CN111476937B - Method and device for assisting one-dimensional signal false identification of two-dimensional signal of financial machine - Google Patents
Method and device for assisting one-dimensional signal false identification of two-dimensional signal of financial machine Download PDFInfo
- Publication number
- CN111476937B CN111476937B CN202010308699.3A CN202010308699A CN111476937B CN 111476937 B CN111476937 B CN 111476937B CN 202010308699 A CN202010308699 A CN 202010308699A CN 111476937 B CN111476937 B CN 111476937B
- Authority
- CN
- China
- Prior art keywords
- dimensional
- area
- signal
- counterfeit
- code disc
- 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 21
- 238000013507 mapping Methods 0.000 claims abstract description 55
- 238000001514 detection method Methods 0.000 claims description 19
- 238000004364 calculation method Methods 0.000 claims description 13
- 238000007781 pre-processing Methods 0.000 claims description 13
- 230000002194 synthesizing effect Effects 0.000 claims description 13
- 230000009466 transformation Effects 0.000 claims description 12
- PXFBZOLANLWPMH-UHFFFAOYSA-N 16-Epiaffinine Natural products C1C(C2=CC=CC=C2N2)=C2C(=O)CC2C(=CC)CN(C)C1C2CO PXFBZOLANLWPMH-UHFFFAOYSA-N 0.000 claims description 8
- 238000001914 filtration Methods 0.000 claims description 6
- 238000011161 development Methods 0.000 abstract description 2
- 230000005540 biological transmission Effects 0.000 description 3
- 230000005389 magnetism Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000005856 abnormality Effects 0.000 description 1
- 239000002390 adhesive tape Substances 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
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
- G07D7/16—Testing the dimensions
- G07D7/162—Length or width
-
- 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
- G07D7/04—Testing magnetic properties of the materials thereof, e.g. by detection of magnetic imprint
-
- 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
- G07D7/06—Testing specially adapted to determine the identity or genuineness of valuable papers or for segregating those which are unacceptable, e.g. banknotes that are alien to a currency using wave or particle radiation
- G07D7/12—Visible light, infrared or ultraviolet radiation
- G07D7/128—Viewing devices
-
- 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
- G07D7/16—Testing the dimensions
- G07D7/164—Thickness
-
- 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
Abstract
A method and a device for identifying a financial machine by using a two-dimensional signal to assist a one-dimensional signal, wherein the method comprises the following steps: step 1, predefining the coordinate position of a counterfeit discrimination area of paper money to be discriminated; step 2, acquiring a one-dimensional signal and a two-dimensional image signal respectively acquired by a one-dimensional sensor and a two-dimensional image sensor of financial equipment; step 3, mapping the one-dimensional signal, the two-dimensional image signal and the counterfeit distinguishing area to the same dimension, and calculating the coverage rate of the counterfeit distinguishing area; and 4, calculating the score of the counterfeit distinguishing area based on the coverage rate of the counterfeit distinguishing area, and performing comprehensive arbitration on the counterfeit distinguishing area based on the score of the counterfeit distinguishing area. The invention superposes the one-dimensional sensor signal with the two-dimensional sensor signal from the dimension of the paper money moving direction, thereby accurately positioning, solving the problems of inaccurate positioning, low efficiency and difficult distinguishing of the one-dimensional sensor of the financial machine tool equipment, improving the development efficiency and increasing the stability and the false distinguishing strength of the equipment.
Description
Technical Field
The invention relates to the technical field of anti-counterfeiting, in particular to a method and a device for assisting one-dimensional signal counterfeit identification by a two-dimensional signal of a financial machine.
Background
The financial machine tool equipment refers to machine tool products which are daily used by financial institutions such as banks and the like, such as anti-counterfeiting currency counters, currency detectors, counter counters, currency sorting machines, currency bundling machines, bundling machines and the like; the sensors of most devices include two-dimensional and one-dimensional sensors, and a general two-dimensional Image Sensor is a two-dimensional Image Sensor named as a Contact Image Sensor (CIS), that is, a two-dimensional Image signal is acquired as an Image; the one-dimensional sensor generally refers to a traditional sensor in the field of financial machines, such as a medium and small coil magnetic head module, an infrared transmission pair tube module, a long magnetic strip module, an ultraviolet module, an infrared reflection pair tube module and the like.
At present, the processing modes of internal algorithms and logics of financial equipment and instruments are respectively and independently operated, image signals acquired by a one-dimensional image sensor and a two-dimensional image sensor are mutually independent in the processes of calculation, analysis and arbitration, and final results are directly output after own analysis conclusions are given. However, due to the physical characteristics of the financial equipment, the position and the angle of the paper money are different when the paper money passes through the equipment channel every time, so that the one-dimensional sensor cannot judge the passing position of the paper money accurately. Such as: when the bank note inclines, the irradiation area of the one-dimensional ultraviolet module does not cover the fluorescent square window area on the bank note, and at the moment, the one-dimensional sensor module can report that the bank note is false, but actually, the fluorescent square window area of the bank note does not pass through the ultraviolet module, so that the signal acquisition is lost. The existing paper money discrimination mode of the financial machine has the following defects:
1. the positioning accuracy is low. The one-dimensional signal positioning is to roughly position according to signals of a plurality of groups of infrared transmission geminate transistors, and when paper money passes through at different positions and different angles, whether a counterfeit distinguishing area on the paper money passes through the one-dimensional sensor cannot be accurately obtained;
2. the counterfeit identification efficiency is low. The state of the note in the machine can only be inferred by one-dimensional signals, and analysis of a problem requires a lot of manual and practical feedback to reach a more stable state.
3. The discrimination is difficult. When some counterfeit identification characteristics are close to the characteristics of the paper money, similar characteristic areas of counterfeit money or genuine money cannot be effectively distinguished, such as: reflective infrared pair tubes are commonly used to detect adhesive tape used in banknote splicing, but security threads for banknotes can also have similar features.
