CN104091388B - A kind of paper money discrimination method based on magnetic image and device - Google Patents
A kind of paper money discrimination method based on magnetic image and device Download PDFInfo
- Publication number
- CN104091388B CN104091388B CN201410347515.9A CN201410347515A CN104091388B CN 104091388 B CN104091388 B CN 104091388B CN 201410347515 A CN201410347515 A CN 201410347515A CN 104091388 B CN104091388 B CN 104091388B
- Authority
- CN
- China
- Prior art keywords
- magnetic image
- magnetic
- binaryzation
- image
- module
- 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.)
- Expired - Fee Related
Links
Landscapes
- Inspection Of Paper Currency And Valuable Securities (AREA)
Abstract
A kind of paper money discrimination method and apparatus based on magnetic image of disclosure, the magnetic image of the bank note that magnetic image sensor obtains is processed, after magnetic image is carried out the pretreatment such as image enhancement processing and slant correction, calculate magnetic image rectangular histogram, carry out binary conversion treatment, cut out the binaryzation magnetic image of two width safety lines, two width binaryzation magnetic images after cutting are carried out floor projection, judge whether the feature of the impulse waveform of two secondary binaryzation magnetic image floor projection curves of safety line meets setting regulation, if all meeting setting regulation, then it is judged as genuine note。Owing to adopting two threshold values of height that magnetic image is carried out binaryzation in the present invention, and cut out the binaryzation magnetic image of two width safety lines, the feature of the binaryzation magnetic image of this two width safety line is identified, if the feature of the binaryzation magnetic image of two width safety lines all meets the requirements just is judged to genuine note。
Description
Technical field
The present invention relates to paper money discrimination field, particularly to a kind of paper money discrimination method based on magnetic image and device。
Background technology
Bank note false proof, is the major issue being related to country's financial stability, closely bound up with people's property safety。ATM as the bank self-help most crucial product of service, provides 24 hours transfer accounts for people, withdraws the money, deposit business, and this not only eliminates substantial amounts of human cost to bank, but also facilitates the life of people。Progress along with science and technology, the anti-counterfeiting technology of RMB is increasingly advanced, bank note obtains false proof point get more and more, but thing followed fraud means are more and more brilliant, emulator is more and more higher, ATM as 24 hour self-help equipment, bank note false proof particularly important, it may be said that it is the equipment requiring false distinguishing ability the strongest in finance device。ATM does not allow to take out counterfeit money, is not stored in counterfeit money yet, but this is all ideal situation, due to the progress of the technology of rehearsing, often can see that so-and-so gets counterfeit money or certain bank outlets is stored in the news of counterfeit money at bank ATM。Constantly there is counterfeit money event in ATM, and this makes to require that ATM is not when affecting normal currency examination with note output, improves the anti-counterfeit capability of bank note to greatest extent。
At present, ATM false proof, main adopt multispectral image analysis and the detection of bank note magnetic signal。The sensor that multispectral figure adopts is based on contact-type image sensor (CIS), it is possible to gathers out and includes infrared external reflection figure, infrared transmission figure, ultraviolet reflectance figure etc.。Magnetic detection on bank note, what adopt is magneto-dependent sensor, also known as magnetic head, current financial machine and tool paper money counter, ATM adopts such sensor exactly, in the false distinguishing passage being distributed in bank note that several roads magnetic head is discrete, when bank note is by magnetic head, each magnetic head is respectively induced out One-Dimension Magnetic signal waveform, this magnetic code that can detect in RMB in safety line, but it is not high that its shortcoming is accuracy of detection, and detection reliability has much room for improvement。
Summary of the invention
It is an object of the invention to provide a kind of paper money discrimination method based on magnetic image, the method adopts high and low two threshold values that the magnetic image in safety line in RMB is carried out binaryzation, and two binaryzation magnetic image floor projection curves are carried out false distinguishing respectively, only the false distinguishing of Liang Ge drop shadow curve is all passed through just to think genuine note, is effectively improved credibility。
The technical solution adopted in the present invention is: a kind of paper money discrimination method based on magnetic image, the magnetic image of the bank note that magnetic image sensor obtains is processed, after magnetic image is carried out the pretreatment such as image enhancement processing and slant correction, comprises the following steps:
