CN115346306B - Method and device for identifying stained paper money - Google Patents
Method and device for identifying stained paper money Download PDFInfo
- Publication number
- CN115346306B CN115346306B CN202211037706.6A CN202211037706A CN115346306B CN 115346306 B CN115346306 B CN 115346306B CN 202211037706 A CN202211037706 A CN 202211037706A CN 115346306 B CN115346306 B CN 115346306B
- Authority
- CN
- China
- Prior art keywords
- difference
- banknote
- target
- determining
- stained
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 44
- 239000003086 colorant Substances 0.000 claims description 14
- 238000003909 pattern recognition Methods 0.000 claims description 13
- 238000013473 artificial intelligence Methods 0.000 abstract description 3
- 238000012550 audit Methods 0.000 description 3
- 238000010801 machine learning Methods 0.000 description 3
- 238000012015 optical character recognition Methods 0.000 description 2
- 230000011218 segmentation Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005562 fading Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000013139 quantization Methods 0.000 description 1
- 238000004064 recycling Methods 0.000 description 1
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
-
- 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
- G07D7/2016—Testing patterns thereon using feature extraction, e.g. segmentation, edge detection or Hough-transformation
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Inspection Of Paper Currency And Valuable Securities (AREA)
Abstract
The invention provides a stained paper money identification method and device, which can be applied to the field of artificial intelligence or finance, and can be used for determining whether a difference area exists in a target paper money by respectively comparing the front and back images of the target paper money with the front and back images of standard paper money, identifying stained paper money of sensitive information by judging whether the difference area exists in the difference area or not if the difference area exists in the difference area, and identifying stained paper money except the sensitive information according to the position information and the difference degree of the difference area if the difference area does not exist in the difference area. The invention can effectively identify various stained paper money so as to ensure the safe circulation of the paper money.
Description
Technical Field
The invention relates to the field of artificial intelligence, in particular to a method and a device for identifying stained paper money.
Background
During circulation, the paper currency may be stained, and handwriting writing or patterns, printing writing or patterns, other stains and the like may be formed on the paper currency.
If the stained area of the paper money is large or the stained degree is high, the paper money is easy to identify. In some cases, the note has a smaller area of soiling and a lower degree of soiling, but the soiling writing or pattern on the note relates to sensitive information, which can have a negative impact if the note is circulated. There is currently no device that can effectively identify such sensitive information as stained notes.
Disclosure of Invention
In view of the above, the invention provides a method and a device for identifying stained paper money, which can effectively identify various stained paper money.
In order to achieve the above purpose, the specific technical scheme provided by the invention is as follows:
A method of identifying a stained banknote, comprising:
Acquiring target paper money;
Acquiring front and back images of the target paper money;
Respectively comparing the front and back images of the target paper money with the front and back images of the standard paper money to determine whether the target paper money has a difference area or not;
If a difference area exists, judging whether sensitive information exists in the difference area or not;
if the sensitive information exists, determining that the target paper currency is stained paper currency;
If no sensitive information exists, acquiring the position information and the difference degree of the difference area;
and determining whether the target paper currency is stained paper currency according to the position information of the difference area and the difference degree.
Optionally, the acquiring the target banknote includes:
Acquiring paper money to be identified;
Identifying the authenticity of the paper currency to be identified;
and if the paper currency to be identified is true, determining the paper currency to be identified as the target paper currency.
Optionally, the comparing the front and back image of the target banknote with the front and back image of the standard banknote to determine whether the target banknote has a difference region includes:
respectively comparing the pixel color of the front and back images of the target banknote with the pixel color of the front and back images of the standard banknote;
If the difference value between the color of each pixel in the front and back images of the target banknote and the color of the corresponding pixel in the standard front and back images is within a preset range, determining that a difference area does not exist in the target banknote;
And otherwise, determining the region composed of the corresponding pixels with the difference value not within the preset range as the difference region.
Optionally, determining whether the difference area has sensitive information includes:
Text recognition is carried out on the difference area;
If the text information is identified, invoking a pre-built sensitive word stock, and judging whether the text information contains sensitive words in the sensitive word stock;
If the text information is not recognized, inputting the image corresponding to the difference region into a pre-constructed sensitive pattern recognition model, and determining whether the difference region has sensitive information according to the recognition result of the sensitive pattern recognition model.
