CN106952393B - Paper money identification method and device, electronic equipment and storage medium - Google Patents
Paper money identification method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN106952393B CN106952393B CN201710191949.8A CN201710191949A CN106952393B CN 106952393 B CN106952393 B CN 106952393B CN 201710191949 A CN201710191949 A CN 201710191949A CN 106952393 B CN106952393 B CN 106952393B
- Authority
- CN
- China
- Prior art keywords
- matching
- image
- gray level
- gray
- preset
- 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
- G07D7/20—Testing patterns thereon
- G07D7/202—Testing patterns thereon using pattern matching
- G07D7/2041—Matching statistical distributions, e.g. of particle sizes orientations
Abstract
The embodiment of the invention discloses a paper money identification method and device, electronic equipment and a storage medium. The method comprises the following steps: acquiring a gray image corresponding to a preset characteristic region in an image of the paper money to be detected; acquiring a statistical feature vector of the gray level image, and matching the statistical feature vector with a statistical feature vector template according to a first preset matching rule to acquire a first matching result; if the first matching result is that the paper money to be detected is a true paper money, acquiring a gray level average template of the gray level image, and matching the gray level image and the gray level average template according to a second preset matching rule to acquire a second matching result; and determining the authenticity of the paper money to be detected according to the second matching result. The technical scheme of the embodiment of the invention solves the technical defects that the single paper currency counterfeit distinguishing method in the prior art cannot simultaneously meet the requirements of high calculation speed, easy realization and high counterfeit distinguishing accuracy, and realizes the single paper currency counterfeit distinguishing process with rapidness, simplicity, convenience and high accuracy.
Description
Technical Field
The embodiment of the invention relates to the technical field of paper currency identification, in particular to a paper currency identification method and device, electronic equipment and a storage medium.
Background
Along with the development of economy, the circulation of paper money is larger and larger, and intelligent unmanned charging systems based on paper money recognition technology appear in many industries. For example, the banknote recognition technology can be applied not only to vending and ticketing, but also to a system such as an automated teller machine in a bank or an automated teller machine in a business office. Meanwhile, the invention of the cash register also provides convenience for various industries. The application of the paper money recognition device saves a large amount of human resources and greatly improves the working efficiency.
The existing paper money counterfeit distinguishing methods are various, common counterfeit distinguishing methods comprise a template matching method, a gray histogram method, an edge image method and the like, and the counterfeit distinguishing methods are long in application difficulty, calculation speed, accuracy and the like.
Although the existing paper money counterfeit distinguishing methods are various, basically, no paper money counterfeit distinguishing method can simultaneously meet the requirements of easy realization, high calculation speed and high accuracy.
Disclosure of Invention
In view of this, embodiments of the present invention provide a method and an apparatus for identifying a banknote, an electronic device, and a storage medium, so as to solve the technical defects that a single banknote authentication method in the prior art cannot simultaneously satisfy the requirements of fast calculation speed, easy implementation, and high authentication accuracy.
In a first aspect, an embodiment of the present invention provides a banknote recognition method, including:
acquiring a gray image corresponding to a preset characteristic region in an image of a paper money to be detected, wherein the preset characteristic region comprises an optical characteristic region of the paper money to be detected;
acquiring a statistical feature vector of the gray level image, and matching the statistical feature vector with a statistical feature vector template according to a first preset matching rule to acquire a first matching result;
if the first matching result is that the paper money to be detected is a true paper money, acquiring a gray level average template of the gray level image, and matching the gray level image and the gray level average template according to a second preset matching rule to acquire a second matching result;
and determining the authenticity of the paper money to be detected according to the second matching result.
In the foregoing method, preferably, the obtaining the statistical feature vector of the grayscale image, and matching the statistical feature vector with a statistical feature vector template according to a first preset matching rule to obtain a first matching result includes:
and acquiring a statistical vector of the histogram of the gray level image, and matching the statistical vector of the histogram with the histogram statistical vector template according to a first preset matching rule to acquire a first matching result.
In the above method, preferably, the obtaining a statistical vector of a histogram of the grayscale image includes:
acquiring a histogram of the gray level image;
and taking the longitudinal coordinate values corresponding to the gray value intervals from small to large in the histogram as statistical vectors of the histogram.
In the foregoing method, preferably, the obtaining the statistical feature vector of the grayscale image, and matching the statistical feature vector with a statistical feature vector template according to a first preset matching rule to obtain a first matching result includes:
and acquiring a statistical vector of a block image of the gray level image, and matching the statistical vector of the block image with a block image statistical vector template according to a first preset matching rule to acquire a first matching result.
In the above method, preferably, the obtaining a statistical vector of the block image of the grayscale image includes:
dividing the gray level image according to rows and columns to obtain each block image;
and acquiring the gray value mean value and the gray value variance of each block image to form a statistical vector of the block images.
In the above method, preferably, the acquiring a grayscale mean template of the grayscale image includes:
acquiring a first gray image corresponding to a preset characteristic area in images of true banknotes of a preset number of banknotes to be detected;
and acquiring the gray mean value images corresponding to the preset number of first gray images, and taking the gray mean value images as the gray mean value template.
In the foregoing method, preferably, the matching the grayscale image and the grayscale mean template according to a second preset matching rule includes:
reducing the gray level image and the gray level average value template according to a preset proportion;
matching the reduced gray level image with the gray level mean value template according to a template matching method, and recording a matching degree value;
taking a matching position corresponding to the maximum value in the matching degree values as a first reference position, and acquiring a second reference position corresponding to the first reference position in the gray level image;
and intercepting the gray level image to be matched corresponding to the second reference position according to a preset corresponding rule, and matching the gray level image to be matched with the gray level mean value template according to the template matching method.
In the above method, before the determining the authenticity of the banknote to be tested according to the second matching result, the method preferably further includes:
acquiring a gray mean value statistical vector of a first block image of the gray image, inputting the gray mean value statistical vector into a preset neural network, and taking an output result of the preset neural network as a third matching result;
and determining the authenticity of the paper money to be detected according to the second matching result, comprising the following steps:
and determining the authenticity of the paper money to be detected according to the second matching result and the third matching result.
