image coordinates after the affine transformation; in this embodiment, in order to make the acquired security line vertical and facilitate the subsequent one-dimensional feature extraction, an affine matrix may be used to perform affine matching on the identification image, where a specific affine method is described in the first embodiment and is not described again.
The one-dimensional characteristic acquisition module is used for acquiring and calculating one-dimensional characteristic information of the security line image after the affine according to a preset method;
in some preferred embodiments, the one-dimensional feature acquisition module comprises a one-dimensional feature conversion module and a one-dimensional feature calculation module;
the one-dimensional characteristic conversion module is used for longitudinally scribing the safety line, transversely collecting the safety line by using a preset sampling frequency and converting the two-dimensional image signal into a one-dimensional signal; the specific method is shown in fig. 2, and comprises the following steps: and longitudinally scribing the safety line, transversely collecting by using a preset sampling frequency, and converting the two-dimensional image signal into a one-dimensional signal.
In some preferred embodiments, the security thread is longitudinally and transversely interlaced such that each black block is about 9 x 10mm in size. 30 columns are transversely sampled, and one column is sampled every 3 columns, so that at least two sampling columns pass through the safety line area.
The one-dimensional characteristic calculation module is used for calculating the rising edge information and the falling edge information of the one-dimensional characteristic information according to the rising edge judgment formula and the falling edge judgment formula; and the device is also used for reflecting the channel image according to the distribution characteristics of the safety lines and acquiring the unit period and the period number of the preset height and width.
The method for acquiring the rising edge and the falling edge of the one-dimensional characteristic information comprises the following steps:
and (3) arranging and combining the characteristics of the continuous points, and locally analyzing a section of continuous points when the rising edge information and the falling edge information of the one-dimensional characteristic information are calculated. If the position of the rising edge is required, at least three points of the first four points are low, and at least two points of the last four points are high. At the falling edge position, at least two points of the first four points are high, and at least three points of the last four points are low. Interference can be effectively filtered by adopting a permutation and combination characteristic mode, and accurate rising edge and falling edge generation points are obtained; the specific calculation formulas of the rising edge and the falling edge are described in the first embodiment and are not repeated.
The method for obtaining the unit period and the number of periods of the preset height and width is shown in fig. 3, and in some embodiments, the unit period and the number of periods of the preset height and width can be obtained from fig. 3 as 12 and 5. It will be appreciated that the unit cycle and the number of cycles will be different for different security threads.
And the one-dimensional characteristic judgment module prestores standard safety line one-dimensional characteristic information, matches the one-dimensional characteristic information obtained by the one-dimensional characteristic conversion and calculation module with the real money safety line one-dimensional characteristic information, judges and judges whether the safety line is abnormal or not.
The standard safety line one-dimensional characteristic information can be true banknote one-dimensional characteristic information, the true banknote one-dimensional characteristic information can be obtained through the steps of S100-S300 or can be imported from the outside in advance, and the true banknote one-dimensional characteristic information is stored in a standard database. Taking 2015 version hundred-yuan bank notes as an example, after the steps of S100-S300, as shown in fig. 3, obtaining 2015 version hundred-yuan bank note one-dimensional feature map, and obtaining 2015 version hundred-yuan bank note one-dimensional feature information rising edge and falling edge numbers, level periods, normal periods and abnormal periods numbers through fig. 3. As shown in fig. 3, specifically, there are 5 windowing security lines for hundreds of dollar banknotes in version 2015, so that there are five peaks in fig. 3 when banknotes are longitudinally acquired. Because the method of acquiring the one-dimensional characteristic information of the security thread image in S300 is adopted, 2 threads cross the security thread, so the upper and lower graphs in fig. 3 respectively represent the one-dimensional characteristic data of the security thread through which two threads pass, and when the upper and lower graphs are completely matched, the security thread is represented by a non-splicing behavior.