Optionally, acquiring the location information and the degree of difference of the difference area includes:
acquiring coordinate information of pixels composing the difference region;
determining position information of the difference region according to coordinate information of pixels composing the difference region;
And determining the difference degree of the difference region according to the preset corresponding relation between the color difference value and the difference degree and the difference value between the colors of the pixels forming the difference region and the colors of the corresponding pixels in the front and back images of the standard paper money.
Optionally, determining whether the target banknote is a stained banknote according to the position information of the difference area and the difference degree includes:
Judging whether the difference area is in a preset key area or not according to the position information of the difference area;
If the difference area is in the preset key area, judging whether the difference degree of the difference area is larger than a first preset value or not;
If the target paper currency is larger than a first preset value, determining that the target paper currency is stained paper currency;
If the target banknote is not greater than the first preset value, determining that the target banknote is not a stained banknote;
if the difference area is not in the preset key area, judging whether the difference degree of the difference area is larger than a second preset value or not;
If the target paper currency is larger than a second preset value, determining that the target paper currency is stained paper currency;
and if the target banknote is not greater than the second preset value, determining that the target banknote is not the stained banknote, wherein the first preset value is smaller than the second preset value.
Optionally, after determining that the target banknote is a stained banknote, the method further comprises:
and if the current service is a withdrawal service, placing the target paper money into a money storage box.
Optionally, after determining that the target banknote is a stained banknote, the method further comprises:
And if the current service is a deposit service, prompting the client that the target paper currency is stained paper currency.
Optionally, after determining that the text information does not include the sensitive word in the sensitive word stock, the method further includes:
If the current service is the cash in the banking institution, the text information is sent to a preset auditing person, and whether the current service is continuously executed is determined according to the auditing result of the preset auditing person.
A stained banknote recognition apparatus comprising:
A target banknote acquiring unit configured to acquire a target banknote;
a banknote image acquisition unit configured to acquire a front-back image of the target banknote;
The banknote image comparison unit is used for respectively comparing the front and back images of the target banknote with the front and back images of the standard banknote to determine whether a difference area exists in the target banknote;
the sensitive information judging unit is used for judging whether sensitive information exists in the difference area or not under the condition that the difference area exists in the target paper money, and determining that the target paper money is stained paper money if the sensitive information exists;
a difference region information obtaining unit, configured to obtain, when there is no sensitive information in the difference region, position information and a degree of difference of the difference region;
And the stained paper money determining unit is used for determining whether the target paper money is stained paper money according to the position information of the difference area and the difference degree.
Optionally, the target banknote acquiring unit is specifically configured to:
Acquiring paper money to be identified;
Identifying the authenticity of the paper currency to be identified;
and if the paper currency to be identified is true, determining the paper currency to be identified as the target paper currency.
Optionally, the banknote image comparing unit is specifically configured to:
respectively comparing the pixel color of the front and back images of the target banknote with the pixel color of the front and back images of the standard banknote;
If the difference value between the color of each pixel in the front and back images of the target banknote and the color of the corresponding pixel in the standard front and back images is within a preset range, determining that a difference area does not exist in the target banknote;
And otherwise, determining the region composed of the corresponding pixels with the difference value not within the preset range as the difference region.
Optionally, the sensitive information judging unit is specifically configured to:
Text recognition is carried out on the difference area;
If the text information is identified, invoking a pre-built sensitive word stock, and judging whether the text information contains sensitive words in the sensitive word stock;
If the text information is not recognized, inputting the image corresponding to the difference region into a pre-constructed sensitive pattern recognition model, and determining whether the difference region has sensitive information according to the recognition result of the sensitive pattern recognition model.
Optionally, the difference area information obtaining unit is specifically configured to:
acquiring coordinate information of pixels composing the difference region;
determining position information of the difference region according to coordinate information of pixels composing the difference region;
And determining the difference degree of the difference region according to the preset corresponding relation between the color difference value and the difference degree and the difference value between the colors of the pixels forming the difference region and the colors of the corresponding pixels in the front and back images of the standard paper money.
Optionally, the stained banknote determining unit is specifically configured to:
Judging whether the difference area is in a preset key area or not according to the position information of the difference area;
If the difference area is in the preset key area, judging whether the difference degree of the difference area is larger than a first preset value or not;
If the target paper currency is larger than a first preset value, determining that the target paper currency is stained paper currency;
If the target banknote is not greater than the first preset value, determining that the target banknote is not a stained banknote;
if the difference area is not in the preset key area, judging whether the difference degree of the difference area is larger than a second preset value or not;
If the target paper currency is larger than a second preset value, determining that the target paper currency is stained paper currency;
and if the target banknote is not greater than the second preset value, determining that the target banknote is not the stained banknote, wherein the first preset value is smaller than the second preset value.
Optionally, the apparatus further includes:
And the first stained paper money processing unit is used for placing the target paper money into a cash storage box if the current service is a cash withdrawal service after the target paper money is stained paper money.
Optionally, the apparatus further includes:
and the second stained paper money processing unit is used for prompting the client that the target paper money is stained paper money if the current business is a deposit business after the target paper money is determined to be stained paper money.
Optionally, the apparatus further includes:
And the third stained paper money processing unit is used for sending the text information to a preset auditor after determining that the text information does not contain the sensitive words in the sensitive word stock, if the current business is the bank note collection in the banking institution, and determining whether to continue executing the current business according to the audit result of the preset auditor.
Compared with the prior art, the invention has the following beneficial effects:
The invention discloses a stained paper money identification method, which is characterized in that whether a difference area exists in a target paper money is determined by respectively comparing front and back images of the target paper money with front and back images of standard paper money, if the difference area exists, the stained paper money with sensitive information is identified by judging whether the difference area exists or not, and if the sensitive information does not exist, stained paper money except the sensitive information is identified according to the position information and the difference degree of the difference area. The invention can effectively identify various stained paper money so as to ensure the safe circulation of the paper money.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are required to be used in the embodiments or the description of the prior art will be briefly described below, and it is obvious that the drawings in the following description are only embodiments of the present invention, and that other drawings can be obtained according to the provided drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic flow chart of a method for identifying stained paper money according to the embodiment of the invention;
FIG. 2 is a schematic flow chart of a part of a method for identifying stained paper money according to the embodiment of the invention;
FIG. 3 is a schematic flow chart of a part of a method for identifying stained paper money according to the embodiment of the invention;
FIG. 4 is a schematic flow chart of a portion of a method for identifying a stained banknote according to an embodiment of the present invention;
Fig. 5 is a schematic structural diagram of a stained banknote recognition apparatus according to an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1, an embodiment of the present invention provides a method for identifying stained paper money, which can be applied to self-service equipment of a bank, such as a self-service deposit and withdrawal machine, and can also be applied to currency detecting equipment inside a banking institution, and the like, and the method specifically includes:
s101: acquiring target paper money;
the target banknote is a banknote awaiting recognition as to whether it is a stained banknote.
Alternatively, the target banknote may be a banknote which is authenticated as genuine, and the banknote waiting for further authentication is a stained banknote, and the method for authenticating the banknote may be any existing banknote authentication method, and the present invention is not limited in particular.
S102: acquiring front and back images of a target banknote;
And scanning the front and back sides of the target paper currency by using an image scanning device to obtain the front and back side images of the target paper currency.
S103: respectively comparing the front and back images of the target paper money with the front and back images of the standard paper money to determine whether the target paper money has a difference area or not;
Note that, the color of the bill may slightly change due to factors such as light irradiation and natural fading during circulation, and if the pixel color of the front and back image of the target bill is inconsistent with the pixel color of the front and back image of the standard bill, the target bill is considered to be a contaminated bill which may affect the current business, which is obviously unsuitable.
On this basis, this embodiment provides an S103 alternative implementation manner, including:
And respectively comparing the pixel colors of the front and back images of the target banknote with the pixel colors of the front and back images of the standard banknote.
If the difference value between the color of each pixel in the front and back images of the target banknote and the color of the corresponding pixel in the standard front and back images is within the preset range, determining that the target banknote has no difference area. The preset range is a preset color difference range which does not affect the current service.
Otherwise, the region composed of the corresponding pixels whose difference value is not within the preset range is determined as the difference region.
It will be appreciated that the difference region, if any, in the target banknote may be one or more.
If there is no difference region, execution proceeds to S104: continuing to process the current service;
The current business can be a withdrawal business, a deposit business, a cash collection in a banking institution and the like.
If there is a difference region, S105 is executed: judging whether sensitive information exists in the difference area;
Referring to fig. 2, this embodiment provides an alternative implementation manner of S105:
s201: text recognition is carried out on the difference area;
In particular, the difference region may be text recognized using OCR (Optical Character Recognition ) techniques.
S202: if the text information is identified, invoking a pre-constructed sensitive word stock, and judging whether the text information contains sensitive words in the sensitive word stock;
The sensitive words in the sensitive word stock are sensitive words which influence banknote circulation, such as reaction propaganda words, negative words and the like.
Specifically, word segmentation processing can be performed on the identified text information, words after word segmentation processing are matched with the sensitive word stock, and whether the text information contains sensitive words in the sensitive word stock is judged according to a matching result.
S203: if the text information is not recognized, inputting the image corresponding to the difference region into a pre-constructed sensitive pattern recognition model, and determining whether the difference region has sensitive information according to the recognition result of the sensitive pattern recognition model.
If the text information is not recognized, the difference area may be a pattern or a stain without any practical meaning, and the sensitive pattern recognition model needs to be called to recognize whether the image corresponding to the difference area has sensitive information.
The sensitive pattern recognition model is obtained by training a specific machine learning model by using a training sample in advance, wherein the specific machine learning model can be a neural network model or other machine learning models, and the training sample is marked with whether the sensitive pattern recognition model is sensitive information in advance.
Further, if the current service is cash collection in the banking institution, after determining that the text information does not contain the sensitive words in the sensitive word stock, the text information is sent to a preset auditor, and whether to continue executing the current service is determined according to an audit result of the preset auditor.
If there is sensitive information, execution S106: determining that the target banknote is a stained banknote;
if no sensitive information exists, execution S107: acquiring position information and difference degree of a difference area;
referring to fig. 3, the present embodiment provides an alternative implementation manner of S107, including:
s301: acquiring coordinate information of pixels constituting a difference region;
S302: determining position information of the difference region according to coordinate information of pixels constituting the difference region;
specifically, the position information of the difference region is determined according to the coordinate information of the pixels at the outline of the difference region.
S303: and determining the difference degree of the difference region according to the preset corresponding relation between the color difference value and the difference degree and the difference value between the colors of the pixels forming the difference region and the colors of the corresponding pixels in the front and back images of the standard banknote.
In order to facilitate quantization of the color difference between the colors of the pixels constituting the difference region and the colors of the corresponding pixels in the regular banknote obverse and reverse side images, the present embodiment expresses the color difference of the difference region with the degree of difference.
S108: and determining whether the target paper currency is the stained paper currency according to the position information of the difference area and the difference degree.
Referring to fig. 4, the present embodiment provides an alternative implementation manner of S108, including:
S401: judging whether the difference area is in a preset key area according to the position information of the difference area;
If the difference region is within the preset key region, S402 is executed: judging whether the difference degree of the difference area is larger than a first preset value or not;
If the value is greater than the first preset value, S403 is executed: determining that the target banknote is a stained banknote;
if not, executing S404: determining that the target banknote is not a stained banknote;
If the difference area is not within the preset key area, S405 is executed: judging whether the difference degree of the difference area is larger than a second preset value or not;
If the value is greater than the second preset value, S403 is executed: determining that the target banknote is a stained banknote;
If not, executing S404: it is determined that the target banknote is not a stained banknote.
Wherein the first preset value is smaller than the second preset value.
The preset key area is an area which influences the circulation of paper currency in preset paper currency, such as an area containing key characters or key patterns in standard paper currency.
Further, the embodiment also discloses a processing method after the target paper currency is determined to be the stained paper currency according to different businesses.
If the current service is a withdrawal service, the target paper money is put into a money storage box, and the next paper money of the target paper money is identified.
If the current service is a deposit service, prompting the client that the target paper money is stained paper money, and then putting the paper money into a cash recycling machine to execute deposit operation after the client removes the stained paper money.
According to the stained paper money identification method disclosed by the embodiment, whether the target paper money has a difference area is determined by comparing the front and back images of the target paper money with the front and back images of the standard paper money respectively, if the difference area exists, the stained paper money with the sensitive information is identified by judging whether the difference area exists or not, and if the sensitive information does not exist, the stained paper money except the sensitive information is identified according to the position information and the difference degree of the difference area. Can effectively identify various stained paper money, thereby ensuring the safe circulation of paper money.
Based on the method for identifying stained paper money disclosed in the above embodiment, the present embodiment correspondingly discloses a device for identifying stained paper money, please refer to fig. 5, the device includes:
a target banknote acquiring unit 501 for acquiring a target banknote;
A banknote image acquisition unit 502 configured to acquire a front-back image of the target banknote;
A banknote image comparing unit 503, configured to compare the front and back images of the target banknote with the front and back images of the standard banknote, respectively, to determine whether there is a difference region in the target banknote;
a sensitive information judging unit 504, configured to judge whether sensitive information exists in the difference area if the target banknote has the difference area, and if the sensitive information exists, determine that the target banknote is a stained banknote;
a difference region information obtaining unit 505, configured to obtain, in a case where there is no sensitive information in the difference region, position information and a degree of difference of the difference region;
And a stained banknote determining unit 506, configured to determine whether the target banknote is a stained banknote according to the position information of the difference area and the degree of difference.
Optionally, the target banknote acquiring unit 501 is specifically configured to:
Acquiring paper money to be identified;
Identifying the authenticity of the paper currency to be identified;
and if the paper currency to be identified is true, determining the paper currency to be identified as the target paper currency.
Optionally, the banknote image comparing unit 503 is specifically configured to:
respectively comparing the pixel color of the front and back images of the target banknote with the pixel color of the front and back images of the standard banknote;
If the difference value between the color of each pixel in the front and back images of the target banknote and the color of the corresponding pixel in the standard front and back images is within a preset range, determining that a difference area does not exist in the target banknote;
And otherwise, determining the region composed of the corresponding pixels with the difference value not within the preset range as the difference region.
Optionally, the sensitive information determining unit 504 is specifically configured to:
Text recognition is carried out on the difference area;
If the text information is identified, invoking a pre-built sensitive word stock, and judging whether the text information contains sensitive words in the sensitive word stock;
If the text information is not recognized, inputting the image corresponding to the difference region into a pre-constructed sensitive pattern recognition model, and determining whether the difference region has sensitive information according to the recognition result of the sensitive pattern recognition model.
Optionally, the difference area information obtaining unit 505 is specifically configured to:
acquiring coordinate information of pixels composing the difference region;
determining position information of the difference region according to coordinate information of pixels composing the difference region;
And determining the difference degree of the difference region according to the preset corresponding relation between the color difference value and the difference degree and the difference value between the colors of the pixels forming the difference region and the colors of the corresponding pixels in the front and back images of the standard paper money.
Optionally, the stained banknote determining unit 506 is specifically configured to:
Judging whether the difference area is in a preset key area or not according to the position information of the difference area;
If the difference area is in the preset key area, judging whether the difference degree of the difference area is larger than a first preset value or not;
If the target paper currency is larger than a first preset value, determining that the target paper currency is stained paper currency;
If the target banknote is not greater than the first preset value, determining that the target banknote is not a stained banknote;
if the difference area is not in the preset key area, judging whether the difference degree of the difference area is larger than a second preset value or not;
If the target paper currency is larger than a second preset value, determining that the target paper currency is stained paper currency;
and if the target banknote is not greater than the second preset value, determining that the target banknote is not the stained banknote, wherein the first preset value is smaller than the second preset value.
Optionally, the apparatus further includes:
And the first stained paper money processing unit is used for placing the target paper money into a cash storage box if the current service is a cash withdrawal service after the target paper money is stained paper money.
Optionally, the apparatus further includes:
and the second stained paper money processing unit is used for prompting the client that the target paper money is stained paper money if the current business is a deposit business after the target paper money is determined to be stained paper money.
Optionally, the apparatus further includes:
And the third stained paper money processing unit is used for sending the text information to a preset auditor after determining that the text information does not contain the sensitive words in the sensitive word stock, if the current business is the bank note collection in the banking institution, and determining whether to continue executing the current business according to the audit result of the preset auditor.
According to the stained paper money identification device disclosed by the embodiment, whether the target paper money has a difference area is determined by comparing the front and back images of the target paper money with the front and back images of the standard paper money respectively, if the difference area exists, the stained paper money with the sensitive information is identified by judging whether the difference area exists or not, and if the sensitive information does not exist, the stained paper money except the sensitive information is identified according to the position information and the difference degree of the difference area. The embodiment can effectively identify various stained paper currencies, and further ensure the safe circulation of the paper currencies.
It should be noted that the method and the device for identifying the stained paper money provided by the invention can be applied to the field of artificial intelligence or the field of finance, and the above is only an example and does not limit the application field of the method and the device for identifying the stained paper money provided by the invention.
In the present specification, each embodiment is described in a progressive manner, and each embodiment is mainly described in a different point from other embodiments, and identical and similar parts between the embodiments are all enough to refer to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant points refer to the description of the method section.
It is further noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
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. The software modules may be disposed in Random Access Memory (RAM), memory, read Only Memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.
The above embodiments may be combined in any manner, and features described in the embodiments in the present specification may be replaced or combined with each other in the above description of the disclosed embodiments, so as to enable those skilled in the art to make or use the present application.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (9)
1. A method of identifying a stained banknote, comprising:
Acquiring target paper money;
Acquiring front and back images of the target paper money;
Respectively comparing the front and back images of the target paper money with the front and back images of the standard paper money to determine whether the target paper money has a difference area or not;
If a difference area exists, judging whether sensitive information exists in the difference area or not;
if the sensitive information exists, determining that the target paper currency is stained paper currency;
If no sensitive information exists, acquiring the position information and the difference degree of the difference area;
determining whether the target paper currency is stained paper currency according to the position information of the difference area and the difference degree;
The determining whether the target banknote is a stained banknote according to the position information of the difference area and the difference degree comprises the following steps:
Judging whether the difference area is in a preset key area or not according to the position information of the difference area;
If the difference area is in the preset key area, judging whether the difference degree of the difference area is larger than a first preset value or not;
If the target paper currency is larger than a first preset value, determining that the target paper currency is stained paper currency;
If the target banknote is not greater than the first preset value, determining that the target banknote is not a stained banknote;
if the difference area is not in the preset key area, judging whether the difference degree of the difference area is larger than a second preset value or not;
If the target paper currency is larger than a second preset value, determining that the target paper currency is stained paper currency;
and if the target banknote is not greater than the second preset value, determining that the target banknote is not the stained banknote, wherein the first preset value is smaller than the second preset value.
2. The method of claim 1, wherein the acquiring the target banknote comprises:
Acquiring paper money to be identified;
Identifying the authenticity of the paper currency to be identified;
and if the paper currency to be identified is true, determining the paper currency to be identified as the target paper currency.
3. The method of claim 1, wherein comparing the front and back images of the target banknote with the front and back images of a standard banknote, respectively, to determine whether the target banknote has a difference region, comprises:
respectively comparing the pixel color of the front and back images of the target banknote with the pixel color of the front and back images of the standard banknote;
if the difference value between the color of each pixel in the front and back images of the target banknote and the color of the corresponding pixel in the front and back images of the standard banknote is within a preset range, determining that a difference area does not exist in the target banknote;
And otherwise, determining the region composed of the corresponding pixels with the difference value not within the preset range as the difference region.
4. The method of claim 1, wherein determining whether the region of difference is sensitive information comprises:
Text recognition is carried out on the difference area;
If the text information is identified, invoking a pre-built sensitive word stock, and judging whether the text information contains sensitive words in the sensitive word stock;
If the text information is not recognized, inputting the image corresponding to the difference region into a pre-constructed sensitive pattern recognition model, and determining whether the difference region has sensitive information according to the recognition result of the sensitive pattern recognition model.
5. The method of claim 1, wherein obtaining location information and a degree of discrepancy of the discrepancy area comprises:
acquiring coordinate information of pixels composing the difference region;
determining position information of the difference region according to coordinate information of pixels composing the difference region;
And determining the difference degree of the difference region according to the preset corresponding relation between the color difference value and the difference degree and the difference value between the colors of the pixels forming the difference region and the colors of the corresponding pixels in the front and back images of the standard paper money.
6. The method of claim 1, wherein after determining that the target banknote is a stained banknote, the method further comprises:
and if the current service is a withdrawal service, placing the target paper money into a money storage box.
7. The method of claim 1, wherein after determining that the target banknote is a stained banknote, the method further comprises:
And if the current service is a deposit service, prompting the client that the target paper currency is stained paper currency.
8. The method of claim 4, wherein after determining that the text information does not contain sensitive words in the sensitive word stock, the method further comprises:
If the current service is the cash in the banking institution, the text information is sent to a preset auditing person, and whether the current service is continuously executed is determined according to the auditing result of the preset auditing person.
9. A stained banknote recognition apparatus, comprising:
A target banknote acquiring unit configured to acquire a target banknote;
a banknote image acquisition unit configured to acquire a front-back image of the target banknote;
The banknote image comparison unit is used for respectively comparing the front and back images of the target banknote with the front and back images of the standard banknote to determine whether a difference area exists in the target banknote;
the sensitive information judging unit is used for judging whether sensitive information exists in the difference area or not under the condition that the difference area exists in the target paper money, and determining that the target paper money is stained paper money if the sensitive information exists;
a difference region information obtaining unit, configured to obtain, when there is no sensitive information in the difference region, position information and a degree of difference of the difference region;
A stained banknote determining unit for determining whether the target banknote is stained banknote according to the position information of the difference area and the difference degree;
The stained paper money determining unit is specifically configured to determine whether the difference area is in a preset critical area according to the position information of the difference area; if the difference area is in the preset key area, judging whether the difference degree of the difference area is larger than a first preset value or not; if the target paper currency is larger than a first preset value, determining that the target paper currency is stained paper currency; if the target banknote is not greater than the first preset value, determining that the target banknote is not a stained banknote; if the difference area is not in the preset key area, judging whether the difference degree of the difference area is larger than a second preset value or not; if the target paper currency is larger than a second preset value, determining that the target paper currency is stained paper currency; and if the target banknote is not greater than the second preset value, determining that the target banknote is not the stained banknote, wherein the first preset value is smaller than the second preset value.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211037706.6A CN115346306B (en) | 2022-08-26 | 2022-08-26 | Method and device for identifying stained paper money |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211037706.6A CN115346306B (en) | 2022-08-26 | 2022-08-26 | Method and device for identifying stained paper money |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115346306A CN115346306A (en) | 2022-11-15 |
| CN115346306B true CN115346306B (en) | 2024-06-11 |
Family
ID=83954710
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211037706.6A Active CN115346306B (en) | 2022-08-26 | 2022-08-26 | Method and device for identifying stained paper money |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115346306B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117314897B (en) * | 2023-11-28 | 2024-03-19 | 恒银金融科技股份有限公司 | Method and device for discriminating distortion of banknote image |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102236897A (en) * | 2011-05-09 | 2011-11-09 | 哈尔滨工业大学 | Method for detecting old and new as well as deformity of paper currency by sorting machine based on paper currency degeneration energy function |
| CN104200561A (en) * | 2014-06-16 | 2014-12-10 | 华中科技大学 | Method for identifying character-stained RMB based on texture features |
| CN107067000A (en) * | 2017-03-31 | 2017-08-18 | 深圳怡化电脑股份有限公司 | A kind of recognition methods of bank note degree and device |
| KR101781009B1 (en) * | 2016-08-31 | 2017-10-23 | 노틸러스효성 주식회사 | Soiled banknote discrimination method |
| CN107895424A (en) * | 2017-10-31 | 2018-04-10 | 深圳怡化电脑股份有限公司 | A kind of recognition methods of bank note, system and financial terminal |
| CN109408632A (en) * | 2018-09-13 | 2019-03-01 | 北京中科闻歌科技股份有限公司 | A kind of information security recognition methods |
| CN110910561A (en) * | 2018-09-18 | 2020-03-24 | 深圳怡化电脑股份有限公司 | Banknote contamination identification method and device, storage medium and financial equipment |
| CN112001282A (en) * | 2020-08-12 | 2020-11-27 | 腾讯音乐娱乐科技（深圳）有限公司 | Image recognition method |
| WO2022142041A1 (en) * | 2020-12-29 | 2022-07-07 | 平安科技（深圳）有限公司 | Training method and apparatus for intent recognition model, computer device, and storage medium |
-
2022
- 2022-08-26 CN CN202211037706.6A patent/CN115346306B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102236897A (en) * | 2011-05-09 | 2011-11-09 | 哈尔滨工业大学 | Method for detecting old and new as well as deformity of paper currency by sorting machine based on paper currency degeneration energy function |
| CN104200561A (en) * | 2014-06-16 | 2014-12-10 | 华中科技大学 | Method for identifying character-stained RMB based on texture features |
| KR101781009B1 (en) * | 2016-08-31 | 2017-10-23 | 노틸러스효성 주식회사 | Soiled banknote discrimination method |
| CN107067000A (en) * | 2017-03-31 | 2017-08-18 | 深圳怡化电脑股份有限公司 | A kind of recognition methods of bank note degree and device |
| CN107895424A (en) * | 2017-10-31 | 2018-04-10 | 深圳怡化电脑股份有限公司 | A kind of recognition methods of bank note, system and financial terminal |
| CN109408632A (en) * | 2018-09-13 | 2019-03-01 | 北京中科闻歌科技股份有限公司 | A kind of information security recognition methods |
| CN110910561A (en) * | 2018-09-18 | 2020-03-24 | 深圳怡化电脑股份有限公司 | Banknote contamination identification method and device, storage medium and financial equipment |
| CN112001282A (en) * | 2020-08-12 | 2020-11-27 | 腾讯音乐娱乐科技（深圳）有限公司 | Image recognition method |
| WO2022142041A1 (en) * | 2020-12-29 | 2022-07-07 | 平安科技（深圳）有限公司 | Training method and apparatus for intent recognition model, computer device, and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115346306A (en) | 2022-11-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US6272245B1 (en) | Apparatus and method for pattern recognition | |
| CN101226655B (en) | Validation template for valuable media of multiple classes | |
| Mirza et al. | Paper currency verification system based on characteristic extraction using image processing | |
| EP2602771A1 (en) | Valuable file identification method and identification system, device thereof | |
| US8611665B2 (en) | Method of recognizing a media item | |
| CN107610322B (en) | Banknote version identification method and device, electronic equipment and storage medium | |
| CN106952393B (en) | Paper money identification method and device, electronic equipment and storage medium | |
| Roy et al. | Machine-assisted authentication of paper currency: an experiment on Indian banknotes | |
| EP3417429A1 (en) | Method and apparatus for detection of document tampering | |
| CN106845469B (en) | Paper money identification method and device | |
| JP2011039821A (en) | Serial number recognition device and paper sheet processor | |
| CN115346306B (en) | Method and device for identifying stained paper money | |
| CN107067533A (en) | The method and device that a kind of bank note differentiates | |
| JP2002092682A (en) | Method and system of detecting watermark | |
| Gautam | Indian currency detection using image recognition technique | |
| CN106898078B (en) | Port currency version identification method and device | |
| CN111462388A (en) | Bill inspection method and device, terminal equipment and storage medium | |
| Chhabra et al. | Detecting fraudulent bank checks | |
| WO2018130119A1 (en) | Double prefix number-based paper money authenticity identification method and system | |
| Garain et al. | On automatic authenticity verification of printed security documents | |
| Satish et al. | Money to ATM–Fake Currency Detection | |
| KR101232684B1 (en) | Method for detecting counterfeits of banknotes using Bayesian approach | |
| KR101812206B1 (en) | Counterfeit discrimnation and tracking system and method performing thereof | |
| CN115205882A (en) | Intelligent identification and processing method for expense voucher in medical industry | |
| TWI378406B (en) | Method for performing color analysis operation on image corresponding to monetary banknote |
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 |