In the above method, preferably, the determining whether the banknote to be tested is true or false according to the second matching result and the third matching result includes:
and if any one of the second matching result and the third matching result is that the paper money to be detected is a true paper money, determining that the paper money to be detected is a true paper money.
In a second aspect, an embodiment of the present invention provides a banknote recognition apparatus, including:
the device comprises a gray level image acquisition module, a characteristic analysis module and a characteristic analysis module, wherein the gray level image acquisition module is used for acquiring a gray level image corresponding to a preset characteristic region in an image of the paper money to be detected, and the preset characteristic region comprises an optical characteristic region of the paper money to be detected;
the first matching result acquisition module is used for acquiring the statistical feature vector of the gray level image, and matching the statistical feature vector with the statistical feature vector template according to a first preset matching rule to acquire a first matching result;
the second matching result acquisition module is used for acquiring a gray level average template of the gray level image if the first matching result is that the paper money to be detected is a true paper money, matching the gray level image and the gray level average template according to a second preset matching rule, and acquiring and recording a second matching result;
and the paper currency authenticity determining module is used for determining the authenticity of the paper currency to be detected according to the second matching result.
In a third aspect, an embodiment of the present invention provides an electronic device, including:
one or more processors;
a memory for storing one or more programs,
when the one or more programs are executed by the one or more processors, the one or more processors implement the banknote recognition method according to the embodiment of the present invention.
In a fourth aspect, embodiments of the present invention provide a storage medium containing computer-executable instructions that, when executed by a computer processor, are configured to perform a banknote recognition method according to embodiments of the present invention.
The embodiment of the invention provides a paper money identification method and a device, which are characterized in that a gray image corresponding to a preset characteristic region in an image of paper money to be detected and a statistical characteristic vector thereof are obtained, the statistical characteristic vector is matched with a statistical characteristic vector template according to a first preset matching rule, a first matching result is obtained, if the first matching result is that the paper money to be detected is a true paper money, a gray mean template of the gray image is continuously obtained, the gray image and the gray mean template are matched according to a second preset matching rule, a second matching result is obtained, and the authenticity of the paper money to be detected is determined according to the second matching result.
Drawings
FIG. 1 is a flow chart of a banknote recognition method according to an embodiment of the present invention;
FIG. 2 is a flow chart of a banknote recognition method according to a second embodiment of the present invention;
FIG. 3 is a flow chart of a banknote recognition method according to a third embodiment of the present invention;
fig. 4 is a structural view of a paper money discriminating apparatus according to a fourth embodiment of the present invention;
fig. 5 is a structural diagram of an electronic device in the fifth embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, embodiments of the present invention are described in further detail below with reference to the accompanying drawings. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting of the invention.
It should be further noted that, for the convenience of description, only some but not all of the relevant aspects of the present invention are shown in the drawings. Before discussing exemplary embodiments in more detail, it should be noted that some exemplary embodiments are described as processes or methods depicted as flowcharts. Although a flowchart may describe the operations (or steps) as a sequential process, many of the operations can be performed in parallel, concurrently or simultaneously. In addition, the order of the operations may be re-arranged. The process may be terminated when its operations are completed, but may have additional steps not included in the figure. The processes may correspond to methods, functions, procedures, subroutines, and the like.
Example one
Fig. 1 is a flowchart of a banknote recognition method according to an embodiment of the present invention, where the method of this embodiment may be implemented by a banknote recognition apparatus, which may be implemented by hardware and/or software, and may be generally integrated into an apparatus having a banknote counterfeit detection function, such as a banknote detector, an automatic teller machine, and a vending machine. The method of the embodiment specifically includes:
step 101, obtaining a gray image corresponding to a preset characteristic area in an image of the paper money to be detected.
Generally, in the anti-counterfeit detection of paper money, infrared or ultraviolet light is firstly used to irradiate the paper money, so as to obtain a gray image of the paper money, and then the authenticity of the paper money is identified through calculation processing of the obtained gray image or a binary image, a histogram or an edge image generated by the obtained gray image. In this embodiment, the method for obtaining the gray image of the banknote to be detected may also be that the infrared or ultraviolet light is used to irradiate the banknote to be detected, so as to obtain the gray image of the banknote to be detected.
In this embodiment, the preset feature area specifically refers to an optical characteristic area of the banknote to be detected, where gray-scale images obtained by the area under different invisible light (e.g., ultraviolet light or infrared light) are different. As will be understood by those skilled in the art, since the characteristics of the inks used in the respective regions of the banknote are different, the transmittance and reflectance of the inks with different characteristics to the same light source are different, and the transmittance and reflectance of the same ink to different light sources are also different, the gray scale patterns obtained by using different light sources or using the same light source but using different receiving modes (such as transmission or reflection) for the same banknote are different, and based on this phenomenon, the region with the ink characteristics different from other regions can be preferably used as the preset feature region in this embodiment.
Illustratively, the white watermark and the optically variable 100 characters at the lower left corner of the front face of the RMB can be displayed in the infrared transmission diagram of the RMB, so that the white watermark and the optically variable 100 characters can be selected as the preset characteristic region.
Since the sizes of the banknotes of different currencies are different and the positions of the preset feature areas of the banknotes of different currencies or different denominations in the banknotes are also different, this embodiment is performed on the premise that the denomination, the orientation (for example, the front direction, the reverse direction, and the reverse direction, etc.) of the banknote to be tested and the position of the preset feature areas in the banknote to be tested (generally, the position of the preset feature areas in the banknote to be tested when the front direction or the reverse direction of the banknote is forward) are known, wherein the denomination, and the orientation of the banknote to be tested can be determined by the obtained gray level image of the banknote to be tested.
In this embodiment, after the gray image of the banknote to be detected is obtained, according to the currency, the face value and the orientation of the known banknote to be detected and the position of the preset feature region in the banknote to be detected, the specific position of the gray image of the preset feature region in the gray image of the banknote to be detected can be determined and intercepted in combination with the resolution of the image acquisition device, and this method belongs to the prior art and will not be described in detail here.