In some preferred embodiments, the one-dimensional characteristic information of the safety line, such as the safety line is shielded by the black tape and the pencil is pasted, can be used as the standard one-dimensional characteristic information, when the safety line of the banknote to be detected is shielded by the black tape or the pencil is pasted, the one-dimensional characteristic of the banknote to be detected can be identified, the behavior of damaging the safety line by pasting the pencil, pasting the black tape and the like in the area of the safety line is identified, and the banknote is determined to be suspicious.
The method converts two-dimensional features of the security thread of the bank note to be detected into a plurality of one-dimensional features, calculates the one-dimensional features of the security thread, matches the calculated one-dimensional features with the one-dimensional features of the security thread of the real bank note, and judges the security thread of the bank note to be detected.
It should be understood that the specific order or hierarchy of steps in the processes disclosed is an example of exemplary approaches. Based upon design preferences, it is understood that the specific order or hierarchy of steps in the processes may be rearranged without departing from the scope of the disclosed invention. The accompanying method claims present elements of the various steps in a sample order, and are not intended to be limited to the specific order or hierarchy presented.
In the foregoing detailed description, various features are grouped together in a single embodiment for the purpose of streamlining the disclosure. This method of disclosure is not to be interpreted as reflecting an intention that the claimed embodiments of the subject matter require more features than are expressly recited in each claim. Rather, as the following claims reflect, invention lies in less than all features of a single disclosed embodiment. Thus, the following claims are hereby expressly incorporated into the detailed description, with each claim standing on its own as a separate preferred embodiment of the invention.
Those of skill would further appreciate that the various illustrative logical blocks, modules, circuits, and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both. To clearly illustrate this interchangeability of hardware and software, various illustrative components, blocks, modules, circuits, and steps have been described above generally in terms of their functionality. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the overall system. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the disclosed invention.
The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied directly in hardware, in a software module executed by a processor, or in a combination of the two. A software module may reside in RAM memory, flash memory, ROM memory, EPROM memory, EEPROM memory, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art. An exemplary storage medium is coupled to the processor such the processor can read information from, and write information to, the storage medium. Of course, the storage medium may also be integral to the processor. The processor and the storage medium may reside in an ASIC. The ASIC may reside in a user terminal. Of course, the processor and the storage medium may reside as discrete components in a user terminal.
For a software implementation, the techniques described herein may be implemented with modules (e.g., procedures, functions, and so on) that perform the functions described herein. The software codes may be stored in memory units and executed by processors. The memory unit may be implemented within the processor or external to the processor, in which case it can be communicatively coupled to the processor via various means as is known in the art.
What has been described above includes examples of one or more embodiments. It is, of course, not possible to describe every conceivable combination of components or methodologies for purposes of describing the aforementioned embodiments, but one of ordinary skill in the art may recognize that many further combinations and permutations of various embodiments are possible. Accordingly, the embodiments described herein are intended to embrace all such alterations, modifications and variations that fall within the scope of the appended claims. Furthermore, to the extent that the term "includes" is used in either the detailed description or the claims, such term is intended to be inclusive in a manner similar to the term "comprising" as "comprising" is interpreted when employed as a transitional word in a claim. Furthermore, any use of the term "or" in the specification of the claims is intended to mean a "non-exclusive or".