Disclosure of Invention
In view of the technical drawbacks and technical disadvantages of the prior art, embodiments of the present invention provide a solution to overcome the above problems or at least partially solve the above problems, and specifically include the following:
as a first aspect of the present invention, there is provided a method for identifying a financial instrument by using a two-dimensional signal to assist a one-dimensional signal, the method comprising:
step 1, predefining the coordinate position of a counterfeit discrimination area of paper money to be discriminated;
step 2, acquiring one-dimensional signals and two-dimensional image signals respectively acquired by a one-dimensional sensor and a two-position image sensor of financial equipment, and acquiring coordinate position information of each signal;
step 3, mapping the one-dimensional signal, the two-dimensional image signal and the counterfeit distinguishing area to the same dimension, and calculating the coverage rate of the counterfeit distinguishing area;
and 4, calculating the score of the counterfeit distinguishing area based on the coverage rate of the counterfeit distinguishing area, and performing comprehensive arbitration on the counterfeit distinguishing area based on the score of the counterfeit distinguishing area.
Preferably, the mapping the coordinate positions of the one-dimensional signal, the two-dimensional image signal and the counterfeit identifying area to the same dimension specifically includes:
step 3.11, mapping one-dimensional signal coordinates: mapping the layout of the one-dimensional signal to an x-axis of a two-dimensional image signal coordinate system according to the one-dimensional signal distribution position of the equipment and the physical size approximately represented by each pixel of the one-dimensional signal;
step 3.12, mapping the signal waveform of the one-dimensional signal: preprocessing the obtained one-dimensional signal, deducing a code disc interval corresponding to the current signal on the two-dimensional image signal by using a code disc difference of a predefined distance between the specific one-dimensional signal and the two-dimensional image signal on a y axis and a front-back relation of the physical positions of the one-dimensional signal and the two-dimensional image signal on the y axis and by using the current code disc value of the one-dimensional signal to perform corresponding addition and subtraction, finding a row number interval by using the code disc interval, mapping the row number interval onto the y axis of an image coordinate system, wherein the coordinate represents the position of a signal generated if the one-dimensional signal is overlapped with the two-dimensional image sensor on the y axis, and mapping a two-dimensional rectangular area generating the signal by combining with the step 3.11 to define the area a; the coded disc difference is obtained by converting the distance between the one-dimensional signal and the two-dimensional image signal from millimeter to a coded disc as a distance unit, the coded disc value is the current coded disc value, and after the machine starts to rotate, the coded disc counts once through each gear and is accumulated in sequence;
step 3.13, mapping the coordinates of the counterfeit distinguishing area: and taking out the predefined counterfeit distinguishing area matched with the denomination and version of the current paper currency, performing inverse transformation on the predefined counterfeit distinguishing area to a two-dimensional image signal based on the affine parameters and the angular point information of the current paper currency to mark, representing the position of the paper currency counterfeit distinguishing area in the current actual data, and defining the position as an area b.
Preferably, the calculating the coverage of the counterfeit detection area specifically includes: describing the area b by coordinates of four corner points; defining an area c representing the position of the one-dimensional signal, wherein the starting position and the width of an x axis of the area are parameters for defining the one-dimensional signal, the starting point of a y axis is a zero point, and the end point is the last, and the calculating steps are as follows:
step 3.21, overlapping the area b and the area c, wherein the overlapped part forms a new rectangle or triangle;
step 3.22, if the rectangle is, dividing the rectangle into two triangles to calculate the area, if the triangle is, directly calculating the area, wherein the area calculation formula uses a Helen formula, and the formula is as follows: given the three sides of the triangle are a1, b1, and c1, respectively, then: p ═ 2 (a1+ b1+ c1)/2, area S ═ sqrt [ p (p-a1) (p-b1) (p-c1) ];
in step 3.23, the area is calculated as S1, taking the one-dimensional signal width as wide and the difference between the highest point and the lowest point on the y-axis of the pseudo-discrimination region after inverse transformation as high, and the coverage rate Per of the pseudo-discrimination region is obtained as S/S1.
Further, the calculating the counterfeit distinguishing region score specifically includes:
step 4.1, confirming the range of the number of lines of the false distinguishing area on the y axis, taking out code disc information of the starting position and the ending position of the number of lines, namely the range of code disc dimensionality, and adding a certain error range before and after the code disc range, wherein the code disc dimensionality refers to the other unit length of the y axis, and 1 code disc is taken as 1 unit;
step 4.2, preprocessing the one-dimensional signals, filtering the one-dimensional signals according to preset conditions, taking each one-dimensional signal meeting the conditions as a section of signal, and recording a starting coded disc and an ending coded disc of each section of signal meeting the conditions and the highest or lowest storage battery of the section of signal;
4.3, mapping each section of signals meeting the conditions to two-dimensional image signals according to the starting code disc and the ending code disc, and leaving one-dimensional signals in the range of the code disc of the false distinguishing area;
step 4.4, synthesizing the one-dimensional signals, setting a parameter n taking the code disc as a unit according to different conditions, and synthesizing the signals with the signal distance smaller than n into a section of signals;
and 4.5, setting the sum of the code wheel ending and code wheel starting differences of each section of signal in the range of the counterfeit distinguishing area as w, setting the code wheel ending and code wheel starting difference of the range of the counterfeit distinguishing area as w1, and setting the number m of the counterfeit distinguishing area as w/w 1.
Preferably, the comprehensive arbitration for the counterfeit detection area based on the counterfeit detection area score specifically comprises: the comprehensive arbitration of the counterfeit distinguishing area based on the counterfeit distinguishing area score specifically comprises the following steps: and (4) scoring each discrimination region based on the method of steps 4.1 to 4.5, and performing comprehensive arbitration on the discrimination regions based on the score of each discrimination region. .
The device comprises a one-dimensional sensor, a two-dimensional image sensor, a false distinguishing area acquisition module, an algorithm core module, an arbitration module and an output module;
the one-dimensional sensor is used for acquiring one-dimensional signals and acquiring coordinate position information of the one-dimensional signals;
the two-dimensional image sensor is used for acquiring two-dimensional image signals and acquiring coordinate position information of the two-dimensional image signals;
the counterfeit distinguishing area acquisition module is used for predefining the coordinate position of the counterfeit distinguishing area of the paper money to be distinguished;
the algorithm core module is used for mapping the one-dimensional signal, the two-dimensional image signal and the counterfeit distinguishing region to the same dimension, calculating the coverage rate of the counterfeit distinguishing region and calculating the score of the counterfeit distinguishing region based on the coverage rate of the counterfeit distinguishing region;
the arbitration module is used for carrying out comprehensive arbitration on the counterfeit detection area based on the counterfeit detection area score.