Step 1, calculate magnetic image rectangular histogram, in histogrammic Far Left with interval, intermediate peak position, take a Low threshold, in intermediate peak with rectangular histogram rightmost interval, take a high threshold；
Step 2, carry out binary conversion treatment, according to high and low dual threshold, obtain two width binaryzation magnetic images；
Step 3, two width binaryzation magnetic images are cut, cut out the binaryzation magnetic image of two width safety lines；
Step 4, to cutting after two width binaryzation magnetic images carry out floor projection；
Step 5, judging whether the feature of the impulse waveform of two secondary binaryzation magnetic image floor projection curves of safety line meets setting regulation, if all meeting setting regulation, being then judged as genuine note。
Owing to adopting two threshold values of height that magnetic image is carried out binaryzation in the present invention, and cut out the binaryzation magnetic image of two width safety lines, the feature of the binaryzation magnetic image of this two width safety line is identified, if the feature of the binaryzation magnetic image of two width safety lines all meets the requirements just is judged to genuine note。
The present invention's it is preferable that slant correction comprises the following steps:
First pass through safety line discrete magnetic image distribution, the safety line magnetic image straight line that matching discrete point magnetic image is constituted, namely adopting method of least square, calculating slope k and the intercept b of safety line magnetic image straight line, thus obtaining inclined angle alpha；
With magnetic image central point, adopt the interpolation algorithm of nearest neighbor interpolation that magnetic image is carried out slant correction α。
When cutting out safety line magnetic image, the magnetic image after high and low threshold binarization is adopted following steps:
Find the left upper apex (x of safety line magnetic code image0,y0),
1/3 part in the middle of magnetic image after Low threshold binaryzation is carried out vertical sweep from left to right, when scanning the row occurred lower than setting threshold value, is required x0,
Magnetic image after Low threshold binaryzation is carried out from top to bottom horizontal sweep, to when scanning the row occurred lower than setting threshold value, is required y0,
Find the bottom right vertex (x of safety line magnetic code image1,y1)。
1/3 part in the middle of magnetic image after Low threshold binaryzation is carried out vertical sweep from right to left, when scanning the row occurred lower than setting threshold value, is required x1,
Magnetic image after Low threshold binaryzation is carried out from bottom to up horizontal sweep, to when scanning the row occurred lower than setting threshold value, is required y1。
The feature of the impulse waveform of binaryzation magnetic image floor projection curve:
The impulse waveform of the binaryzation magnetic image floor projection curve of high threshold is in periodically, and each cycle first becomes amplitude, then returns 0, then is low amplitude value, then returns 0 again；
The impulse waveform of the binaryzation magnetic image floor projection curve of low valve valve is in the periodicity consistent with the impulse waveform cycle of the binaryzation magnetic image floor projection curve of high threshold, each cycle first becomes negative amplitude signal, followed by amplitude reference signal, it is little negative amplitude signal again, eventually passes back to amplitude reference signal。
The present invention also provides for a kind of paper money discrimination device, bank note is carried out false distinguishing by detecting the feature of the magnetic image on bank note by this device, including magnetic image acquisition device, also include that the magnetic image that described magnetic image acquisition device is acquired is carried out the method for claim 1 and carry out the process device of false distinguishing process。
ATM etc. is provided with this device and can be effectively improved the false distinguishing ability of bank note。
Below in conjunction with specific embodiment, the present invention is described in more detail。
Accompanying drawing explanation
Fig. 1 is magnetic image information processing and false distinguishing main flow。
Fig. 2 is safety line magnetic code region magnetic image rectangular histogram。
Fig. 3 is the magnetic image schematic diagram after Low threshold binaryzation。
Fig. 4 is the magnetic image schematic diagram after high threshold binaryzation。
Fig. 5 is Low threshold safety line magnetic code image level drop shadow curve figure。
Fig. 6 is high threshold safety line magnetic code image level drop shadow curve figure。
Detailed description of the invention
The present embodiment is a kind of paper money discrimination device, bank note is carried out false distinguishing by detecting the feature of the magnetic image on bank note by this device, the process device that RMB magnetic image including magnetic image acquisition device with to the acquisition of magnetic image acquisition device processes, this process device obtains the magnetic image in RMB initially with magnetic image sensor, then it is digitized magnetic image processing, this device includes magnetic image acquisition device, storage has the data base of bank note magnetic image characteristic, enhancement process module, slant correction module, histogram calculation module, binary conversion treatment module, safety line cutting module, the module such as projection module and judge module。
Wherein:
The input of histogram calculation module is connected with the outfan of magnetic image acquisition device；The outfan of histogram calculation module is connected with the input of binary conversion treatment module；The outfan of binary conversion treatment module is connected with the input of safety line cutting module；The outfan of binary conversion treatment module is connected with the input of projection module；The input of judge module is connected with the outfan of projection module and data base respectively, it is judged that the instruction device such as display screen etc. whether the module outfan bank note detected with instruction is genuine note is connected。
The magnetic image of the detected bank note that magnetic image acquisition device is obtained by enhancement process module carries out the magnetic image that image enhancement processing output strengthens；
The magnetic image of the enhancing of described enhancement process module output is carried out slant correction by slant correction module, exports the magnetic image through slant correction and exports histogram calculation module。
Histogram calculation module calculates the magnetic image rectangular histogram through slant correction。
The magnetic image rectangular histogram binaryzation that histogram calculation module is calculated by binary conversion treatment module generates binaryzation magnetic image, takes a Low threshold and takes a high threshold in intermediate peak with rectangular histogram rightmost interval in the histogrammic Far Left of the threshold values that binary conversion treatment module adopts respectively magnetic image and interval, intermediate peak position。
The binaryzation magnetic image that safety line cutting module cutting binary conversion treatment module generates, therefrom cuts out the binaryzation magnetic image of safety line。
The binaryzation magnetic image of safety line is carried out floor projection by projection module, forms the floor projection curve of the binaryzation magnetic image of safety line；
The floor projection curve magnetic image characteristic corresponding with the bank note preserved in feature database of described projection module output is compared by judge module, it is thus achieved that whether the bank note being detected is the result of genuine note。
Comprise the following steps:
Magnetic image is carried out image enhancement processing by step A, employing enhancement process module；
Carry out magnetic image strengthening is exactly that magnetic image is carried out contrast enhancement processing。Purpose is that with soft magnetism, Hard Magnetic image, safety line magnetic code image, prefix code region magnetic image are carried out enhancement process, reduce bank note magnetic transition pixel, by image enhaucament, make white pixel become whiter, black pixel becomes more black, so makes what magnetic signal feature extraction became to be easier to。Assuming that strengthening front magnetic image pixel distribution ranges for [a, b], the enhanced pixel distribution range set of contrast is [c, d], wherein c less than a, d more than b, s pixel value is the pixel currently carrying out contrast enhancement processing, and t is the pixel value after conversion, then contrast stretching formula is, the pixel t obtained through this formula can reach the purpose that contrast strengthens。
Step B, according to safety line magnetic code image, calculate the angle of inclination of bank note；
Step C, according to angle of inclination, magnetic image is carried out slant correction；
Both the above step is completed by slant correction module, it is achieved slant correction, the slant correction of magnetic image。First pass through the straight line that the discrete pixel of safety line magnetic code is constituted, the discrete point coordinate of magnetic code signal is extracted, adopt method of least square, calculate slope k and the intercept b of safety line magnetic code, thus obtaining inclined angle alpha, then with magnetic image central point, magnetic image is carried out slant correction α, in order to accelerate algorithm speed, nor affecting on the quality after image rotation, interpolation algorithm adopts nearest neighbor interpolation here。
Step D, utilize histogram calculation module to calculate magnetic image rectangular histogram, according to rectangular histogram, calculate high and low pair of binary-state threshold of magnetic image；
Step E, magnetic image binaryzation, according to the step D high and low dual threshold obtained, obtain two width binaryzation magnetic images, figure after the binaryzation that Low threshold is corresponding is background is white, prospect is black magnetic image, and the figure after the binaryzation that high threshold is corresponding is background is black, and prospect is white magnetic image；
Both the above step realizes the binaryzation of magnetic image and is realized by binary conversion treatment module。First the grey level histogram of magnetic image is calculated, herein for histogrammic distribution is described, Fig. 2 shows the magnetic image rectangular histogram in safety line region, the histogram shape of whole magnetic image is similar with the magnetic image rectangular histogram in safety line region, as shown in Figure 2, rectangular histogram is the most left is the pixel count that magnetic signal is corresponding with the histogram value of least significant, and intermediate peak figure is magnetic image background area, i.e. non-magnetic pixel count。By analyzing, magnetic image is processed by the binarization method that need to adopt dual threshold, a threshold value is taken in histogrammic Far Left with interval, intermediate peak position, i.e. Low threshold, in intermediate peak with rectangular histogram rightmost interval, take threshold value, i.e. a high threshold, so processed by dual threshold, magnetic image after binaryzation can retain almost all of main information, and facilitates later feature extraction。As it is shown on figure 3, it is white for obtaining a width background after Low threshold binaryzation, prospect is black magnetic image, and as shown in Figure 4, it is black for obtaining a width background after high threshold binaryzation, and prospect is white magnetic image。In Fig. 3, Fig. 4, it is safety line magnetic code image schematic diagram that little rectangle constitutes the image of a vertical straight line, and big rectangular image is prefix code magnetic schematic diagram, and the rectangle of three strips is soft magnetism and Hard Magnetic image schematic diagram。
Step F, cutting safety line magnetic code image；
Cutting safety line magnetic code image it is crucial that determine the region of safety line, the namely coordinate in the coordinate in the upper left corner and the lower right corner or the lower right corner and the upper left corner。Here overlapping 1999 editions, 2005 editions RMB of RMB 50 yuan with the 5th, 100 yuan be example, and as shown in Fig. 3, Fig. 4, the magnetic image major part after binaryzation is the background not having magnetic signal, only safety line magnetic code signal, prefix code region magnetic signal, soft magnetism and Hard Magnetic image。In order to safety line magnetic code signal is done further explication de texte, have to Fig. 3, magnetic code signal black, white on Fig. 4 is cut down, the method of cutting is as follows: owing to magnetic image having been carried out slant correction, as long as finding original position and end position (x, y) coordinate of safety line magnetic code signal here。First look for the left upper apex of magnetic code signal, the magnetic image after Fig. 3 Low threshold binaryzation, in order to add fast speed, 1/3 part in the middle of Fig. 3 is carried out vertical sweep from left to right, when scanning the row occurred lower than setting threshold value, be required x0, then magnetic image is carried out from top to bottom horizontal sweep, to when scanning the row occurred lower than setting threshold value。It is required y0, thus find the left upper apex (x of safety line magnetic code image0,y0), next step looks for the bottom right vertex (x of safety line magnetic code signal1,y1), as long as changing a scanning direction here, look for x1In time, is scanned from right to left, looks for y1Time, scan from bottom to up。After finding left upper apex and the bottom right vertex of safety line magnetic code signal, so that it may this signal is cut。For Fig. 4, the safety line magnetic code image cutting method after high threshold binaryzation is similar, is not discussed herein。Surely, after putting in place, these pixels are taken out。
Two width magnetic code images after cutting are carried out floor projection by step G, safety line cutting module；
The floor projection of safety line magnetic code signal。Safety line magnetic code signal divides the two-value safety line magnetic code image of Low threshold and the two-value safety line magnetic code picture of high threshold, and as shown in Fig. 5, Fig. 6, Fig. 5 is the two-value safety line magnetic code projection picture of Low threshold, and Fig. 6 is the two-value safety line magnetic code projection picture of high threshold。Owing to the bianry image background of Low threshold is white, prospect is black, so when without magnetic signal, projection occurs that maximum is 21, and when having signal, amplitude then declines, signal is more strong, decline more many, and the bianry image background of high threshold is black, prospect is white, and when nonmagnetic number is, projection value is 0, when having signal, amplitude then rises, and signal is more strong, and amplitude is more big。
Step H, by multilevel iudge module realize floor projection curve is carried out rule algorithm research, according to drop shadow curve's rule, bank note is carried out high sensitivity false distinguishing；
The law-analysing of safety line magnetic code drop shadow curve and false distinguishing are crucial, and the rule of safety line magnetic code drop shadow curve is stored in the memorizer of false-identifying device。Fig. 5, Fig. 6 are the 5th set RMB 99 editions, 05 edition 100 yuan safety line magnetic code projections, for the two-value safety line magnetic code projection of Fig. 6 high threshold, preliminary analysis, it can be seen that, impulse wave forms cyclically-varying, and simply amplitude is different, carefully analyzes and draws such rule, waveform first becomes amplitude, then returns 0, then is low amplitude value, then 0 such cyclically-varying is returned again, by such rule, it is possible to carrying out false distinguishing, general counterfeit money is difficult to accomplish this point。The cycle size analyzing it again is how many, different bank note face amounts, the cycle of magnetic code signal is different, as can be drawn from Figure 6, the cycle of safety line magnetic code signal is about 22, includes an amplitude signal here, one low amplitude value signal, two 0 amplitude signals, by such rule, it is believed that this is 100 yuan of genuine notes。By analyzing, the rule of Fig. 5 is such, and its wave period is also about 22, a negative greatly amplitude signal is included inside one cycle, one little negative amplitude signal, two amplitudes are 21 is amplitude reference signal, here it is the two-value safety line magnetic code signal rule of Low threshold。Two-value safety line magnetic code projection for high threshold, safety line magnetic code false distinguishing method is as described below: first detect the cycle of drop shadow curve, the calculating in cycle is with amplitude pulse signal for standard, by scanning projection figure, obtain the position of each amplitude pulse signal, the coordinate figure of later pulse signal is deducted, if the result subtracted each other is between 21 ~ 23, then it is assumed that this bank note magnetic code signal meets the requirements with the coordinate of previous pulse；Then the quantity of high impulse is calculated, if high impulse number is between 14 ~ 18, it is also considered as this bank note magnetic code signal to meet the requirements, finally detect the signal whether containing two 0 amplitudes in each cycle and a low pulse signal again, if signal meets these rules in the major part cycle, meeting is the condition of genuine note, three above condition any one be unsatisfactory for being judged to counterfeit money, reason is false distinguishing parameter have been done in certain limit surplus process, in order to prevent that parameter area is narrow causes that genuine notes are judged to counterfeit money。The two-value safety line magnetic code projection discrimination method of Low threshold is similar with the two-value safety line magnetic code projection of high threshold, first calculate the undersuing cycle, calculate the quantity of negative pulse again, finally detect whether each cycle exists corresponding signal, if these false distinguishing parameters are all satisfied, then it is judged to genuine note, is otherwise counterfeit money。Finally, the two-value magnetic image of dual threshold is adopted, it is possible to carry out safety line magnetic code comprehensively analyzing and detection, it does not have miss any useful information in safety line, enhance the false distinguishing ability of bank note。
In arranging due to the invention process, first magnetic image is carried out slant correction, which solves magneto-dependent sensor and magnetic signal can not be carried out the drawback of slant correction, decrease the tilt of paper money impact on false distinguishing；Then have employed dual-threshold voltage and magnetic image is carried out binaryzation, in contrast to single threshold and process, dual threshold can remain almost all of for magnetic image main information, and this not only facilitates next step signal processing, also makes the curve law after projection highlight；Then bank note safety line magnetic code waveform is carried out Regularity Analysis, according to projection waveform rule, bank note magnetic signal is carried out highly sensitive rate false distinguishing to detect, greatly strengthen the false distinguishing ability of bank note, the present invention also analyzes soft magnetism and Hard Magnetic image rule in RMB, by whether there is soft magnetism to identify the 5th version overlapping RMB with Hard Magnetic signal。
Claims (6)
1., based on a paper money discrimination method for magnetic image, in paper money discrimination device, the magnetic image of the bank note that magnetic image sensor obtains is processed, comprises the following steps:
Step 1, calculate magnetic image rectangular histogram, in histogrammic Far Left with interval, intermediate peak position, take a Low threshold, in intermediate peak with rectangular histogram rightmost interval, take a high threshold；
Step 2, carry out binary conversion treatment, according to high and low dual threshold, obtain two width binaryzation magnetic images；
Step 3, two width binaryzation magnetic images are cut, cut out the binaryzation magnetic image of two width safety lines；
Step 4, the binaryzation magnetic image of two width safety lines after cutting is carried out floor projection；
Step 5, judging whether the impulse waveform of two secondary binaryzation magnetic image floor projection curves of safety line meets setting regulation, if all meeting setting regulation, being then judged as genuine note；
Before step 1, in addition it is also necessary to magnetic image is carried out image enhancement processing and slant correction；Slant correction comprises the following steps:
First pass through safety line discrete magnetic image distribution, the safety line magnetic image straight line that matching discrete point magnetic image is constituted；
Adopting method of least square, calculating slope k and the intercept b of safety line magnetic image straight line, thus obtaining inclined angle alpha；
With magnetic image central point, adopt the interpolation algorithm of nearest neighbor interpolation that magnetic image is carried out slant correction；
It is characterized in that: the magnetic image after high and low threshold binarization is adopted following steps by described step 3:
Find the left upper apex (x of safety line magnetic code image0,y0),
1/3 part in the middle of magnetic image after Low threshold binaryzation is carried out vertical sweep from left to right, when scanning the row occurred lower than setting threshold value, is required x0,
Magnetic image after Low threshold binaryzation is carried out from top to bottom horizontal sweep, to when scanning the row occurred lower than setting threshold value, is required y0,
Find the bottom right vertex (x of safety line magnetic code image1,y1)；
1/3 part in the middle of magnetic image after Low threshold binaryzation is carried out vertical sweep from right to left, when scanning the row occurred lower than setting threshold value, is required x1,
Magnetic image after Low threshold binaryzation is carried out from bottom to up horizontal sweep, to when scanning the row occurred lower than setting threshold value, is required y1。
2. the paper money discrimination method based on magnetic image according to claim 1, it is characterised in that: described setting regulation includes:
The impulse waveform of the binaryzation magnetic image floor projection curve of high threshold is in periodically, and each cycle first becomes amplitude, then returns 0, then is low amplitude value, then returns 0 again；
The impulse waveform of the binaryzation magnetic image floor projection curve of low valve valve is in the periodicity consistent with the impulse waveform cycle of the binaryzation magnetic image floor projection curve of high threshold, each cycle first becomes negative amplitude signal, followed by amplitude reference signal, it is little negative amplitude signal again, eventually passes back to amplitude reference signal。
3. the paper money discrimination method based on magnetic image according to claim 2, it is characterised in that: the detection for the binaryzation magnetic image floor projection curve of high threshold comprises the following steps:
First the cycle of drop shadow curve is detected, the calculating in cycle is with amplitude pulse signal for standard, by scanning projection figure, obtain the position of each amplitude pulse signal, the coordinate figure of later amplitude pulse signal is deducted with the coordinate of previous amplitude pulse, if the result subtracted each other is between 21 ~ 23, then it is assumed that this bank note magnetic code signal meets the requirements；
Then the quantity of high impulse is calculated, if amplitude pulse number is between 14 ~ 18, then it is assumed that this bank note magnetic code signal meets the requirements；
Finally detect the signal whether containing two 0 amplitudes in each cycle and a low pulse signal again, if certainly, then it is genuine note, is otherwise counterfeit money。
4. the paper money discrimination method based on magnetic image according to claim 2, it is characterised in that: the detection for the binaryzation magnetic image floor projection curve of high threshold comprises the following steps:
First the undersuing cycle is calculated, the calculating in cycle is with undersuing for standard, by scanning projection curve chart, obtain the position of each undersuing, the coordinate figure of later undersuing is deducted with the coordinate of previous negative pulse, if the result subtracted each other is between 21 ~ 23, then it is assumed that this bank note magnetic code signal meets the requirements；
Calculate the quantity of negative pulse again, if negative pulse number is between 14 ~ 18, then it is assumed that this bank note magnetic code signal meets the requirements；
Finally detect whether each cycle exists two amplitude reference signals and a little negative amplitude signal, if affirmative is then genuine note, be otherwise counterfeit money。
5. a paper money discrimination device, bank note is carried out false distinguishing by detecting the feature of the magnetic image on bank note by this device, including magnetic image acquisition device, storage has the data base of bank note magnetic image characteristic, it is characterised in that: also include histogram calculation module, binary conversion treatment module, safety line cutting module, projection module and judge module；
The input of described histogram calculation module is connected with the outfan of described magnetic image acquisition device；The outfan of described histogram calculation module is connected with the input of described binary conversion treatment module；The outfan of described binary conversion treatment module is connected with the input of described safety line cutting module；The outfan of described safety line cutting module is connected with the input of described projection module；The input of described judge module is connected with the outfan of described projection module and data base respectively, and the instruction the device whether described judge module outfan bank note detected with instruction is genuine note is connected；
Described histogram calculation module calculates the magnetic image rectangular histogram of the acquired detected bank note of described magnetic image acquisition device；
The magnetic image rectangular histogram binaryzation that described histogram calculation module is calculated by described binary conversion treatment module generates binaryzation magnetic image, takes a Low threshold and takes a high threshold in intermediate peak with rectangular histogram rightmost interval in the threshold values histogrammic Far Left of respectively magnetic image that described binary conversion treatment module adopts and interval, intermediate peak position；
The binaryzation magnetic image that the described binary conversion treatment module described in the cutting of safety line cutting module generates, therefrom cuts out the binaryzation magnetic image of safety line；
The binaryzation magnetic image of safety line is carried out floor projection by described projection module, forms the floor projection curve of the binaryzation magnetic image of safety line；
The floor projection curve magnetic image characteristic corresponding with the bank note preserved in described data base of described projection module output is compared by described judge module, it is thus achieved that whether the bank note being detected is the result of genuine note。
6. paper money discrimination device according to claim 5, it is characterised in that: also include enhancement process module and slant correction module；
The magnetic image of the detected bank note that described magnetic image acquisition device is obtained by described enhancement process module carries out the magnetic image that image enhancement processing output strengthens；
The magnetic image of the enhancing of described enhancement process module output is carried out slant correction by described slant correction module, and the magnetic image through slant correction exports described histogram calculation module。
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410347515.9A CN104091388B (en) | 2014-07-22 | 2014-07-22 | A kind of paper money discrimination method based on magnetic image and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410347515.9A CN104091388B (en) | 2014-07-22 | 2014-07-22 | A kind of paper money discrimination method based on magnetic image and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104091388A CN104091388A (en) | 2014-10-08 |
| CN104091388B true CN104091388B (en) | 2016-06-22 |
Family
ID=51639102
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410347515.9A Expired - Fee Related CN104091388B (en) | 2014-07-22 | 2014-07-22 | A kind of paper money discrimination method based on magnetic image and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104091388B (en) |
Families Citing this family (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104346858B (en) * | 2014-10-10 | 2016-11-02 | 新达通科技股份有限公司 | A kind of bank note face amount recognition methods based on magnetic image and device |
| CN105184953B (en) * | 2015-08-03 | 2017-12-08 | 深圳怡化电脑股份有限公司 | A kind of method and device of bill handling |
| CN105184955B (en) * | 2015-08-18 | 2018-03-02 | 深圳怡化电脑股份有限公司 | A kind of recognition methods of bank note and device |
| CN105719386A (en) * | 2016-01-18 | 2016-06-29 | 新达通科技股份有限公司 | Paper currency identification method and device based on optically-variable hollowed windowing security line |
| CN106251467B (en) * | 2016-08-05 | 2019-03-12 | 深圳怡化电脑股份有限公司 | A kind of detection method and device of safety line magnetic feature |
| CN106447897A (en) * | 2016-08-15 | 2017-02-22 | 深圳怡化电脑股份有限公司 | Method and apparatus for detecting magnetic characteristics of paper note |
| CN106504407B (en) * | 2016-11-01 | 2019-06-07 | 深圳怡化电脑股份有限公司 | A kind of method and device handling banknote image |
| CN108074322B (en) * | 2016-11-17 | 2020-09-15 | 深圳怡化电脑股份有限公司 | Image identification method and device |
| CN107038793B (en) * | 2017-05-02 | 2019-07-09 | 深圳怡化电脑股份有限公司 | A kind of recognition methods, device and the equipment of horizontally-spliced bank note |
| CN107481391B (en) * | 2017-07-03 | 2019-11-19 | 广州广电运通金融电子股份有限公司 | Method and device for detecting graffiti on banknotes |
| CN107369240B (en) * | 2017-07-10 | 2020-03-27 | 深圳怡化电脑股份有限公司 | Paper money counterfeit discrimination method and device, computer and storage medium |
| CN107464333A (en) * | 2017-07-12 | 2017-12-12 | 深圳怡化电脑股份有限公司 | Paper Currency Identification, device and terminal device |
| CN108197512B (en) * | 2018-01-25 | 2021-03-12 | 深圳怡化电脑股份有限公司 | Bill magnetic code recognition method and device, bill processing equipment and storage medium |
| DE102019103723A1 (en) * | 2019-02-14 | 2020-08-20 | TE Connectivity Sensors Germany GmbH | Sensor device and system for detecting a magnetic security feature of a document |
| CN112509209A (en) * | 2019-08-26 | 2021-03-16 | 深圳怡化电脑股份有限公司 | Paper currency magnetic detection method and device, currency detection equipment and readable storage medium |
| CN111627145B (en) * | 2020-05-19 | 2022-06-21 | 武汉卓目科技有限公司 | Method and device for identifying fine hollow image-text of image |
| CN112863042B (en) * | 2021-01-08 | 2023-05-09 | 中钞印制技术研究院有限公司 | Magnetic characteristic detection device and method |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101447027A (en) * | 2008-12-25 | 2009-06-03 | 东莞市微模式软件有限公司 | Binaryzation method of magnetic code character area and application thereof |
| CN201570059U (en) * | 2009-11-25 | 2010-09-01 | 魏伟 | Magnetic image sensor for cash register |
| CN101923741A (en) * | 2010-08-11 | 2010-12-22 | 西安理工大学 | A Banknote Number Recognition Method Based on Banknote Detector |
| CN102737435A (en) * | 2011-04-11 | 2012-10-17 | 北京新岸线数字图像技术有限公司 | Paper money discrimination method and device |
| CN103136845A (en) * | 2013-01-23 | 2013-06-05 | 浙江大学 | Renminbi (RMB) counterfeit identifying method based on crown-word image characters |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1255764C (en) * | 2002-03-25 | 2006-05-10 | 鲍东山 | Composite high tech machine for checking and accepting bank paper |
| US7492974B2 (en) * | 2005-08-18 | 2009-02-17 | International Business Machines Corporation | Gray scale image cleaning system and method |
-
2014
- 2014-07-22 CN CN201410347515.9A patent/CN104091388B/en not_active Expired - Fee Related
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101447027A (en) * | 2008-12-25 | 2009-06-03 | 东莞市微模式软件有限公司 | Binaryzation method of magnetic code character area and application thereof |
| CN201570059U (en) * | 2009-11-25 | 2010-09-01 | 魏伟 | Magnetic image sensor for cash register |
| CN101923741A (en) * | 2010-08-11 | 2010-12-22 | 西安理工大学 | A Banknote Number Recognition Method Based on Banknote Detector |
| CN102737435A (en) * | 2011-04-11 | 2012-10-17 | 北京新岸线数字图像技术有限公司 | Paper money discrimination method and device |
| CN103136845A (en) * | 2013-01-23 | 2013-06-05 | 浙江大学 | Renminbi (RMB) counterfeit identifying method based on crown-word image characters |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104091388A (en) | 2014-10-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104091388B (en) | A kind of paper money discrimination method based on magnetic image and device | |
| CN105303676B (en) | A kind of version recognition methods of bank note and system | |
| CN105957238B (en) | A kind of paper currency management method and its system | |
| CN103136845B (en) | A kind of Renminbi false distinguishing method based on crown word number characteristics of image | |
| CN104346858B (en) | A kind of bank note face amount recognition methods based on magnetic image and device | |
| US20140098360A1 (en) | Method of discriminating banknote using terahertz electromagnetic waves | |
| CN103279735A (en) | Dust stratification detection method and system for financial bill identification module | |
| CN103456075A (en) | Paper money processing method and device | |
| CN104992494A (en) | Method and device for detecting authenticity of paper money | |
| CN107103683B (en) | Paper money identification method and device, electronic equipment and storage medium | |
| CN104966349A (en) | ATM platform-based method of detecting new bank note and old bank note | |
| Sharan et al. | Detection of counterfeit Indian currency note using image processing | |
| CN113205633B (en) | Method and device for detecting red and blue fibers of bill, electronic equipment and storage medium | |
| Geusebroek et al. | Learning banknote fitness for sorting | |
| CN106340116B (en) | A kind of recognition methods of bank note and device | |
| CN106780966B (en) | A kind of paper money discrimination method and device | |
| CN106203397A (en) | Differentiate and localization method based on the form of tabular analysis technology in image | |
| CN105551134B (en) | A kind of method and system of the identification of bank note fold | |
| CN107134047A (en) | White watermark detection method and device | |
| CN106875543B (en) | It is a kind of based on visually impaired people's bill acceptor system of RGB-D camera and recognition methods | |
| CN106600812B (en) | Paper money identification method and device | |
| CN105957237B (en) | A kind of version recognition methods of bank note and device | |
| CN107742357A (en) | A kind of recognition methods of paper money number and device | |
| CN106447904B (en) | Method and device for identifying paper money | |
| CN106204616A (en) | The recognition methods of a kind of Iran note denomination and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20160622 Termination date: 20190722 |