Claims (5)
1. A method of identifying a security thread, comprising:
s100, acquiring safety line image coordinate information; the method for acquiring the coordinate information of the safety line image adopts a cross sliding filtering algorithm, and the specific formula is as follows:
wherein i and j are coordinate information corresponding to the pixel points of the safety line, and A (i, j) is a pixel value corresponding to the pixel point with the coordinate of (i, j);
s200, carrying out affine transformation on the safety line image coordinate information to obtain the safety line image coordinate after affine transformation;
s300, acquiring and calculating one-dimensional characteristic information of the security line image after the affine according to a preset method; the method for acquiring the one-dimensional characteristic information of the security line image after the affine comprises the following steps: longitudinally scribing the safety line, transversely collecting by using a preset sampling frequency, and converting an image two-dimensional signal into a one-dimensional signal; the one-dimensional feature information includes: the number of rising edges and falling edges, the number of level periods, normal periods and abnormal periods; the rising edge decision formula is:
(A (i, j) -Ref) + (A (i-1, j) -Ref) + (A (i-2, j) -Ref) + (A (i-3, j) -Ref) ≦ 1 and (A (i +1, j) -Ref) + (A (i +2, j) -Ref) + (A (i +3, j) -Ref) + (A (i +4, j) -Ref) ≧ 2;
wherein, A (i, j) is a pixel value corresponding to a point with coordinates (i, j), Ref is a reference value corresponding to binarization segmentation, and the result (A (i, j) -Ref) is a logic operation result 0 or 1, and the expression meaning of a summation formula is the number of conditions to be met; the falling edge decision formula is:
(A (i, j) -Ref) + (A (i-1, j) -Ref) + (A (i-2, j) -Ref) + (A (i-3, j) -Ref) ≥ 2 and (A (i +1, j) -Ref) + (A (i +2, j) -Ref) + (A (i +3, j) -Ref) + (A (i +4, j) -Ref) ≤ 1; wherein, A (i, j) is a pixel value corresponding to a point with coordinates (i, j), Ref is a reference value corresponding to binarization segmentation, and the result (A (i, j) -Ref) is a logic operation result 0 or 1, and the expression meaning of a summation formula is the number of conditions to be met;
s400, the calculated one-dimensional characteristic information is matched with the standard safety line one-dimensional characteristic information, and whether the safety line is abnormal or not is judged.
2. A security thread identifying method as claimed in claim 1, wherein the standard security thread one-dimensional characteristic information can be obtained through steps S100 to S300 or can be pre-imported from the outside.
3. A security thread identification method according to claim 1, wherein affine transformation is performed on said security thread coordinate information, the affine formula being:
the image coordinates are affine-transformed from (x, y) to (x ', y') by an affine formula.
4. A security thread identification device, comprising: the system comprises an image identification module, an affine transformation module, a one-dimensional feature acquisition module and a one-dimensional feature judgment module; wherein the content of the first and second substances,
the image identification module is used for acquiring the image coordinate information of the safety line; the method for acquiring the coordinate information of the safety line image adopts a cross sliding filtering algorithm, and the specific formula is as follows:
wherein i and j are coordinate information corresponding to the pixel points of the safety line, and A (i, j) is a pixel value corresponding to the pixel point with the coordinate of (i, j);
the affine transformation module is used for carrying out affine transformation on the safety line coordinate information to obtain the safety line image coordinates after the affine transformation;
the one-dimensional characteristic acquisition module is used for acquiring and calculating one-dimensional characteristic information of the security line image after the affine according to a preset method; the method for acquiring the one-dimensional characteristic information of the security line image after the affine comprises the following steps: longitudinally scribing the safety line, transversely collecting by using a preset sampling frequency, and converting an image two-dimensional signal into a one-dimensional signal; the one-dimensional feature information includes: the number of rising edges and falling edges, the number of level periods, normal periods and abnormal periods; the rising edge decision formula is:
(A (i, j) -Ref) + (A (i-1, j) -Ref) + (A (i-2, j) -Ref) + (A (i-3, j) -Ref) ≦ 1 and (A (i +1, j) -Ref) + (A (i +2, j) -Ref) + (A (i +3, j) -Ref) + (A (i +4, j) -Ref) ≧ 2;
wherein, A (i, j) is a pixel value corresponding to a point with coordinates (i, j), Ref is a reference value corresponding to binarization segmentation, and the result (A (i, j) -Ref) is a logic operation result 0 or 1, and the expression meaning of a summation formula is the number of conditions to be met; the falling edge decision formula is:
(A (i, j) -Ref) + (A (i-1, j) -Ref) + (A (i-2, j) -Ref) + (A (i-3, j) -Ref) ≥ 2 and (A (i +1, j) -Ref) + (A (i +2, j) -Ref) + (A (i +3, j) -Ref) + (A (i +4, j) -Ref) ≤ 1; wherein, A (i, j) is a pixel value corresponding to a point with coordinates (i, j), Ref is a reference value corresponding to binarization segmentation, and the result (A (i, j) -Ref) is a logic operation result 0 or 1, and the expression meaning of a summation formula is the number of conditions to be met;
and the one-dimensional characteristic judgment module prestores standard safety line one-dimensional characteristic information, matches the one-dimensional characteristic information obtained by the one-dimensional characteristic conversion and calculation module with the real money safety line one-dimensional characteristic information and judges whether the safety line is abnormal or not.