102, obtaining a statistical feature vector of the gray level image, and matching the statistical feature vector with a statistical feature vector template according to a first preset matching rule to obtain a first matching result.
In this embodiment, the statistical features of the grayscale image may specifically be a mean value of grayscale values, histogram statistical data, a median value of grayscale values, a variance of grayscale values, and the like of the grayscale image, and since these statistical features can well reflect the grayscale characteristics of the grayscale image itself, they can be compared with other grayscale images as distinguishing features.
For example, the number of pixel points in each gray scale interval in the histogram corresponding to the gray scale image may be used as the statistical feature of the gray scale image, the gray scale image may be partitioned, the gray scale median, the gray scale variance, or the gray scale mean of each small block image may be used as the statistical feature of the gray scale image, the number of edge points included in a plurality of specific regions in the edge detection image corresponding to the gray scale image may be used as the statistical feature of the gray scale image, and the number of pixel points having a gray scale value of 0 or 1 included in a plurality of specific regions in the binarized image corresponding to the gray scale image may be used as the statistical feature of the gray scale image.
In this embodiment, the statistical feature vector specifically refers to a vector formed by statistical features of the grayscale image according to a certain arrangement rule.
For example, the number of pixels in each gray scale interval from small to large in a histogram corresponding to the gray scale image may be used as a statistical feature vector of the gray scale image, and the gray scale image may be partitioned, and a gray scale variance or a gray scale mean of each small image from left to right and from top to bottom or on any diagonal line may be used as the statistical feature vector of the gray scale image.
In this embodiment, the first preset matching rule specifically refers to a vector similarity calculation method, which may be typically a cosine angle method or a correlation coefficient method, and different matching rules may be selected for different statistical characteristics, so that the matching result is more accurate. In addition, since the smaller brightness difference of the same gray image does not have a large influence on the calculation results of the correlation coefficient method and the cosine clip angle method, when the two methods are used for matching, the influence on the brightness of the gray image of the paper money to be detected due to the different gray image acquisition environments can be effectively avoided, so in the embodiment, the cosine clip angle method and the correlation coefficient method are preferentially selected by the first preset matching rule.
In this embodiment, after the statistical feature vector is matched with the statistical feature vector template according to the first preset matching rule, a specific matching degree data is obtained, where the data indicates the matching degree between the statistical feature vector and the statistical feature vector template, the matching degree data may be compared with a preset threshold, and then the authenticity of the paper money to be tested is determined according to the comparison result. The first matching result may specifically be that the paper money to be detected is a genuine money, or the paper money to be detected is a counterfeit money.
And 103, if the first matching result is that the paper money to be detected is a true paper money, acquiring a gray level average template of the gray level image, and matching the gray level image and the gray level average template according to a second preset matching rule to acquire a second matching result.
In this embodiment, the grayscale mean template of the grayscale image specifically refers to a grayscale mean image corresponding to the grayscale image in the preset feature region in the image of the true banknote of the several to-be-detected banknotes, and since the additive noise mean is zero, the grayscale mean image is used as the template, so that the influence of noise on the accuracy of the template can be reduced.
In this embodiment, the second preset matching rule may specifically be that the moving distance of the grayscale mean template on the grayscale image is 10 or 15 pixels each time, and after the matching position with the highest matching degree is located, conventional template matching is performed around the matching position, or methods such as performing conventional template matching on the grayscale image and the grayscale mean template after being reduced according to a certain proportion, after the matching position with the highest matching degree is located, determining an image region corresponding to the matching position in the grayscale image, and performing conventional template matching on the image region and the grayscale mean template, and the like, which are not limited in this embodiment.
The conventional template matching specifically means that the template moves on an image to be detected in a horizontal and longitudinal sequence, the moving distance is one pixel point every time, and the overall matching of the image is performed once every time the template moves, so that the conventional template matching method is large in calculation amount and low in banknote false distinguishing speed, and therefore in the embodiment, the second preset matching rule does not directly match the grayscale image with the grayscale mean template according to the conventional template matching method.
Further, in this embodiment, in the conventional template matching, an algorithm used when the grayscale mean template is matched with the grayscale image at the current position may specifically be a cosine distance method, or may also be an algorithm such as a correlation coefficient method, which is not limited in this embodiment.
In this embodiment, if the first matching result is that the paper money to be tested is counterfeit paper money, it may be specifically determined that the paper money to be tested is counterfeit paper money according to the first matching result, the paper money identification process is ended, and the paper money identification method different from that in step 102 may be further used to identify the authenticity of the paper money to be tested, which is not limited in this embodiment.
And 104, determining the authenticity of the paper money to be detected according to the second matching result.
In this embodiment, the second matching result may specifically be that the banknote to be detected is a genuine banknote, or the banknote to be detected is a counterfeit banknote. When the second matching result is that the paper money to be detected is true money, determining that the paper money to be detected is true money; and when the second matching result is that the paper money to be detected is counterfeit money, determining that the paper money to be detected is counterfeit money.
The embodiment of the invention provides a paper currency identification method, which comprises the steps of obtaining a gray level image and a statistical characteristic vector of a corresponding preset characteristic region in an image of paper currency to be detected, matching the statistical characteristic vector with a statistical characteristic vector template according to a first preset matching rule and obtaining a first matching result, if the first matching result is that the paper currency to be detected is a true paper currency, continuously obtaining a gray level average template of the gray level image, matching the gray level image with the gray level average template according to a second preset matching rule and obtaining a second matching result, and determining the authenticity of the paper currency to be detected according to the second matching result, so that the technical defects that a single paper currency counterfeit identification method in the prior art cannot simultaneously meet the requirements of high calculation speed, easiness in realization and high counterfeit identification accuracy are overcome, and counterfeit notes with low simulation degree can be quickly identified by comparing the statistical characteristics of the gray level image firstly, and then, the counterfeit money with high simulation degree is identified by using an image matching method with high accuracy, so that the single paper money identification process with high speed, convenience and accuracy is realized.
Example two
Fig. 2 is a flowchart of a banknote recognition method according to a second embodiment of the present invention. In this embodiment, a statistical feature vector of a gray-scale image is obtained, the statistical feature vector is matched with a statistical feature vector template according to a first preset matching rule, and a first matching result is obtained, where the optimization is as follows: and acquiring a statistical vector of a histogram of the gray level image, and matching the statistical vector of the histogram with a histogram statistical vector template according to a first preset matching rule to acquire a first matching result.
Further, the statistical vector of the histogram of the acquired gray level image is optimized as follows: acquiring a histogram of a gray level image; and taking the vertical coordinate values corresponding to the gray value intervals from small to large in the histogram as statistical vectors of the histogram.
Further, the gray average template for obtaining the gray image is optimized as follows: acquiring a first gray image corresponding to a preset characteristic area in an image of true banknotes of a preset number of banknotes to be detected; and acquiring gray mean value images corresponding to the first gray images in a preset number, and taking the gray mean value images as gray mean value templates.
Further, matching the gray level image and the gray level mean value template according to a second preset matching rule, and optimizing as follows: reducing the gray level image and the gray level average value template according to a preset proportion; matching the reduced gray level image with the gray level mean value template according to a template matching method, and recording a matching degree value; taking the matching position corresponding to the maximum value in the matching degree numerical value as a first reference position, and acquiring a second reference position corresponding to the first reference position in the gray level image; and intercepting the gray level image to be matched corresponding to the second reference position according to a preset corresponding rule, and matching the gray level image to be matched with the gray level mean value template according to a template matching method.
Correspondingly, the method of the embodiment specifically includes:
step 201, obtaining a gray image corresponding to a preset characteristic area in an image of the paper money to be detected.
Step 202, obtaining a histogram of the gray level image, and taking a vertical coordinate value corresponding to each gray level interval from small to large in the histogram as a statistical vector of the histogram.
In the present embodiment, steps S202 to S203 give a preferable way of obtaining the first matching result.
In this embodiment, the gray scale interval division rule of the histogram of the gray scale image should be consistent with the gray scale interval division rule corresponding to the histogram statistic vector template. After a histogram of a gray image is obtained, longitudinal coordinate values corresponding to gray value intervals from small to large in the histogram are sequentially obtained to form a statistical vector of the histogram, wherein the composition mode of the statistical vector of the histogram is consistent with that of a histogram statistical vector template, and if the composition mode of the histogram statistical vector template is formed by the longitudinal coordinate values corresponding to the gray value intervals from large to small or the longitudinal coordinate values corresponding to certain specific gray value intervals, the composition mode of the statistical vector of the histogram should be changed to be formed by the longitudinal coordinate values corresponding to the gray value intervals from large to small or the longitudinal coordinate values corresponding to certain specific gray value intervals of the histogram.
And 203, matching the statistical vector of the histogram with the statistical vector template of the histogram according to a first preset matching rule to obtain a first matching result.
In this embodiment, the histogram statistical vector and the histogram statistical vector template may be specifically matched according to a vector similarity calculation method such as a cosine distance method or a correlation coefficient method, and after matching, matching degree data is obtained, and the matching degree data may be compared with a preset threshold value to obtain a first matching result.
And 204, judging whether the paper money to be detected is true paper money or not according to the first matching result, if so, executing the step 205, and if not, ending the step.
And step 205, acquiring a first gray image corresponding to a preset characteristic area in the image of the true banknotes of the paper money to be detected with the preset number.
In this embodiment, steps S205 to S206 provide a preferred way to obtain the gray-scale mean template.
In the present embodiment, the preset number may typically be 100 or 200, etc. The process and method for obtaining the first gray scale image are consistent with the process and method for obtaining the gray scale image corresponding to the preset characteristic region in the image of the paper money to be detected, and detailed description is omitted here.
And step 206, acquiring the gray average value images corresponding to the preset number of first gray images, and taking the gray average value images as gray average value templates.
In this embodiment, the gray-scale average image specifically refers to an image formed by averaging gray-scale values of pixels at the same positions of a preset number of first gray-scale images and calculating the average value of the gray-scale values according to the positions of the original pixels.
And step 207, reducing the gray level image and the gray level average template according to a preset proportion, matching the reduced gray level image and the gray level average template according to a template matching method, and recording a matching degree value.
In this embodiment, steps 270 to 290 show a specific process of matching the grayscale image and the grayscale mean template according to a second preset matching rule.
In this embodiment, the method for reducing the grayscale image and the grayscale mean template may specifically be an image reduction method based on equal-interval sampling, or an image reduction method based on a local mean, and the present embodiment does not limit this. The preset ratio may typically be 50% or 60%, etc.
In this embodiment, the template matching method specifically refers to a conventional template matching method, that is, the template moves on the image to be detected in a horizontal and vertical sequence, each moving distance is a pixel point, and the overall matching of the image is performed once every moving.
In this embodiment, the matching degree value specifically refers to a value obtained by performing overall matching on an image every time the grayscale image and the grayscale mean template are moved when performing conventional template matching. The value range of the matching degree value differs according to different image overall matching algorithms, for example, when the grayscale image and the grayscale mean template are moved each time and the image overall matching is performed by using a cosine distance method or a correlation coefficient method, the value range of the matching degree value is 0 to 1.
And step 208, taking the matching position corresponding to the maximum value in the matching degree values as a first reference position, and acquiring a second reference position corresponding to the first reference position in the gray-scale image.
In the present embodiment, the first reference position specifically refers to an image range in which the reduced grayscale image corresponds to the maximum matching degree value, and may typically be an image range represented by the pixel point position of the vertex.
In the present embodiment, the second reference position specifically refers to an image range corresponding to the first reference position in the reduced grayscale image in the grayscale image original image. Since the image reduction method of the gray image is known, the corresponding relationship between the pixel positions in the two images before and after reduction can be determined according to the known image reduction method, and the method belongs to the prior art and is not described in detail herein.
And 209, intercepting the gray level image to be matched corresponding to the second reference position according to a preset corresponding rule, and matching the gray level image to be matched with the gray level mean value template according to a template matching method to obtain a second matching result.
In this embodiment, the grayscale image to be matched specifically refers to an image range in which an image range corresponding to the second reference position is enlarged according to a certain proportion, where the certain proportion may be typically 20% or 30%.
In this embodiment, after the grayscale image to be matched is matched with the grayscale mean template according to the template matching method, matching degree data is obtained, the best matching degree data may be compared with a preset threshold, and a second matching result is determined according to the comparison result.
And step 210, determining the authenticity of the paper money to be detected according to the second matching result.
The second embodiment of the invention provides a paper money identification method, which embodies the process of obtaining the first matching result and can simply, conveniently and quickly obtain the first matching result; the acquisition process of the gray level average template is embodied, so that the influence of noise on the gray level average template can be reduced; meanwhile, the process of matching the gray level image and the gray level mean value template according to a second preset matching rule is embodied, and the calculated amount in the matching process can be reduced through the reduction operation on the image. The method can quickly, accurately and conveniently identify the rough counterfeit money by comparing the statistical characteristics of the gray level images, and can determine the matching position by template matching of the reduced images, thereby identifying the paper money to be detected with high accuracy and quickly.
EXAMPLE III
Fig. 3 is a flowchart of a banknote recognition method according to a third embodiment of the present invention. In this embodiment, a statistical feature vector of a gray-scale image is obtained, the statistical feature vector is matched with a statistical feature vector template according to a first preset matching rule, and a first matching result is obtained, where the optimization is as follows: and acquiring a statistical vector of a block image of the gray level image, and matching the statistical vector of the block image with a statistical vector template of the block image according to a first preset matching rule to acquire a first matching result.
Further, the statistical vector of the block image of the acquired gray level image is optimized as follows: dividing the gray level image according to rows and columns to obtain each block image; and acquiring the gray value mean value and the gray value variance of each block image to form a statistical vector of the block images.
Further, before determining the authenticity of the paper currency to be detected according to the second matching result, the optimizing method further comprises the following steps: and acquiring a gray mean value statistical vector of a first block image of the gray image, inputting the gray mean value statistical vector into a preset neural network, and taking an output result of the preset neural network as a third matching result.
Correspondingly, the authenticity of the paper money to be detected is determined according to the second matching result, and the method is optimized as follows: and determining the authenticity of the paper money to be detected according to the second matching result and the third matching result.
Further, the authenticity of the paper money to be detected is determined according to the second matching result and the third matching result, and the method is optimized as follows: and if any one of the second matching result and the third matching result is that the paper money to be detected is the true paper money, determining that the paper money to be detected is the true paper money.
Correspondingly, the method of the embodiment specifically includes:
301, obtaining a gray image corresponding to a preset characteristic area in the image of the paper money to be detected.
And step 302, dividing the gray level image according to rows and columns to obtain each block image.
In the present embodiment, steps S302 to S304 give a preferable way of obtaining the first matching result. Specifically, the grayscale image may be divided according to rows and columns, where the number of rows and columns may be equal or different, the width of each row may be equal or different, the width of each column may be equal or different, and the width of a row and the width of a column may typically be 20 pixel points.
Step 303, obtaining the mean value and variance of the gray values of the block images to form statistical vectors of the block images.
In this embodiment, the mean gray value of the block image specifically refers to the gray values of all the pixels in the block image and a numerical value obtained by dividing the sum by the total number of the pixels. The gray variance of the block image specifically means that the gray value of all pixel points in the block image is subtracted by the sum of squares of the mean gray values of the block image divided by the total number of the pixel points. It is understood that the mean value and the variance of the gray scale can be used to characterize the statistical characteristics of the gray scale image, and the median value, the mode value and the range value of the gray scale image can also be used to characterize the statistical characteristics of the gray scale image, so the median value, the mode value and/or the range value of the gray scale of each block image can also be used to form the statistical vector of the block image.
In addition, the mode of forming the statistical vector by the gray mean and the gray variance of each block image should be consistent with the mode of forming the statistical vector template of the block image, specifically, the statistical vector of the block image may be formed by the gray mean and the gray variance of all block images from left to right from the first row to the last row, or the statistical vector of the block image may be formed by the gray variance and the gray mean of all block images from top to bottom from the first column to the last column, and the like, which is not limited in this embodiment.
And 304, matching the statistical vector of the block image with the statistical vector template of the block image according to a first preset matching rule to obtain a first matching result.
In this embodiment, the statistical vector of the block image and the statistical vector template of the block image may be specifically matched according to a vector similarity calculation method such as a cosine distance method or a correlation coefficient method, and after matching, matching degree data is obtained, and the matching degree data may be compared with a preset threshold value to obtain a first matching result.
And 305, judging whether the paper money to be detected is true paper money or not according to the first matching result, if so, executing step 306, and if not, ending.
And step 306, acquiring a gray average template of the gray image, and matching the gray image and the gray average template according to a second preset matching rule to acquire a second matching result.
And 307, acquiring a gray mean value statistical vector of a first block image of the gray image, inputting the gray mean value statistical vector into a preset neural network, and taking an output result of the preset neural network as a third matching result.
In this embodiment, the obtaining manner of the first block image may specifically be to block the grayscale image according to rows and columns, or to block the grayscale image only according to rows, or to block the grayscale image only according to columns, and the like.
In this embodiment, the gray level mean statistical vector specifically refers to a vector composed of the gray level means of the first block image, and the composition manner of the gray level mean statistical vector should be consistent with the composition manner of the gray level mean statistical vector used in the preset neural network training.
In this embodiment, the third matching result may specifically be that the to-be-detected banknote is a genuine banknote or a counterfeit banknote.
And 308, if any one of the second matching result and the third matching result is that the paper money to be detected is true, determining that the paper money to be detected is true.
The third embodiment of the invention provides a paper money identification method, which embodies the process of obtaining the first matching result and can simply, conveniently and quickly obtain the first matching result; meanwhile, the third matching result obtained by using the preset neural network is optimized and increased, and the accuracy of the identification of the paper money to be detected can be improved. By using the method, the rough counterfeit money can be quickly, accurately and conveniently identified by comparing the statistical characteristics of the gray level images, and meanwhile, the truth of the paper money to be detected is judged by the second matching result and the third matching result together, so that the misjudgment caused by the breakage or the stain of the paper money to be detected can be avoided.
Example four
Fig. 4 is a structural diagram of a banknote recognition apparatus according to a fourth embodiment of the present invention. As shown in fig. 4, the apparatus includes: a grayscale image obtaining module 401, a first matching result obtaining module 402, a second matching result obtaining module 403, and a banknote authenticity determining module 404. Wherein:
the grayscale image acquiring module 401 is configured to acquire a grayscale image corresponding to a preset feature region in an image of a banknote to be detected, where the preset feature region includes an optical characteristic region of the banknote to be detected;
a first matching result obtaining module 402, configured to obtain a statistical feature vector of the grayscale image, match the statistical feature vector with the statistical feature vector template according to a first preset matching rule, and obtain a first matching result;
a second matching result obtaining module 403, configured to obtain a grayscale average template of the grayscale image if the first matching result is that the banknote to be detected is a true banknote, match the grayscale image and the grayscale average template according to a second preset matching rule, and obtain and record a second matching result;
and the banknote authenticity determining module 404 is configured to determine authenticity of the banknote to be detected according to the second matching result.
The embodiment of the invention provides a paper money identification device, which is characterized in that a gray level image and a statistical characteristic vector of the gray level image corresponding to a preset characteristic region in an image of paper money to be detected are obtained, the statistical characteristic vector is matched with a statistical characteristic vector template according to a first preset matching rule, a first matching result is obtained, if the first matching result is that the paper money to be detected is a true paper money, a gray level average template of the gray level image is continuously obtained, the gray level image and the gray level average template are matched according to a second preset matching rule, a second matching result is obtained, and the authenticity of the paper money to be detected is determined according to the second matching result.
On the basis of the foregoing embodiments, the first matching result obtaining module may include:
and the histogram matching unit is used for acquiring a statistical vector of a histogram of the gray level image, and matching the statistical vector of the histogram with the histogram statistical vector template according to a first preset matching rule to acquire a first matching result.
On the basis of the foregoing embodiments, the histogram matching unit may include:
a histogram acquisition subunit configured to acquire a histogram of the grayscale image;
and the histogram statistical vector acquisition subunit is used for taking the ordinate numerical value corresponding to each gray value interval from small to large in the histogram as the statistical vector of the histogram.
On the basis of the foregoing embodiments, the first matching result obtaining module may further include:
and the block image matching unit is used for acquiring the statistical vector of the block image of the gray level image, and matching the statistical vector of the block image with the block image statistical vector template according to a first preset matching rule to acquire a first matching result.
On the basis of the above embodiments, the block image matching unit may include:
the block image acquisition unit is used for dividing the gray level image according to rows and columns to obtain each block image;
and the block image statistical vector acquisition subunit is used for acquiring the gray value mean value and the gray value variance of each block image to form the statistical vector of the block image.
On the basis of the foregoing embodiments, the second matching result obtaining module may include:
the first gray image acquisition unit is used for acquiring a first gray image corresponding to a preset characteristic area in the images of the true banknotes of the paper money to be detected in a preset number;
and the gray average template acquisition unit is used for acquiring gray average images corresponding to the preset number of first gray images and taking the gray average images as the gray average templates.
On the basis of the foregoing embodiments, the second matching result obtaining module may further include:
the image reducing unit is used for reducing the gray level image and the gray level mean value template according to a preset proportion;
the matching degree data recording unit is used for matching the reduced gray level image with the gray level mean value template according to a template matching method and recording a matching degree value;
the reference position determining unit is used for taking the matching position corresponding to the maximum value in the matching degree values as a first reference position and acquiring a second reference position corresponding to the first reference position in the gray level image;
and the template matching unit is used for intercepting the gray level image to be matched corresponding to the second reference position according to a preset corresponding rule and matching the gray level image to be matched with the gray level mean value template according to a template matching method.
On the basis of the above embodiments, the method may further include:
the third matching result acquisition module is used for acquiring a gray value mean value statistical vector of the first block image of the gray value image before the authenticity of the paper money to be detected is determined according to the second matching result, inputting the gray value mean value statistical vector into the preset neural network, and taking an output result of the preset neural network as a third matching result;
accordingly, the banknote authenticity determination module may include:
and the matching result determining unit is used for determining the authenticity of the paper money to be detected according to the second matching result and the third matching result.
On the basis of the foregoing embodiments, the matching result determining unit may be specifically configured to:
and if any one of the second matching result and the third matching result is that the paper money to be detected is the true paper money, determining that the paper money to be detected is the true paper money.
The paper money recognition device provided by the embodiment of the invention can be used for executing the paper money recognition method provided by any embodiment of the invention, has corresponding functional modules and realizes the same beneficial effects.
EXAMPLE five
Fig. 5 is a schematic structural diagram of an apparatus according to a fifth embodiment of the present invention, as shown in fig. 5, the apparatus includes a processor 501, a memory 502, and an output device 503; the number of the processors 501 in the device may be one or more, and one processor 501 is taken as an example in fig. 5; the processor 501, the memory 502 and the output device 503 in the apparatus may be connected by a bus or other means, and fig. 5 illustrates the connection by the bus as an example.
The memory 502 is a computer-readable storage medium, and can be used to store software programs, computer-executable programs, and modules, such as program instructions/modules corresponding to the banknote recognition method in the embodiment of the present invention (for example, the grayscale image obtaining module 401, the first matching result obtaining module 402, the second matching result obtaining module 403, and the banknote authenticity determining module 404 in the banknote recognition apparatus). The processor 501 executes various functional applications of the apparatus and data processing by executing software programs, instructions, and modules stored in the memory 502, that is, realizes the above-described bill identifying method.
The memory 502 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application program required for at least one function; the storage data area may store data created according to the use of the terminal, and the like. Further, the memory 502 may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid state storage device. In some examples, memory 502 may further include memory located remotely from processor 501, which may be connected to devices through a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The output device 503 may include a display device such as a display screen.
EXAMPLE six
An embodiment of the present invention further provides a storage medium containing computer-executable instructions, which when executed by a computer processor, perform a banknote recognition method, the method including:
acquiring a gray image corresponding to a preset characteristic region in an image of a paper money to be detected, wherein the preset characteristic region comprises an optical characteristic region of the paper money to be detected;
acquiring a statistical feature vector of the gray level image, and matching the statistical feature vector with a statistical feature vector template according to a first preset matching rule to acquire a first matching result;
if the first matching result is that the paper money to be detected is a true paper money, acquiring a gray level average template of the gray level image, and matching the gray level image and the gray level average template according to a second preset matching rule to acquire a second matching result;
and determining the authenticity of the paper money to be detected according to the second matching result.
Of course, the storage medium provided by the embodiment of the present invention contains computer-executable instructions, and the computer-executable instructions are not limited to the operations of the method described above, and may also perform related operations in the banknote recognition method provided by any embodiment of the present invention.
From the above description of the embodiments, it is obvious for those skilled in the art that the present invention can be implemented by software and necessary general hardware, and certainly, can also be implemented by hardware, but the former is a better embodiment in many cases. Based on such understanding, the technical solutions of the present invention may be embodied in the form of a software product, which may be stored in a computer-readable storage medium, such as a floppy disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a FLASH Memory (FLASH), a hard disk or an optical disk of a computer, and includes several instructions for enabling a computer device (which may be a personal computer, a server, or a network device) to execute the methods according to the embodiments of the present invention.
It should be noted that, in the embodiment of the above-mentioned paper money identification device, the included units and modules are merely divided according to the functional logic, but not limited to the above-mentioned division, as long as the corresponding functions can be realized; in addition, specific names of the functional units are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the present invention.
It is to be noted that the foregoing is only illustrative of the preferred embodiments of the present invention and the technical principles employed. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, although the present invention has been described in greater detail by the above embodiments, the present invention is not limited to the above embodiments, and may include other equivalent embodiments without departing from the spirit of the present invention, and the scope of the present invention is determined by the scope of the appended claims.
Claims (11)
1. A banknote recognition method, comprising:
acquiring a gray image corresponding to a preset characteristic region in an image of a paper money to be detected, wherein the preset characteristic region comprises an optical characteristic region of the paper money to be detected;
acquiring a statistical feature vector of the gray level image, and matching the statistical feature vector with a statistical feature vector template according to a first preset matching rule to acquire a first matching result;
if the first matching result is that the paper money to be detected is a true paper money, acquiring a gray level average template of the gray level image, and matching the gray level image and the gray level average template according to a second preset matching rule to acquire a second matching result;
determining the authenticity of the paper money to be detected according to the second matching result,
the matching of the gray level image and the gray level mean value template according to a second preset matching rule comprises the following steps:
reducing the gray level image and the gray level average value template according to a preset proportion;
matching the reduced gray level image with the gray level mean value template according to a template matching method, and recording a matching degree value;
taking a matching position corresponding to the maximum value in the matching degree value in the reduced gray scale image as a first reference position, and acquiring a second reference position corresponding to the first reference position in the gray scale image;
and intercepting a gray level image to be matched corresponding to the second reference position from the gray level image according to a preset corresponding rule, and matching the gray level image to be matched with the gray level mean value template according to the template matching method.
2. The method according to claim 1, wherein the obtaining the statistical feature vector of the grayscale image, and matching the statistical feature vector with a statistical feature vector template according to a first preset matching rule to obtain a first matching result comprises:
and acquiring a statistical vector of the histogram of the gray level image, and matching the statistical vector of the histogram with the histogram statistical vector template according to a first preset matching rule to acquire a first matching result.
3. The method of claim 2, wherein obtaining a statistical vector for a histogram of the grayscale image comprises:
acquiring a histogram of the gray level image;
and taking the longitudinal coordinate values corresponding to the gray value intervals from small to large in the histogram as statistical vectors of the histogram.
4. The method according to claim 1, wherein the obtaining the statistical feature vector of the grayscale image, and matching the statistical feature vector with a statistical feature vector template according to a first preset matching rule to obtain a first matching result comprises:
and acquiring a statistical vector of a block image of the gray level image, and matching the statistical vector of the block image with a block image statistical vector template according to a first preset matching rule to acquire a first matching result.
5. The method of claim 4, wherein obtaining a statistical vector for a block image of the grayscale image comprises:
dividing the gray level image according to rows and columns to obtain each block image;
and acquiring the gray value mean value and the gray value variance of each block image to form a statistical vector of the block images.
6. The method of claim 1, wherein obtaining the grayscale mean template of the grayscale image comprises:
acquiring a first gray image corresponding to a preset characteristic area in images of true banknotes of a preset number of banknotes to be detected;
and acquiring the gray mean value images corresponding to the preset number of first gray images, and taking the gray mean value images as the gray mean value template.
7. The method according to claim 1, further comprising, before said determining the authenticity of the banknote to be tested based on the second matching result:
acquiring a gray mean value statistical vector of a first block image of the gray image, inputting the gray mean value statistical vector into a preset neural network, and taking an output result of the preset neural network as a third matching result;
and determining the authenticity of the paper money to be detected according to the second matching result, comprising the following steps:
and determining the authenticity of the paper money to be detected according to the second matching result and the third matching result.
8. The method according to claim 7, wherein the determining the authenticity of the banknote to be tested according to the second matching result and the third matching result comprises:
and if any one of the second matching result and the third matching result is that the paper money to be detected is a true paper money, determining that the paper money to be detected is a true paper money.
9. A paper money discriminating apparatus characterized by comprising:
the device comprises a gray level image acquisition module, a characteristic analysis module and a characteristic analysis module, wherein the gray level image acquisition module is used for acquiring a gray level image corresponding to a preset characteristic region in an image of the paper money to be detected, and the preset characteristic region comprises an optical characteristic region of the paper money to be detected;
the first matching result acquisition module is used for acquiring the statistical feature vector of the gray level image, and matching the statistical feature vector with the statistical feature vector template according to a first preset matching rule to acquire a first matching result;
a second matching result obtaining module, configured to obtain a grayscale mean template of the grayscale image if the first matching result is that the banknote to be detected is a true banknote, match the grayscale image with the grayscale mean template according to a second preset matching rule, and obtain and record a second matching result, where the second matching result obtaining module further includes:
the image reducing unit is used for reducing the gray level image and the gray level mean value template according to a preset proportion;
the matching degree data recording unit is used for matching the reduced gray level image with the gray level mean value template according to a template matching method and recording a matching degree value;
a reference position determining unit, configured to use a matching position corresponding to a maximum value in the reduced grayscale image as a first reference position, and acquire a second reference position corresponding to the first reference position in the grayscale image;
the template matching unit is used for intercepting a gray level image to be matched corresponding to the second reference position from the gray level image according to a preset corresponding rule, and matching the gray level image to be matched with the gray level mean value template according to the template matching method;
and the paper currency authenticity determining module is used for determining the authenticity of the paper currency to be detected according to the second matching result.
10. An electronic device, characterized in that the electronic device comprises:
one or more processors;
a memory for storing one or more programs,
when executed by the one or more processors, cause the one or more processors to implement the banknote recognition method of any one of claims 1-8.
11. A storage medium containing computer executable instructions for performing the banknote recognition method of any one of claims 1-8 when executed by a computer processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710191949.8A CN106952393B (en) | 2017-03-28 | 2017-03-28 | Paper money identification method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710191949.8A CN106952393B (en) | 2017-03-28 | 2017-03-28 | Paper money identification method and device, electronic equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106952393A CN106952393A (en) | 2017-07-14 |
| CN106952393B true CN106952393B (en) | 2020-02-07 |
Family
ID=59474796
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710191949.8A Active CN106952393B (en) | 2017-03-28 | 2017-03-28 | Paper money identification method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106952393B (en) |
Families Citing this family (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107784730A (en) * | 2017-09-14 | 2018-03-09 | 深圳怡化电脑股份有限公司 | A kind of recognition methods of bank note and device |
| CN107610321B (en) * | 2017-10-10 | 2019-10-11 | 深圳怡化电脑股份有限公司 | A kind of identification forge or true or paper money method, apparatus, equipment and storage medium |
| CN107610322B (en) * | 2017-10-11 | 2020-02-07 | 深圳怡化电脑股份有限公司 | Banknote version identification method and device, electronic equipment and storage medium |
| CN109523566A (en) * | 2018-09-18 | 2019-03-26 | 姜枫 | A kind of automatic division method of Sandstone Slice micro-image |
| CN110880003B (en) * | 2019-10-12 | 2023-01-17 | 中国第一汽车股份有限公司 | Image matching method and device, storage medium and automobile |
| CN112116748A (en) * | 2020-02-28 | 2020-12-22 | 李淑 | Red and blue lamp body driving system utilizing cloud computing |
| CN114972709A (en) * | 2022-07-14 | 2022-08-30 | 彼图科技(青岛)有限公司 | Image artificial intelligence algorithm based on block similarity |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN102890840A (en) * | 2012-08-22 | 2013-01-23 | 山东新北洋信息技术股份有限公司 | Method and device for identifying paper money |
| CN105632015A (en) * | 2015-12-24 | 2016-06-01 | 中钞实业有限公司 | Bank bill fingerprint feature anti-counterfeiting identification method based on cloud platform |
| CN105894656A (en) * | 2016-03-30 | 2016-08-24 | 浙江大学 | Banknote image recognition method |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB0313002D0 (en) * | 2003-06-06 | 2003-07-09 | Ncr Int Inc | Currency validation |
| CN102306415B (en) * | 2011-08-01 | 2013-06-26 | 广州广电运通金融电子股份有限公司 | Portable valuable file identification device |
-
2017
- 2017-03-28 CN CN201710191949.8A patent/CN106952393B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN102890840A (en) * | 2012-08-22 | 2013-01-23 | 山东新北洋信息技术股份有限公司 | Method and device for identifying paper money |
| CN105632015A (en) * | 2015-12-24 | 2016-06-01 | 中钞实业有限公司 | Bank bill fingerprint feature anti-counterfeiting identification method based on cloud platform |
| CN105894656A (en) * | 2016-03-30 | 2016-08-24 | 浙江大学 | Banknote image recognition method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106952393A (en) | 2017-07-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106952393B (en) | Paper money identification method and device, electronic equipment and storage medium | |
| CN107103683B (en) | Paper money identification method and device, electronic equipment and storage medium | |
| KR20190004807A (en) | Banknote management method and system | |
| CN107610322B (en) | Banknote version identification method and device, electronic equipment and storage medium | |
| CN104992496A (en) | Paper money face identification method and apparatus | |
| CN106875545B (en) | Method and device for identifying paper money | |
| CN106920318B (en) | Method and device for identifying paper money | |
| CN104298989A (en) | Counterfeit identifying method and counterfeit identifying system based on zebra crossing infrared image characteristics | |
| CN107610316B (en) | Method and device for detecting defect of paper money and terminal equipment | |
| CN107038794B (en) | Method, device and equipment for identifying authenticity of paper money and storage medium | |
| CN106780966B (en) | A kind of paper money discrimination method and device | |
| CN108510639B (en) | Paper money counterfeit discriminating method and device, currency detector and storage medium | |
| CN106898078B (en) | Port currency version identification method and device | |
| CN104537364A (en) | Dollar bill denomination and edition identifying method based on texture analysis | |
| CN106469483A (en) | A kind of method and device of paper money recognition | |
| CN106447910B (en) | A kind of method and device of paper money recognition | |
| CN107680246B (en) | Method and equipment for positioning curve boundary in paper money pattern | |
| CN108806058A (en) | A kind of paper currency detecting method 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 | |
| CN106447904B (en) | Method and device for identifying paper money | |
| CN106296975B (en) | method and device for identifying face value of dollar paper money | |
| CN106447908B (en) | Paper money counterfeit distinguishing method and device | |
| CN108510638B (en) | Paper money identification method and device | |
| CN111563845A (en) | Bill surface scratch detection method, device, equipment and storage medium |
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 |