Further, mapping the one-dimensional signal, the two-bit image signal, and the counterfeit detection region to the same dimension specifically includes:
mapping one-dimensional signal coordinates: mapping the layout of the one-dimensional signal to an x-axis of a two-dimensional image signal coordinate system according to the one-dimensional signal distribution position of the equipment and the physical size approximately represented by each pixel of the one-dimensional signal;
mapping the signal waveform of the one-dimensional signal: preprocessing the obtained one-dimensional signal, deducing a code disc interval corresponding to the current signal on the two-dimensional image signal by using a code disc difference of a predefined distance between the specific one-dimensional signal and the two-dimensional image signal on a y axis and a front-back relation of the physical positions of the one-dimensional signal and the two-dimensional image signal on the y axis and by using the current code disc value of the one-dimensional signal to perform corresponding addition and subtraction, finding a row number interval by using the code disc interval, mapping the row number interval onto the y axis of an image coordinate system, wherein the row number represents the position of the signal generated if the one-dimensional signal is overlapped with the two-dimensional image sensor on the y axis, and mapping a two-dimensional rectangular area generating the signal by combining the mapped one-dimensional signal coordinate to define the area a; the coded disc difference is obtained by converting the distance between the one-dimensional signal and the two-dimensional image signal from millimeter to a coded disc as a distance unit, the coded disc value is the current coded disc value, and after the machine starts to rotate, the coded disc counts once through each gear and is accumulated in sequence;
mapping the false distinguishing area coordinates: and taking out the predefined counterfeit distinguishing area matched with the denomination and version of the current paper currency, performing inverse transformation on the predefined counterfeit distinguishing area to a two-dimensional image signal based on the affine parameters and the angular point information of the current paper currency to mark, representing the position of the paper currency counterfeit distinguishing area in the current actual data, and defining the position as an area b.
Further, the calculation of the coverage rate of the counterfeit identification area specifically comprises:
describing the area b by coordinates of four corner points; defining an area c representing the position of the one-dimensional signal, wherein the starting position and the width of an x axis of the area are parameters for defining the one-dimensional signal, the starting point of a y axis is a zero point, and the end point is the last, and the calculating steps are as follows:
step 3.21, overlapping the area b and the area c, wherein the overlapped part forms a new rectangle or triangle;
step 3.22, if the rectangle is, dividing the rectangle into two triangles to calculate the area, if the triangle is, directly calculating the area, wherein the area calculation formula uses a Helen formula, and the formula is as follows: given the three sides of the triangle are a1, b1, and c1, respectively, then: p ═ 2 (a1+ b1+ c1)/2, area S ═ sqrt [ p (p-a1) (p-b1) (p-c1) ];
in step 3.23, the area is calculated as S1, taking the one-dimensional signal width as wide and the difference between the highest point and the lowest point on the y-axis of the pseudo-discrimination region after inverse transformation as high, and the coverage rate Per of the pseudo-discrimination region is obtained as S/S1.
Further, the calculation of the counterfeit identification region score specifically comprises:
confirming the range of the number of lines of the pseudo-discrimination area on the y axis, taking out code disc information of starting and ending positions of the number of lines, namely the range of code disc dimensionality, and adding a certain error range before and after the code disc range, wherein the code disc dimensionality refers to another unit length of the y axis, and 1 code disc is taken as 1 unit;
preprocessing one-dimensional signals, filtering the one-dimensional signals according to preset conditions, taking each one-dimensional signal meeting the conditions as a section of signal, and recording a starting coded disc and an ending coded disc of each section of signal meeting the conditions and a highest or lowest storage battery of the section of signal;
mapping each section of signals meeting the conditions to two-dimensional image signals according to a starting code disc and an ending code disc, and leaving one-dimensional signals in the range of the code disc of the false distinguishing area;
synthesizing one-dimensional signals, setting a parameter n with a code disc as a unit according to different conditions, and synthesizing a section of signals with the signal interval smaller than n;
and the sum of the end code disc and the start code disc difference of each section of signal code disc arranged in the range of the counterfeit distinguishing area is w, and the difference of the end code disc and the start code disc of the range of the counterfeit distinguishing area is w1, so that the counterfeit distinguishing area fraction m is w/w 1.
Further, the comprehensive arbitration for the counterfeit detection area based on the counterfeit detection area score specifically comprises: and scoring each counterfeit distinguishing region, and performing comprehensive arbitration on the counterfeit distinguishing regions based on the score of each counterfeit distinguishing region.
The invention has the following beneficial effects:
1. this scheme is from paper currency direction of motion's dimensionality with two-dimensional sensor signal stack to accurate location has solved the inaccurate, inefficiency of financial machines equipment one-dimensional sensor location, has distinguished difficult problem, has improved development efficiency, has increased equipment stability and has distinguished pseudo-intensity.
2. The positioning is accurate, and the one-dimensional sensor is virtually overlapped with the two-dimensional sensor on the y axis, so that the percentage of the paper money counterfeit distinguishing area passing through the one-dimensional sensor is calculated.
3. The efficiency is high, what you see is what you get, after the predefining step is finished, the running state of the paper currency can be clearly known only by looking at the coverage percentage calculated in the middle, so that the arbitration is simplified.
4. The distinguishing is easy, when the special one-dimensional sensor is faced, the specific area of the paper currency can be accurately selected, and therefore whether the signal is generated in the area where the paper currency originally has the characteristics or not can be accurately positioned.
Drawings
Fig. 1 is a method for assisting the discrimination of a one-dimensional signal by a two-dimensional signal of a financial instrument according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the present invention, and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
As shown in fig. 1, as a first embodiment of the present invention, there is provided a method for two-dimensional signal-assisted one-dimensional signal authentication of a financial instrument, the method including:
step 1, predefining the coordinate position of the counterfeit distinguishing area of the paper money to be distinguished, wherein the paper money needing counterfeit distinguishing in the running process of the equipment needs to calibrate the counterfeit distinguishing area of the paper money with the designated denomination and version one by one in advance, and the method comprises the following steps: 1. and calibrating the range of the counterfeit identification area, wherein the range comprises a starting x-axis coordinate, a starting y-axis coordinate, an area length and an area width relative to a zero point. 2. And calibrating the counterfeit identification region type, such as a magnetic region, an infrared region, an ultraviolet region, a thickness measuring region and the like. 3. Calibrating the type characteristics of the counterfeit identification area, such as whether the magnetic area is nonmagnetic, weak magnetic or strong magnetic;
step 2, acquiring one-dimensional signals and two-dimensional image signals respectively acquired by a one-dimensional sensor and a two-dimensional image sensor of financial equipment, acquiring coordinate position information of each signal, and marking the positions of all the one-dimensional signals of the equipment relative to the x axis and the y axis of the two-dimensional image signals one by one according to the distribution position of the sensors of the equipment, wherein the method comprises the following steps: 1. sensor types, including but not limited to: the device comprises a coil magnetic head, a long magnetic head, infrared transmission geminate transistors, infrared reflection geminate transistors, a thickness measuring module, ultraviolet reflection geminate transistors and the like. 2. A sensor coverage area comprising: x-axis width of the acquired image signal, x-axis starting position. 3. The distance between the y-axis direction of the image signal and cis is finally converted into the distance of the code disc;
step 3, acquiring all data of the paper money passing through the equipment channel through the input device, and acquiring the denomination, version, direction, angular point coordinates and affine transformation coordinates of the current paper money through other modules; the other modules comprise a denomination identification module and a corner calculation module; the denomination recognition module is used for recognizing the denomination, version and direction of the current two-dimensional image signal, and the corner point module is used for calculating four corner points and affine parameters of the paper money in the current image.
Step 4, mapping the one-dimensional signal, the two-position image signal and the counterfeit distinguishing area to the same dimension, virtually overlapping the one-dimensional signal and the two-dimensional image signal on the y axis, and judging the spatial position of the paper money when the paper money passes through each one-dimensional sensor, so that the percentage of the specific area of the paper money passing through the one-dimensional sensor is judged, and the coverage rate of the counterfeit distinguishing area is calculated;
and 5, calculating the score of the counterfeit distinguishing area based on the coverage rate of the counterfeit distinguishing area, and performing comprehensive arbitration on the counterfeit distinguishing area based on the score of the counterfeit distinguishing area.
Preferably, the mapping the coordinate positions of the one-dimensional signal, the two-dimensional image signal and the counterfeit identifying area to the same dimension specifically includes:
step 3.11, mapping one-dimensional signal coordinates: mapping the layout of the one-dimensional signal to an x-axis of a two-dimensional image signal coordinate system according to the one-dimensional signal distribution position of the equipment and the physical size approximately represented by each pixel of the one-dimensional signal;
step 3.12, mapping the signal waveform of the one-dimensional signal: preprocessing the obtained one-dimensional signal, deducing a code disc interval corresponding to the current one-dimensional signal on the two-dimensional image signal by using a code disc difference of a predefined distance between the specific one-dimensional signal and the two-dimensional image signal on a y axis and a front-back relation of a physical position of the one-dimensional signal and the two-dimensional image signal on the y axis and by using a current code disc value of the one-dimensional signal to perform corresponding addition and subtraction, finding a row number interval by using the code disc interval, mapping the row number interval onto the y axis of an image coordinate system, wherein the section of coordinate represents the position of a signal generated if the one-dimensional signal is overlapped with the two-dimensional image sensor on the y axis, and mapping a two-dimensional rectangular area generating the signal by combining with the step 3.11 to define the area a; the coded disc difference is obtained by converting the distance between the one-dimensional signal and the two-dimensional image signal from millimeter to a coded disc as a distance unit, the coded disc value is the current coded disc value, and after the machine starts to rotate, the coded disc counts once through each gear and is accumulated in sequence;
step 3.13, mapping the coordinates of the counterfeit distinguishing area: and taking out the predefined counterfeit distinguishing area matched with the denomination and version of the current paper currency, performing inverse transformation on the predefined counterfeit distinguishing area to a two-dimensional image signal based on the affine parameters and the angular point information of the current paper currency to mark, representing the position of the paper currency counterfeit distinguishing area in the current actual data, and defining the position as an area b.
Preferably, the calculating the coverage of the counterfeit detection area specifically includes: describing the area b by coordinates of four corner points; defining an area c representing the position of the one-dimensional signal, wherein the starting position and the width of an x axis of the area are parameters for defining the one-dimensional signal, the starting point of a y axis is a zero point, and the end point is the last, and the calculating steps are as follows:
step 3.21, overlapping the area b and the area c, wherein the overlapped part forms a new rectangle or triangle;
step 3.22, if the rectangle is, dividing the rectangle into two triangles to calculate the area, if the triangle is, directly calculating the area, wherein the area calculation formula uses a Helen formula, and the formula is as follows: given the three sides of the triangle are a1, b1, and c1, respectively, then: p ═ 2 (a1+ b1+ c1)/2, area S ═ sqrt [ p (p-a1) (p-b1) (p-c1) ].
Preferably, the calculating the counterfeit identifying region score specifically includes:
step 4.1, confirming the range of the number of lines of the false distinguishing area on the y axis, taking out code disc information of the starting position and the ending position of the number of lines, namely the range of code disc dimensionality, and adding a certain error range before and after the code disc range, wherein the code disc dimensionality refers to the other unit length of the y axis, and 1 code disc is taken as 1 unit;
step 4.2, preprocessing the one-dimensional signals, filtering the one-dimensional signals according to preset conditions, taking each one-dimensional signal meeting the conditions as a section of signal, and recording a starting coded disc and an ending coded disc of each section of signal meeting the conditions and the highest or lowest storage battery of the section of signal;
4.3, mapping each section of signals meeting the conditions to two-dimensional image signals according to the starting code disc and the ending code disc, and leaving one-dimensional signals in the range of the code disc of the false distinguishing area;
step 4.4, synthesizing the one-dimensional signals, setting a parameter n taking the code disc as a unit according to different conditions, and synthesizing the signals with the signal distance smaller than n into a section of signals;
and 4.5, setting the sum of the code wheel ending and code wheel starting differences of each section of signal in the range of the counterfeit distinguishing area as w, setting the code wheel ending and code wheel starting difference of the range of the counterfeit distinguishing area as w1, and setting the number m of the counterfeit distinguishing area as w/w 1.
Preferably, the comprehensive arbitration for the counterfeit detection area based on the counterfeit detection area score specifically comprises: and (4) scoring each discrimination region based on the method of steps 4.1 to 4.5, and performing comprehensive arbitration on the discrimination regions based on the score of each discrimination region. Each authentication region has different authentication functions, including but not limited to the following functions: detecting whether magnetism exists; detecting whether magnetism is absent; detecting whether fluorescence exists; detecting whether the fluorescence is absent; detecting whether the safety line is in a long magnetic range; detecting whether the thickness exceeds the range; detecting whether there is a reflection abnormality, etc. Due to the difference of the sizes of the counterfeit identification areas and the difference of the distribution densities of the one-dimensional sensors, one counterfeit identification area may pass through a plurality of one-dimensional sensors at the same time, and different comprehensive arbitration strategies need to be carried out by synthesizing signals of each passing one-dimensional sensor and the current anti-counterfeiting grade;
the long magnetic range is the effective range of the one-dimensional long magnetic sensor on the x-axis.
And (3) outputting a result of the counterfeit identification area: after the comprehensive arbitration is finished, a final arbitration result is given and a result confidence coefficient is given at the same time.
As a second aspect of the present invention, a device for assisting in identifying a counterfeit of a one-dimensional signal by a two-dimensional signal of a financial instrument is provided, the device comprising a one-dimensional sensor, a two-dimensional image sensor, a counterfeit identifying area obtaining module, a one-dimensional sensor algorithm core module, an arbitration module, and an output module;
the method for acquiring one-dimensional signals comprises the following steps: one-dimensional paper money denomination, version, direction and signal preprocessing intermediate results;
the two-dimensional image sensor is used for acquiring two-dimensional image signals and comprises: image code disc information, image angular points, image width, image height, actual data width of each line of an image, an image original starting pointer, image calculation denomination, version, direction, image channel number, image brake points and anti-counterfeiting grade;
the counterfeit distinguishing area acquisition module is used for predefining the coordinate position of the counterfeit distinguishing area of the paper money to be distinguished;
the algorithm core module is used for mapping the one-dimensional signal, the two-dimensional image signal and the counterfeit distinguishing region to the same dimension, calculating the coverage rate of the counterfeit distinguishing region and calculating the score of the counterfeit distinguishing region based on the coverage rate of the counterfeit distinguishing region;
the arbitration module is used for carrying out comprehensive arbitration on the counterfeit detection area based on the counterfeit detection area score.
Preferably, the mapping of the one-dimensional signal, the two-bit image signal and the counterfeit detection region to the same dimension is specifically:
mapping one-dimensional signal coordinates: mapping the layout of the one-dimensional signal to an x-axis of a two-dimensional image signal coordinate system according to the one-dimensional signal distribution position of the equipment and the physical size approximately represented by each pixel of the one-dimensional signal;
mapping the signal waveform of the one-dimensional signal: preprocessing the obtained one-dimensional signal, deducing a code disc interval corresponding to the current signal on the image by using a code disc difference of a predefined distance between the specific one-dimensional signal and the two-dimensional image signal on a y axis and a front-back relation of the physical positions of the one-dimensional signal and the two-dimensional image signal on the y axis and by using the current code disc value of the one-dimensional signal to perform corresponding addition and subtraction, finding a row number interval through the code disc interval, mapping the row number interval onto the y axis of an image coordinate system, wherein the row number represents the position of the signal generated if the one-dimensional signal is overlapped with the two-dimensional image sensor on the y axis, and mapping the one-dimensional signal coordinate to obtain a two-dimensional rectangular area for generating the signal, which is defined as an area a; the coded disc difference is obtained by converting the distance between the one-dimensional signal and the two-dimensional image signal from millimeter to a coded disc as a distance unit, the coded disc value is the current coded disc value, and after the machine starts to rotate, the coded disc counts once through each gear and is accumulated in sequence;
mapping the false distinguishing area coordinates: and taking out the predefined counterfeit distinguishing area matched with the denomination and version of the current paper currency, performing inverse transformation on the predefined counterfeit distinguishing area to a two-dimensional image signal based on the affine parameters and the angular point information of the current paper currency to mark, representing the position of the paper currency counterfeit distinguishing area in the current actual data, and defining the position as an area b.
Preferably, the calculating the coverage rate of the counterfeit detection area specifically comprises:
describing the area b by coordinates of four corner points; defining an area c representing the position of the one-dimensional signal, wherein the starting position and the width of an x axis of the area are parameters defined by the one-dimensional signal, the parameters are equivalent to the width of the one-dimensional signal and are determined by the size and the position of the sensor, the size and the position of each sensor of the same machine are fixed, the starting point of a y axis is a zero point, the ending point is the last, and the calculation steps are as follows:
step 3.21, overlapping the area b and the area c, wherein the overlapped part forms a new rectangle or triangle;
step 3.22, if the rectangle is, dividing the rectangle into two triangles to calculate the area, if the triangle is, directly calculating the area, wherein the area calculation formula uses a Helen formula, and the formula is as follows: given the three sides of the triangle are a1, b1, and c1, respectively, then: p ═ 2 (a1+ b1+ c1)/2, area S ═ sqrt [ p (p-a1) (p-b1) (p-c1) ];
in step 3.23, the area is calculated as S1, taking the one-dimensional signal width as wide and the difference between the highest point and the lowest point on the y-axis of the pseudo-discrimination region after inverse transformation as high, and the coverage rate Per of the pseudo-discrimination region is obtained as S/S1.
Preferably, the calculating the counterfeit identifying region score specifically comprises:
confirming the range of the number of lines of the pseudo-discrimination area on the y axis, taking out code disc information of starting and ending positions of the number of lines, namely the range of code disc dimensionality, and adding a certain error range before and after the code disc range, wherein the code disc dimensionality refers to another unit length of the y axis, and 1 code disc is taken as 1 unit;
preprocessing one-dimensional signals, filtering the one-dimensional signals according to preset conditions, taking each one-dimensional signal meeting the conditions as a section of signal, and recording a starting coded disc and an ending coded disc of each section of signal meeting the conditions and a highest or lowest storage battery of the section of signal;
mapping each section of signals meeting the conditions to two-dimensional image signals according to a starting code disc and an ending code disc, and leaving one-dimensional signals in the range of the code disc of the false distinguishing area;
synthesizing one-dimensional signals, setting a parameter n with a code disc as a unit according to different conditions, and synthesizing a section of signals with the signal interval smaller than n;
and the sum of the end code disc and the start code disc difference of each section of signal code disc arranged in the range of the counterfeit distinguishing area is w, and the difference of the end code disc and the start code disc of the range of the counterfeit distinguishing area is w1, so that the counterfeit distinguishing area fraction m is w/w 1.
Further, the comprehensive arbitration for the counterfeit detection area based on the counterfeit detection area score specifically comprises: and scoring each counterfeit distinguishing region, and performing comprehensive arbitration on the counterfeit distinguishing regions based on the score of each counterfeit distinguishing region.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.
Claims (6)
1. A method for assisting the discrimination of one-dimensional signals by two-dimensional signals of a financial tool is characterized by comprising the following steps:
step 1, predefining the coordinate position of a counterfeit discrimination area of paper money to be discriminated;
step 2, acquiring one-dimensional signals and two-dimensional image signals respectively acquired by a one-dimensional sensor and a two-dimensional image sensor of financial equipment, and acquiring coordinate position information of each signal;
step 3, mapping the one-dimensional signal, the two-dimensional image signal and the counterfeit distinguishing area to the same dimension, and calculating the coverage rate of the counterfeit distinguishing area;
step 4, calculating the score of the counterfeit distinguishing area based on the coverage rate of the counterfeit distinguishing area, and performing comprehensive arbitration on the counterfeit distinguishing area based on the score of the counterfeit distinguishing area;
the mapping of the coordinate positions of the one-dimensional signal, the two-dimensional image signal and the counterfeit distinguishing area to the same dimension specifically comprises the following steps:
step 3.11, mapping one-dimensional signal coordinates: mapping the layout of the one-dimensional signal to an x-axis of a two-dimensional image signal coordinate system according to the one-dimensional signal distribution position of the equipment and the physical size represented by each pixel of the one-dimensional signal;
step 3.12, mapping the signal waveform of the one-dimensional signal: preprocessing the obtained one-dimensional signal, deducing a code disc interval corresponding to the current one-dimensional signal on the two-dimensional image signal by using a code disc difference of a predefined distance between the specific one-dimensional signal and the two-dimensional image signal on a y axis and a front-back relation of a physical position of the one-dimensional signal and the two-dimensional image signal on the y axis and by using a current code disc value of the one-dimensional signal to perform corresponding addition and subtraction, finding a row number interval by using the code disc interval, mapping the row number interval onto the y axis of an image coordinate system, wherein the section of coordinate represents the position of a signal generated if the one-dimensional signal is overlapped with the two-dimensional image sensor on the y axis, and mapping a two-dimensional rectangular area generating the signal by combining with the step 3.11 to define the area a; the coded disc difference is obtained by converting the distance between the one-dimensional signal and the two-dimensional image signal from millimeter to a coded disc as a distance unit, the coded disc value is the current coded disc value, and after the machine starts to rotate, the coded disc counts once through each gear and is accumulated in sequence;
step 3.13, mapping the coordinates of the counterfeit distinguishing area: taking out the predefined counterfeit distinguishing area matched with the denomination and version of the current paper currency, performing inverse transformation on the predefined counterfeit distinguishing area to a two-dimensional image signal based on affine parameters and angular point information of the current paper currency to mark the predefined counterfeit distinguishing area, representing the position of the paper currency counterfeit distinguishing area in the current actual data, and defining the area as an area b;
wherein, calculating the coverage rate of the counterfeit distinguishing area specifically comprises: describing the area b by coordinates of four corner points; defining an area c representing the position of the one-dimensional signal, wherein the starting position and the width of an x axis of the area are parameters for defining the one-dimensional signal, and the starting point of a y axis is a zero point, and the calculating steps are as follows:
step 3.21, overlapping the area b and the area c, wherein the overlapped part forms a new rectangle or triangle;
step 3.22, if the rectangle is, dividing the rectangle into two triangles to calculate the area, if the triangle is, directly calculating the area, wherein the area calculation formula uses a Helen formula, and the formula is as follows: given the three sides of the triangle are a1, b1, and c1, respectively, then: p = (a1+ b1+ c1)/2, area S = sqrt [ p (p-a1) (p-b1) (p-c1) ];
and 3.23, calculating the area to be S1 by taking the width of the one-dimensional signal as wide and the difference between the highest point and the lowest point on the y axis of the pseudo-discrimination area after inverse transformation as high, and obtaining the coverage rate Per = S/S1 of the pseudo-discrimination area.
2. The method of claim 1, wherein calculating the discrimination zone score comprises:
step 4.1, confirming the range of the number of lines of the false distinguishing area on the y axis, taking out code disc information of the starting position and the ending position of the number of lines, namely the range of code disc dimensionality, and adding a certain error range before and after the code disc range, wherein the code disc dimensionality refers to the other unit length of the y axis, and 1 code disc is taken as 1 unit;
step 4.2, preprocessing the one-dimensional signals, filtering the one-dimensional signals according to preset conditions, taking each one-dimensional signal meeting the conditions as a section of signal, and recording a starting coded disc and an ending coded disc of each section of signal meeting the conditions and the highest or lowest storage battery of the section of signal;
4.3, mapping each section of signals meeting the conditions to two-dimensional image signals according to the starting code disc and the ending code disc, and leaving one-dimensional signals in the range of the code disc of the false distinguishing area;
step 4.4, synthesizing the one-dimensional signals, setting a parameter n taking the code disc as a unit according to different conditions, and synthesizing the signals with the signal distance smaller than n into a section of signals;
and 4.5, if the sum of the code wheel ending and code wheel starting differences of each section of signal in the range of the counterfeit distinguishing area is w, and the code wheel ending and code wheel starting difference of the range of the counterfeit distinguishing area is w1, the counterfeit distinguishing area is m = w/w 1.
3. The method as claimed in claim 2, wherein the comprehensive arbitration of the counterfeit discriminating region based on the score of the counterfeit discriminating region comprises: and (4) scoring each discrimination region based on the method of steps 4.1 to 4.5, and performing comprehensive arbitration on the discrimination regions based on the score of each discrimination region.
4. The device for assisting the counterfeit discrimination of the one-dimensional signal by the two-dimensional signal of the financial machine is characterized by comprising a one-dimensional sensor, a two-dimensional image sensor, a counterfeit discrimination area acquisition module, an algorithm core module, an arbitration module and an output module;
the one-dimensional sensor is used for acquiring one-dimensional signals and acquiring coordinate position information of the one-dimensional signals;
the two-dimensional image sensor is used for acquiring two-dimensional image signals and acquiring coordinate position information of the two-dimensional image signals;
the counterfeit distinguishing area acquisition module is used for predefining the coordinate position of the counterfeit distinguishing area of the paper money to be distinguished;
the algorithm core module is used for mapping the one-dimensional signal, the two-dimensional image signal and the counterfeit distinguishing region to the same dimension, calculating the coverage rate of the counterfeit distinguishing region and calculating the score of the counterfeit distinguishing region based on the coverage rate of the counterfeit distinguishing region;
the arbitration module is used for carrying out comprehensive arbitration on the counterfeit distinguishing area based on the counterfeit distinguishing area score;
the mapping of the coordinate positions of the one-dimensional signal, the two-dimensional image signal and the counterfeit distinguishing area to the same dimension specifically comprises the following steps:
step 3.11, mapping one-dimensional signal coordinates: mapping the layout of the one-dimensional signal to an x-axis of a two-dimensional image signal coordinate system according to the one-dimensional signal distribution position of the equipment and the physical size represented by each pixel of the one-dimensional signal;
step 3.12, mapping the signal waveform of the one-dimensional signal: preprocessing the obtained one-dimensional signal, deducing a code disc interval corresponding to the current one-dimensional signal on the two-dimensional image signal by using a code disc difference of a predefined distance between the specific one-dimensional signal and the two-dimensional image signal on a y axis and a front-back relation of a physical position of the one-dimensional signal and the two-dimensional image signal on the y axis and by using a current code disc value of the one-dimensional signal to perform corresponding addition and subtraction, finding a row number interval by using the code disc interval, mapping the row number interval onto the y axis of an image coordinate system, wherein the section of coordinate represents the position of a signal generated if the one-dimensional signal is overlapped with the two-dimensional image sensor on the y axis, and mapping a two-dimensional rectangular area generating the signal by combining with the step 3.11 to define the area a; the coded disc difference is obtained by converting the distance between the one-dimensional signal and the two-dimensional image signal from millimeter to a coded disc as a distance unit, the coded disc value is the current coded disc value, and after the machine starts to rotate, the coded disc counts once through each gear and is accumulated in sequence;
step 3.13, mapping the coordinates of the counterfeit distinguishing area: taking out the predefined counterfeit distinguishing area matched with the denomination and version of the current paper currency, performing inverse transformation on the predefined counterfeit distinguishing area to a two-dimensional image signal based on affine parameters and angular point information of the current paper currency to mark the predefined counterfeit distinguishing area, representing the position of the paper currency counterfeit distinguishing area in the current actual data, and defining the area as an area b;
wherein, the calculation of the coverage rate of the counterfeit distinguishing area specifically comprises the following steps:
describing the area b by coordinates of four corner points; defining an area c representing the position of the one-dimensional signal, wherein the starting position and the width of an x axis of the area are parameters for defining the one-dimensional signal, and the starting point of a y axis is a zero point, and the calculating steps are as follows:
step 3.21, overlapping the area b and the area c, wherein the overlapped part forms a new rectangle or triangle;
step 3.22, if the rectangle is, dividing the rectangle into two triangles to calculate the area, if the triangle is, directly calculating the area, wherein the area calculation formula uses a Helen formula, and the formula is as follows: given the three sides of the triangle are a1, b1, and c1, respectively, then: p = (a1+ b1+ c1)/2, area S = sqrt [ p (p-a1) (p-b1) (p-c1) ];
and 3.23, calculating the area to be S1 by taking the width of the one-dimensional signal as wide and the difference between the highest point and the lowest point on the y axis of the pseudo-discrimination area after inverse transformation as high, and obtaining the coverage rate Per = S/S1 of the pseudo-discrimination area.
5. The apparatus of claim 4, wherein the means for calculating the discrimination area score comprises:
confirming the range of the number of lines of the pseudo-discrimination area on the y axis, taking out code disc information of starting and ending positions of the number of lines, namely the range of code disc dimensionality, and adding a certain error range before and after the code disc range, wherein the code disc dimensionality refers to another unit length of the y axis, and 1 code disc is taken as 1 unit;
preprocessing one-dimensional signals, filtering the one-dimensional signals according to preset conditions, taking each one-dimensional signal meeting the conditions as a section of signal, and recording a starting coded disc and an ending coded disc of each section of signal meeting the conditions and a highest or lowest storage battery of the section of signal;
mapping each section of signals meeting the conditions to two-dimensional image signals according to a starting code disc and an ending code disc, and leaving one-dimensional signals in the range of the code disc of the false distinguishing area;
synthesizing one-dimensional signals, setting a parameter n with a code disc as a unit according to different conditions, and synthesizing a section of signals with the signal interval smaller than n;
and the sum of the end code disc and the start code disc difference of each section of signal code disc arranged in the range of the counterfeit distinguishing area is w, and the end code disc and start code disc difference of the range of the counterfeit distinguishing area is w1, so that the counterfeit distinguishing area is m = w/w 1.
6. The apparatus of claim 5, wherein the comprehensive arbitration of the counterfeit detection zone based on the score of the counterfeit detection zone comprises: and scoring each counterfeit distinguishing region, and performing comprehensive arbitration on the counterfeit distinguishing regions based on the score of each counterfeit distinguishing region.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010308699.3A CN111476937B (en) | 2020-04-18 | 2020-04-18 | Method and device for assisting one-dimensional signal false identification of two-dimensional signal of financial machine |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010308699.3A CN111476937B (en) | 2020-04-18 | 2020-04-18 | Method and device for assisting one-dimensional signal false identification of two-dimensional signal of financial machine |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111476937A CN111476937A (en) | 2020-07-31 |
| CN111476937B true CN111476937B (en) | 2021-11-16 |
Family
ID=71755663
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010308699.3A Active CN111476937B (en) | 2020-04-18 | 2020-04-18 | Method and device for assisting one-dimensional signal false identification of two-dimensional signal of financial machine |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111476937B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH04124791A (en) * | 1990-09-17 | 1992-04-24 | Oki Electric Ind Co Ltd | Paper sheet discriminator |
| CN102136166A (en) * | 2011-01-14 | 2011-07-27 | 哈尔滨工业大学 | Method and device for distinguishing false money by imaging paper money through multimodal information fusion |
| JP2012093874A (en) * | 2010-10-26 | 2012-05-17 | Nippon Conlux Co Ltd | Bill identification device |
| CN102890841A (en) * | 2012-10-08 | 2013-01-23 | 广州广电运通金融电子股份有限公司 | Method and device for identifying valuable documents |
| CN103310256A (en) * | 2013-06-03 | 2013-09-18 | 何南炎 | Methods for preparing and identifying continuous-real-object anti-counterfeit label based on image contrast |
| CN104036290A (en) * | 2014-06-11 | 2014-09-10 | 新达通科技股份有限公司 | Method and device for identifying face value of paper money |
| CN106548558A (en) * | 2016-11-07 | 2017-03-29 | 广州广电运通金融电子股份有限公司 | A kind of detection method and device of bill one-dimensional signal |
| CN108335402A (en) * | 2017-01-18 | 2018-07-27 | 武汉卓目科技有限公司 | A kind of cash inspecting machine infrared tube false distinguishing method based on deep learning |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2007042054A (en) * | 2005-06-27 | 2007-02-15 | Systec:Kk | Recoding one-dimensional/two-dimensional code, recoding one-dimensional/two-dimensional code system, recoding one-dimensional/two-dimensional code encoder and recoding one-dimensional/two-dimensional code decoder |
-
2020
- 2020-04-18 CN CN202010308699.3A patent/CN111476937B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH04124791A (en) * | 1990-09-17 | 1992-04-24 | Oki Electric Ind Co Ltd | Paper sheet discriminator |
| JP2012093874A (en) * | 2010-10-26 | 2012-05-17 | Nippon Conlux Co Ltd | Bill identification device |
| CN102136166A (en) * | 2011-01-14 | 2011-07-27 | 哈尔滨工业大学 | Method and device for distinguishing false money by imaging paper money through multimodal information fusion |
| CN102890841A (en) * | 2012-10-08 | 2013-01-23 | 广州广电运通金融电子股份有限公司 | Method and device for identifying valuable documents |
| CN103310256A (en) * | 2013-06-03 | 2013-09-18 | 何南炎 | Methods for preparing and identifying continuous-real-object anti-counterfeit label based on image contrast |
| CN104036290A (en) * | 2014-06-11 | 2014-09-10 | 新达通科技股份有限公司 | Method and device for identifying face value of paper money |
| CN106548558A (en) * | 2016-11-07 | 2017-03-29 | 广州广电运通金融电子股份有限公司 | A kind of detection method and device of bill one-dimensional signal |
| CN108335402A (en) * | 2017-01-18 | 2018-07-27 | 武汉卓目科技有限公司 | A kind of cash inspecting machine infrared tube false distinguishing method based on deep learning |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111476937A (en) | 2020-07-31 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP2905754B1 (en) | Valuable document authentication method and device | |
| CN102176262B (en) | Thickness detecting method and device for slice medium | |
| JPH0644377A (en) | Device for sorting pattern, particularly pattern of paper money or money | |
| CN105551133A (en) | Banknote splicing seam or crease recognition method and system | |
| JP2009129390A (en) | Medium discrimination device | |
| CN102096961A (en) | Paper currency identifying method and device | |
| CN105006062A (en) | Bill identification method and deposit and withdrawal device | |
| CN106548558A (en) | A kind of detection method and device of bill one-dimensional signal | |
| CN104050749B (en) | A kind of method automatically selecting valuable papers's different characteristic point judgement | |
| CN111476937B (en) | Method and device for assisting one-dimensional signal false identification of two-dimensional signal of financial machine | |
| TW420791B (en) | Method for identifying paper bills such as bank notes | |
| CN106683261A (en) | Method and device for authentic identification of banknote | |
| CN102713982A (en) | Paper sheet identification device and paper sheet identification method | |
| KR101076322B1 (en) | Method for discriminating the authenticity of paper money by using a contact image sensor | |
| CN104517348A (en) | Novel banknote recognition module | |
| CN103903329A (en) | Financial instrument authenticity identification device with front CIS | |
| CN106652157A (en) | Method and device for detection of floating roller magnetism | |
| CN107123187A (en) | A kind of authenticity of banknotes detection method and system | |
| US10922913B2 (en) | Method and apparatus for detecting a security thread in a value document | |
| CN106504406B (en) | A kind of method and device identifying bank note | |
| JPS59180794A (en) | Paper money discrimination system | |
| CN111612965B (en) | Method, apparatus and device for denomination recognition using security thread magnetic encoding | |
| CN112509210A (en) | Banknote image processing method and device, banknote checking equipment and readable storage medium | |
| CN213716038U (en) | Paper currency recognition module and financial machine | |
| CN109685971B (en) | Folded paper money detection method, device and equipment |
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 |