5. The apparatus according to claim 4, wherein the one-dimensional feature obtaining module comprises a one-dimensional feature conversion module and a one-dimensional feature calculation module;
the one-dimensional characteristic conversion module is used for longitudinally scribing the safety line, transversely collecting the safety line by using a preset sampling frequency and converting the two-dimensional image signal into a one-dimensional signal;
the one-dimensional characteristic calculation module is used for calculating the rising edge information and the falling edge information of the one-dimensional characteristic information according to the rising edge judgment formula and the falling edge judgment formula; and the device is also used for reflecting the channel image according to the distribution characteristics of the safety lines and acquiring the unit period and the period number of the preset height and width.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010011798.5A CN110956737B (en) | 2020-01-07 | 2020-01-07 | Safety line identification method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010011798.5A CN110956737B (en) | 2020-01-07 | 2020-01-07 | Safety line identification method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110956737A CN110956737A (en) | 2020-04-03 |
| CN110956737B true CN110956737B (en) | 2021-10-12 |
Family
ID=69985812
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010011798.5A Active CN110956737B (en) | 2020-01-07 | 2020-01-07 | Safety line identification method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110956737B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111612965B (en) * | 2020-05-19 | 2022-04-01 | 武汉卓目科技有限公司 | Method, apparatus and device for denomination recognition using security thread magnetic encoding |
| CN111627145B (en) * | 2020-05-19 | 2022-06-21 | 武汉卓目科技有限公司 | Method and device for identifying fine hollow image-text of image |
| CN111738079A (en) * | 2020-05-19 | 2020-10-02 | 武汉卓目科技有限公司 | Banknote denomination recognition method and device |
| CN111915792B (en) * | 2020-05-19 | 2022-06-07 | 武汉卓目科技有限公司 | Method and device for identifying zebra crossing image-text |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102096962A (en) * | 2010-12-23 | 2011-06-15 | 北京新岸线软件科技有限公司 | Paper currency detecting method and device |
| CN102509383A (en) * | 2011-11-28 | 2012-06-20 | 哈尔滨工业大学深圳研究生院 | Feature detection and template matching-based mixed number identification method |
| CN102956025A (en) * | 2011-08-26 | 2013-03-06 | 北京中盈信安科技发展有限责任公司 | Image watermark detection method and system |
| CN105184955A (en) * | 2015-08-18 | 2015-12-23 | 深圳怡化电脑股份有限公司 | Method and device for identifying paper money |
| CN105590301A (en) * | 2016-01-28 | 2016-05-18 | 河南师范大学 | Impulse noise elimination method of self-adaption normal-inclined double cross window mean filtering |
| CN106355744A (en) * | 2016-08-24 | 2017-01-25 | 深圳怡化电脑股份有限公司 | Image identification method and device |
| CN106408746A (en) * | 2016-08-25 | 2017-02-15 | 深圳怡化电脑股份有限公司 | Safety thread identification method and apparatus |
| CN106710062A (en) * | 2016-12-12 | 2017-05-24 | 深圳怡化电脑股份有限公司 | Banknote security line detecting method and device |
| CN108335402A (en) * | 2017-01-18 | 2018-07-27 | 武汉卓目科技有限公司 | A kind of cash inspecting machine infrared tube false distinguishing method based on deep learning |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1691539A1 (en) * | 2005-02-15 | 2006-08-16 | European Central Bank | Two-dimensional security pattern that can be authenticated with one-dimensional signal processing |
| ATE537524T1 (en) * | 2007-05-17 | 2011-12-15 | Nidec Sankyo Corp | METHOD AND DEVICE FOR MAGNETIC CHARACTER RECOGNITION |
| CN107133922A (en) * | 2016-02-29 | 2017-09-05 | 孙智权 | A kind of silicon chip method of counting based on machine vision and image procossing |
-
2020
- 2020-01-07 CN CN202010011798.5A patent/CN110956737B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102096962A (en) * | 2010-12-23 | 2011-06-15 | 北京新岸线软件科技有限公司 | Paper currency detecting method and device |
| CN102956025A (en) * | 2011-08-26 | 2013-03-06 | 北京中盈信安科技发展有限责任公司 | Image watermark detection method and system |
| CN102509383A (en) * | 2011-11-28 | 2012-06-20 | 哈尔滨工业大学深圳研究生院 | Feature detection and template matching-based mixed number identification method |
| CN105184955A (en) * | 2015-08-18 | 2015-12-23 | 深圳怡化电脑股份有限公司 | Method and device for identifying paper money |
| CN105590301A (en) * | 2016-01-28 | 2016-05-18 | 河南师范大学 | Impulse noise elimination method of self-adaption normal-inclined double cross window mean filtering |
| CN106355744A (en) * | 2016-08-24 | 2017-01-25 | 深圳怡化电脑股份有限公司 | Image identification method and device |
| CN106408746A (en) * | 2016-08-25 | 2017-02-15 | 深圳怡化电脑股份有限公司 | Safety thread identification method and apparatus |
| CN106710062A (en) * | 2016-12-12 | 2017-05-24 | 深圳怡化电脑股份有限公司 | Banknote security line detecting method and device |
| CN108335402A (en) * | 2017-01-18 | 2018-07-27 | 武汉卓目科技有限公司 | A kind of cash inspecting machine infrared tube false distinguishing method based on deep learning |
Non-Patent Citations (1)
| Title |
|---|
| 2015版新版人民币图像特征的鉴伪研究;罗帅;《中国优秀硕士学位论文》;20170731;第1-54页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110956737A (en) | 2020-04-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110956737B (en) | Safety line identification method and device | |
| EP3089103B1 (en) | Method for correcting fragmentary or deformed quadrangular image | |
| CN105046807B (en) | A kind of counterfeit money recognition methods and system based on smart mobile phone | |
| CN107180479B (en) | Bill identification method, device, equipment and storage medium | |
| CN114549981A (en) | Intelligent inspection pointer type instrument recognition and reading method based on deep learning | |
| WO2018082540A1 (en) | Bank note one-dimensional signal detection method and device | |
| WO2015032187A1 (en) | Banknote processing method and device | |
| KR102007685B1 (en) | Hybrid counterfeit discrimination apparatus, and system thereof | |
| CN106934921B (en) | Method and device for detecting sticking of paper foreign matter | |
| CN104966349A (en) | ATM platform-based method of detecting new bank note and old bank note | |
| KR101001691B1 (en) | Recognizing the Denomination of a Note Using Wavelet transform | |
| CN103413375A (en) | Discrimination system and method of old and new paper currency based on image statistical features | |
| CN106599923B (en) | Method and device for detecting seal anti-counterfeiting features | |
| CN107742357A (en) | A kind of recognition methods of paper money number and device | |
| CN108711213B (en) | Method and device for identifying black and white blocks of paper money zebra stripes | |
| CN106934922A (en) | A kind of paper currency detecting method and device | |
| CN105957237A (en) | Method and device for identifying version of banknote | |
| CN109543554B (en) | Bill detection method, device, terminal and computer readable storage medium | |
| CN111915792B (en) | Method and device for identifying zebra crossing image-text | |
| CN114663899A (en) | Financial bill processing method, device, equipment and medium | |
| CN109410420B (en) | Image detection method and device and bill discriminator | |
| CN113256873B (en) | Abnormality detection method and device for paper money, electronic equipment and machine storage medium | |
| CN108320371B (en) | Method and device for identifying counterfeit paper money | |
| CN108154596B (en) | Double-crown-number paper currency discrimination method based on image matching | |
| CN110867015A (en) | RMB counterfeit discriminating 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |