WO2016138740A1 - 票据绵软识别方法和装置 - Google Patents

票据绵软识别方法和装置 Download PDF

Info

Publication number
WO2016138740A1
WO2016138740A1 PCT/CN2015/086464 CN2015086464W WO2016138740A1 WO 2016138740 A1 WO2016138740 A1 WO 2016138740A1 CN 2015086464 W CN2015086464 W CN 2015086464W WO 2016138740 A1 WO2016138740 A1 WO 2016138740A1
Authority
WO
WIPO (PCT)
Prior art keywords
ticket
soft
bill
force sensor
force
Prior art date
Application number
PCT/CN2015/086464
Other languages
English (en)
French (fr)
Inventor
黄晓群
方敏杰
岳许要
林玉梅
Original Assignee
广州广电运通金融电子股份有限公司
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 广州广电运通金融电子股份有限公司 filed Critical 广州广电运通金融电子股份有限公司
Priority to RU2017132261A priority Critical patent/RU2666472C1/ru
Priority to EP15883791.4A priority patent/EP3267402B1/en
Priority to US15/549,628 priority patent/US10102704B2/en
Publication of WO2016138740A1 publication Critical patent/WO2016138740A1/zh
Priority to HK18107482.0A priority patent/HK1248387A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G07—CHECKING-DEVICES
    • G07D—HANDLING OF COINS OR VALUABLE PAPERS, e.g. TESTING, SORTING BY DENOMINATIONS, COUNTING, DISPENSING, CHANGING OR DEPOSITING
    • G07D7/00—Testing specially adapted to determine the identity or genuineness of valuable papers or for segregating those which are unacceptable, e.g. banknotes that are alien to a currency
    • G07D7/181—Testing mechanical properties or condition, e.g. wear or tear
    • 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
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01G—WEIGHING
    • G01G17/00—Apparatus for or methods of weighing material of special form or property
    • G01G17/02—Apparatus for or methods of weighing material of special form or property for weighing material of filamentary or sheet form
    • 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
    • G07D7/181—Testing mechanical properties or condition, e.g. wear or tear
    • G07D7/182—Testing stiffness

Definitions

  • the invention relates to the field of financial bill processing, and in particular to a method and device for softly identifying bills.
  • the thickness sensor, the magnetic sensor, the ultraviolet sensor, the infrared sensor, the contact image sensor, etc. used in the existing banknote identification module application cannot directly perform the small amount of information on the softness of the bill. It is recognized that even high-definition contact image sensors can only distinguish between old and new bills, but in practical applications, many new bills are soft due to moisture and other reasons, which affects the normal recycling and circulation of bills. Contact image sensors cannot distinguish such soft new bills, and another existing identification method is to use sound to identify such soft bills, but due to the noise of various frequencies generated by the machine itself and the surrounding environment, The frequency of various noise sources is not fixed, which seriously affects the accuracy and stability of recognition with sound.
  • the embodiment of the invention provides a method and a device for softly identifying a bill, which can solve the problems of low softness, slow speed and poor anti-interference of the currently detected bills.
  • Rotating the ticket causes the ticket to press against a predetermined plurality of force sensors
  • the ticket is a soft soft ticket.
  • the obtaining the effective force signal of the force sensor feedback specifically includes:
  • determining whether the effective force signal of the effective force sensor satisfies a preset soft condition, and if yes, the ticket is a soft soft ticket specifically:
  • the ticket is a soft soft ticket
  • the ticket is a soft soft ticket
  • the ticket is a soft ticket.
  • the method further includes:
  • the ticket is an abnormal ticket.
  • the method further includes:
  • the soft soft ticket or abnormal bill is separated.
  • a receiving unit configured to receive a ticket
  • An extracting unit configured to extract the bills into pieces, so that the bills enter the bill passages in a single sheet
  • An image collecting unit configured to collect a single bill image of the extracted ticket and a corresponding bill background image
  • a rotating unit for rotating the ticket such that the ticket is pressed against a preset plurality of force sensors
  • a force sensing unit configured to acquire an effective force signal fed back by the force sensor
  • An image processing unit configured to acquire an inclination angle of the ticket according to the single ticket image and a corresponding ticket background image
  • An effective determining unit configured to determine an effective force sensor that is pressed by the bill according to the tilt angle
  • An identifying unit configured to determine whether the effective force signal of the effective force sensor satisfies a preset soft condition
  • the ticket determining unit is configured to determine that the ticket is a soft ticket when the determination result of the identifying unit is YES.
  • the force sensing unit specifically includes:
  • a force signal acquisition subunit for acquiring an original force signal generated by the force sensor during a process in which the ticket begins to press away from the force sensor
  • the force signal processing subunit is configured to calculate an effective force signal of the force sensor according to the original force signal.
  • the identifying unit specifically includes:
  • a first identifying subunit configured to determine whether the effective force signals of all the effective force sensors are smaller than a preset soft threshold
  • a second identification subunit configured to determine whether the effective force signal in the effective force sensor is less than a preset soft soft threshold value of more than half of the total effective force sensor
  • the third identifying subunit is configured to determine whether the effective force sensor has a valid force signal that is less than a preset soft threshold.
  • the device further includes:
  • An abnormality identifying unit configured to determine whether the effective force sensor has a valid force signal greater than a preset new bill maximum value
  • the abnormality determining unit is configured to determine that the ticket is an abnormal ticket when the determination result of the abnormality identifying unit is YES.
  • the device further includes:
  • a separation unit for separating the soft soft ticket or the abnormal ticket.
  • the ticket is received; the ticket is extracted and separated, so that the ticket enters the ticket channel in a single manner; then, the single ticket image of the extracted ticket and the corresponding ticket background image are collected;
  • the bill presses a plurality of preset force sensors; acquires an effective force signal fed back by the force sensor; and then, according to the single bill image and the corresponding ticket Obtaining an inclination angle of the bill according to the background image; determining an effective force sensor that is pressed by the bill according to the tilt angle; and finally, determining whether the effective force signal of the effective force sensor satisfies a preset soft condition, and if so, Then the ticket is a soft note.
  • the billing angle is calculated by simultaneously acquiring a single bill image, and the effective force signals of the plurality of force sensors for collecting and calculating the bill press are calculated, and the softness of the bill is judged by the preset soft condition, Affected by the speed of sound propagation and noise, the problem of low softness, slow speed and poor anti-interference of the currently detected bills is effectively solved.
  • FIG. 1 is a flow chart of an embodiment of a method for identifying softness of a bill according to an embodiment of the present invention
  • Figure 2.1 is a schematic diagram of the bill receiving pressure sensor at the corner of the bill.
  • Figure 2.2 is a schematic diagram of the front end of the bill entering the corner channel and the back end of the bill is about to be pressed to the force sensor;
  • Figure 2.3 is a schematic view of the timing at which the front end of the bill enters the corner channel and the back end of the bill presses the force sensor;
  • Figure 2.4 is a schematic diagram of the front end of the bill entering the corner channel of the ticket.
  • Figure 3 is a schematic diagram of three different attitudes of the ticket passing through the image sensor
  • FIG. 4 is a schematic diagram of a picture of three gestures of a ticket obtained by an image sensor
  • Figure 5 is a schematic view of the bills without tilting and touching all three force sensors
  • Figure 6 is a schematic view of one or two force sensors that are tilted to the right and touched to the left;
  • Figure 7 is a schematic diagram of one or two force sensors that are tilted to the left and touched to the right;
  • Figure 8 is a schematic view of the inclined angle of the bill
  • Figure 9 is a schematic diagram of the force signal output by the force sensor
  • Figure 10 is a schematic view showing the position of the three pressure contact force sensors of the ticket
  • Figure 11 is a schematic view showing the structure of the force sensor.
  • the embodiment of the invention provides a method and a device for softly identifying a bill, which is used for solving the problem that the current detection bill has low softness, low speed, and low anti-interference.
  • an embodiment of a method for softly identifying a ticket in an embodiment of the present invention includes:
  • the ticket After receiving the ticket, the ticket can be extracted and separated so that the ticket enters the ticket channel in a single sheet.
  • the single ticket image of the extracted ticket and the corresponding ticket background image may be collected.
  • Rotating the ticket causes the ticket to be pressed against a preset plurality of force sensors
  • the ticket After the ticket is extracted and split, the ticket can also be rotated such that the ticket is pressed against a predetermined plurality of force sensors.
  • the effective force signal fed back by the force sensor can be obtained.
  • the tilt angle of the ticket may be obtained according to the single ticket image and the corresponding ticket background image.
  • the effective force sensor that the bill is pressed against may be determined according to the tilt angle. It can be understood that the effective force sensor is part or all of the above force sensors.
  • step 109 determines whether the effective force signal of the effective force sensor meets the preset soft condition, if yes, step 109 is performed, and if not, step 110 is performed;
  • step 109 After determining the effective force sensor, it may be determined whether the effective force signal of the effective force sensor satisfies a preset soft condition, and if yes, step 109 is performed, and if no, step 110 is performed.
  • the note is a soft note
  • the ticket is a soft soft ticket.
  • the ticket is a receivable ticket.
  • the ticket is a receivable ticket.
  • the ticket is received; the ticket is extracted, so that the ticket enters the ticket channel in a single manner; then, the single ticket image of the extracted ticket and the corresponding ticket background image are collected; and the rotating ticket causes the ticket to be pressed Touching a preset plurality of force sensors; acquiring an effective force signal fed back by the force sensor; and then acquiring an inclination angle of the ticket according to the single ticket image and the corresponding ticket background image; determining, according to the tilt angle, the ticket is pressed The effective force sensor; finally, it is judged whether the effective force signal of the effective force sensor satisfies the preset soft condition, and if so, the ticket is a soft soft ticket.
  • the bill softness is judged by the preset soft condition.
  • the sound propagation speed and noise interference effectively solve the problem of low softness accuracy, slow speed and poor anti-interference of the currently detected bills.
  • the machine receives the ticket.
  • the entire stack of bills is extracted and separated, and after the bills are extracted, the bills are divided into single sheets into the ticket passage according to the set speed, and the intervals of the adjacent bills are ensured to coincide with the subsequent unit work beats according to the preset interval.
  • the ticket is extracted and divided into a ticket passage.
  • A is an image sensor, preferably a contact image sensor, and the image sensor scans the direction of the ticket perpendicular to the advance direction of the ticket. It is easier to get the tilt angle of the ticket.
  • the slope of the bill is the side and advance of the direction of the bill The angle of the direction.
  • the image of each ticket also includes the background within the entire range of the ticket, so that the subsequent steps calculate the angle of inclination of the ticket.
  • the image of the ticket is preferably a visible light image or an infrared light image.
  • the ticket passes through the image sensor in three different poses: no tilt, left tilt, and right tilt.
  • A is an image sensor
  • B is a ticket
  • C is a forward direction of the ticket.
  • FIG. 4 a picture diagram of three gestures of the ticket obtained by the image sensor.
  • B is a ticket
  • D is a ticket background.
  • the pressure sensor is applied to the rear end of the banknote.
  • Each ticket is pressed to a fixed position force sensor at a fixed speed, angle and curvature.
  • the force sensor Obtain the force signal generated on the force sensor by each touch point of the ticket.
  • the force sensor selected by the invention uses a silicon semiconductor integrated piezoelectric resistor and constitutes a bridge. When external pressure acts on the contact of the sensor, the contact directly acts on the detected piezoelectric resistor, and the piezoelectric resistor The resistance changes with the magnitude of the force, causing a change in the output voltage of the bridge. As shown in Fig.
  • K is a contact (detection point) of the force sensor
  • J is a sensor case.
  • the bill press force sensor is implemented at a 90 degree corner of the billing passage.
  • 1 is an image sensor
  • 2 is a ticket
  • 3 is a force sensor
  • 4 is a driving wheel.
  • the ticket is rotated by the driving wheel 4 to enter the turning passage of the banknote.
  • the positions of 3 and 4 are set distances, and the distance between the tangent point of 2 and 4 and the center point of 3 can be set to 38 mm.
  • Figure 2.1 shows that the ticket will enter the corner pressure contact force sensor in the banknote passage, and the ticket is driven by the transmission wheel into the curve passage in the banknote passage.
  • Figure 2.2 shows that the front end of the bill is driven into the turning passage by the driving wheel 4, and the back end of the bill is lifted up, and the contact of the force sensor is tapped at a fixed speed and angle.
  • the rear end of the bill shown in Figure 2.3 is pressed against the contact of the force sensor to apply a force to the force sensor contact.
  • the bill is a flexible sheet-like object, and the bill is deformed after the back end of the bill is pressed against the force sensor, that is, a certain elastic deformation force is generated on the force sensor, and the resultant force of the bill's flapping force and the elastic deforming force acts on the force sensor.
  • the force signal detected by the force sensor is formed.
  • the bill shown in Fig. 2.4 is about to leave the force sensor under the driving of the driving wheel, and completes the pressing process of a bill to the force sensor.
  • the force sensor gets pressed from the bill to the force sensor to the force The original force signal of the sensor process.
  • the ticket is not tilted and is pressed against all three force sensors.
  • the ticket is tilted to the right and touches one or two force sensors to the left.
  • the ticket is tilted to the left and touches one or two force sensors to the right.
  • the image and force signals of the ticket are processed.
  • the tilt angle G of the bill can be calculated, and the right tilt can be defined as positive, the left tilt is negative, and the left tilt or right tilt is less than 1 degree.
  • the tilt angle G can be defined to be zero.
  • the analog signal obtained by the force sensor is converted into a digital signal usable by the processing chip.
  • a 16-bit ADC chip conversion signal is preferably used, and the resolution is up to 31 uV with a reference voltage of 2.048 V, ensuring a resolution of 31 uV.
  • the resolution of the force signal is 0.01N. It is a process from the start of the bill to the force sensor to the exit, that is, the detected analog signal is a process quantity and needs to be sampled. As shown in FIG. 9, the force signal is output from the force sensor to the force sensor to the force sensor.
  • the ADC chip samples the top H segment of the curve in the figure and obtains an average value, which is the effective force signal of the sheet on the force sensor. The same method finds the effective force signal that the bill acts on the other two force sensors.
  • the machine comprehensively recognizes and determines the plurality of effective force signals and the tilt angle after processing.
  • the three positions E1, E2, and E3 are respectively effective force signals obtained at three positions, and the following three modes can be defined:
  • the effective force signals of the three force sensors are between 0.26N and 0.4N in the acceptable range, (0.26N is the lowest critical value of the soft soft ticket, and 0.4N is the new maximum value of the bill)
  • the ticket is determined to be a receivable ticket. If the three effective force signals are less than the set soft threshold, the ticket is determined to be a soft ticket; if one or both of the effective force signals are less than the set soft threshold, according to the preset Strict level is used for judging. The highest rigor level is that the effective signal is less than the set soft threshold and the bill is judged as a soft bill. The lowest rigor level is determined by the three effective force signals being less than the set soft threshold. Soft soft ticket, if one or more force signals are higher than the maximum value of the new bill, it is judged to be an abnormal bill, and is made with a soft bill. The same processing.
  • the effective force signal relationship of the three force sensors is E1>E2>E3, where E3 can be equal to zero, that is, the bill has a large tilt angle, and there is no force sensor that presses to the E3 position.
  • E1, E2, and E3 are calculated according to the 0.26N to 0.4N receiving range at zero tilt at different tilt angles, respectively, and three ranges of values are obtained. If the three values are all within the receiving range, the ticket is determined to be a receivable ticket.
  • the effective force signal relationship of the three force sensors has E1 ⁇ E2 ⁇ E3, where E1 can be equal to zero, and the method of determining the softness of the bill is similar to the right tilt.
  • the processing chip controls the corresponding structure according to the soft decision result of the ticket, so that the ticket enters different channels, separates the soft soft ticket, and completes the soft recognition process.
  • a receiving unit configured to receive a ticket
  • An extracting unit configured to extract the bills into pieces, so that the bills enter the bill passages in a single sheet
  • An image collecting unit configured to collect a single bill image of the extracted ticket and a corresponding bill background image
  • a rotating unit for rotating the ticket such that the ticket is pressed against a preset plurality of force sensors
  • a force sensing unit configured to acquire an effective force signal fed back by the force sensor
  • An image processing unit configured to acquire an inclination angle of the ticket according to the single ticket image and the corresponding ticket background image
  • An effective determining unit configured to determine, according to the tilt angle, an effective force sensing that is pressed by the bill Device
  • An identification unit configured to determine whether the effective force signal of the effective force sensor satisfies a preset soft condition
  • the ticket determining unit is configured to determine that the ticket is a soft ticket when the determining result of the identifying unit is YES.
  • the force sensing unit may specifically include:
  • a force signal acquisition subunit for acquiring an original force signal generated by the force sensor during a process in which the ticket begins to press away from the force sensor
  • the force signal processing subunit is configured to calculate an effective force signal of the force sensor according to the original force signal.
  • the identifying unit may specifically include:
  • a first identifying subunit configured to determine whether all effective force signals of the effective force sensor are less than a preset soft soft threshold
  • a second identifying sub-unit configured to determine whether the effective force signal in the effective force sensor is less than a preset soft soft threshold value of more than half of the total effective force sensor
  • the third identifying subunit is configured to determine whether the effective force sensor has a valid force signal that is less than a preset soft threshold.
  • the soft soft identification device of the bill may further comprise:
  • An abnormality identifying unit configured to determine whether the effective force sensor has a valid force signal greater than a preset new maximum value of the ticket
  • the abnormality determining unit is configured to determine that the ticket is an abnormal ticket when the determination result of the abnormality identifying unit is YES.
  • the soft soft identification device of the bill may further comprise:
  • a separation unit for separating the soft soft ticket or the abnormal ticket.
  • the receiving unit receives the ticket; the extracting unit extracts the ticket, so that the ticket enters the ticket channel in a single manner; then, the image collecting unit collects the single ticket image of the extracted ticket and the corresponding ticket a background image; the rotating unit rotates the ticket such that the ticket presses against the preset plurality of force sensors; then, the force sensing unit acquires an effective force signal fed back by the force sensor; the image processing unit according to the single ticket image and the corresponding ticket background Obtaining an inclination angle of the ticket; the effective determining unit determines, according to the tilt angle, that the ticket is pressed The effectiveness sensor; finally, the identification unit determines whether the effective force signal of the effective force sensor satisfies a preset soft condition; when the determination result of the identification unit is YES, the ticket determination unit determines that the ticket is a soft ticket.
  • the bill softness is judged by the preset soft condition.
  • the sound propagation speed and noise interference effectively solve the problem of low softness accuracy, slow speed and poor anti-interference of the currently detected bills.
  • the receiving unit receives the ticket.
  • the extracting unit separates the entire stack of bills, and the bill extracting and dividing the bills into separate bills into the bill channel according to the set speed, and the interval of the adjacent bills is ensured to coincide with the subsequent unit working beat according to the preset interval.
  • the image acquisition unit collects a single ticket image of the extracted ticket and a corresponding background image of the ticket, as shown in FIG. 3, where A is an image sensor, preferably a contact image sensor, and the image sensor scans the direction of the ticket perpendicular to the advance direction of the ticket. It is easier to get the tilt angle of the ticket.
  • the inclination of the bill is the angle between the side of the advance direction of the bill and the advancing direction.
  • the image of each ticket also includes the background within the entire range of the ticket, so that the subsequent steps calculate the angle of inclination of the ticket.
  • the image of the ticket is preferably a visible light image or an infrared light image.
  • the ticket passes through the image sensor in three different poses: no tilt, left tilt, and right tilt.
  • A is an image sensor
  • B is a ticket
  • C is a forward direction of the ticket.
  • FIG. 4 a picture diagram of three gestures of the ticket obtained by the image sensor.
  • B is a ticket
  • D is a ticket background.
  • the rotating unit moves the ticket at the same speed and angle to the next step.
  • the pressure sensor is applied to the rear end of the banknote, and each ticket is pressed to a fixed position with a fixed speed, angle and curvature.
  • the force sensing unit acquires a force signal generated by each of the touch points of the ticket on the force sensor.
  • the force sensor selected by the present invention is a silicon semiconductor integrated with a piezoelectric resistor and constitutes a
  • the bridge when the external pressure acts on the contact of the sensor, the contact directly acts on the detected piezoresistor, and the resistance value of the piezoresistor changes correspondingly with the magnitude of the force, thereby causing a change in the output voltage of the bridge.
  • K is a contact (detection point) of the force sensor
  • J is a sensor case.
  • the bill press force sensor is implemented at a 90 degree corner of the billing passage.
  • 1 is an image sensor
  • 2 is a ticket
  • 3 is a force sensor
  • 4 is a driving wheel.
  • the bill is rotated by the driving wheel 4 to enter the turning passage of the bill, and the positions of 3 and 4 are set distances, and the distance between the tangent point of 2 and 4 is 38 mm from the center point of 3.
  • Figure 2.1 shows that the ticket will enter the corner pressure contact force sensor in the banknote passage, and the ticket is driven by the transmission wheel into the curve passage in the banknote passage.
  • Figure 2.2 shows that the front end of the bill is driven into the turning passage by the driving wheel 4, and the back end of the bill is lifted up, and the contact of the force sensor is tapped at a fixed speed and angle.
  • the rear end of the bill shown in Figure 2.3 is pressed against the contact of the force sensor to apply a force to the force sensor contact.
  • the bill is a flexible sheet-like object, and the bill is deformed after the back end of the bill is pressed against the force sensor, that is, a certain elastic deformation force is generated on the force sensor, and the resultant force of the bill's flapping force and the elastic deforming force acts on the force sensor.
  • the force signal detected by the force sensor is formed.
  • the bill shown in Fig. 2.4 is about to leave the force sensor under the driving of the driving wheel, and completes the pressing process of a bill to the force sensor.
  • the force sensor obtains the original force signal from the time the ticket begins to press the force sensor to the force sensor.
  • the ticket is not tilted and is pressed against all three force sensors.
  • the ticket is tilted to the right and touches one or two force sensors to the left.
  • the ticket is tilted to the left and touches one or two force sensors to the right.
  • the image processing unit processes the ticket image.
  • the tilt angle G of the ticket can be calculated, and the right tilt can be defined as positive, the left tilt is negative, and the left tilt or right tilt is less than 1 Time can be determined
  • the tilt angle G is 0.
  • the force signal acquisition subunit in the force sensing unit can also convert the obtained analog force signal into a digital signal usable by the processing chip.
  • a 16-bit ADC chip conversion signal is preferably used to 2.048V.
  • the resolution can reach 31uV, ensuring the resolution of the force signal of 0.01N. It is a process from the start of the bill to the force sensor to the exit, that is, the detected analog signal is a process quantity, and the force signal processing subunit is required to perform sampling processing.
  • the force signal is output from the force sensor to the force sensor to the force sensor.
  • the ADC chip samples the top H segment of the curve in the figure and obtains an average value, which is the effective force signal of the sheet on the force sensor. The same method finds the effective force signal that the bill acts on the other two force sensors.
  • the effective determining unit determines the effective force sensor that the bill is pressed against according to the tilt angle, and the identifying unit performs the comprehensive recognition judgment according to the effective force signal of the effective force sensor.
  • the three positions E1, E2, and E3 are respectively effective force signals obtained at three positions, and the following three modes can be defined:
  • the effective force signals of the three force sensors are between 0.26N and 0.4N in the acceptable range (0.26N is the lowest critical value of the soft soft ticket, and 0.4N is the maximum value of the new bill)
  • the ticket is determined to be a receivable ticket. If the three effective force signals are less than the set soft threshold, the ticket is determined to be a soft ticket; if one or both of the effective force signals are less than the set soft threshold, according to the preset
  • the strict level is used for judging. The highest stringency level is determined by a valid force signal being less than the set soft threshold value, and the bill is judged as a soft bill. The lowest stringency level is determined by the three effective force signals being less than the set soft threshold. For soft notes. If one or more force signals are higher than the maximum value of the new ticket, it is determined to be an abnormal ticket, and the same processing is performed as the soft ticket.
  • the effective force signal relationship of the three force sensors is E1>E2>E3, where E3 can be equal to zero, that is, the bill has a large tilt angle, and there is no force sensor that presses to the E3 position.
  • E1, E2, and E3 are calculated according to the 0.26N to 0.4N receiving range at zero tilt at different tilt angles, respectively, and three ranges of values are obtained. If the three values are all within the receiving range, the ticket is determined to be a receivable ticket.
  • the ticket determining unit determines that the ticket is a soft ticket; if one or both of the tickets The effective force signal is less than the set soft soft threshold and is judged according to the preset strict level. If the effective level signal is less than the set soft threshold and the bills are pressed against the three force sensors, the ticket determination unit determines that the ticket is a soft ticket. If the E3 does not touch the force sensor, then E1 and E2 are required. If the value is greater than the set soft threshold, it can be judged as the receivable ticket; the lowest strict level is determined that the three effective force signals are less than the set soft threshold to determine the soft soft ticket.
  • the abnormality identifying unit determines whether one or more force signals are higher than the maximum value of the new ticket, and if so, the abnormality determining unit determines that the ticket is an abnormal ticket, and performs the same processing as the soft soft ticket.
  • the effective force signal relationship of the three force sensors has E1 ⁇ E2 ⁇ E3, where E1 can be equal to zero, and the method of determining the softness of the bill is similar to the right tilt.
  • the processing chip controls the corresponding structure to make the ticket enter different channels according to the soft decision result of the ticket, and the separating unit separates the soft soft ticket or the abnormal ticket to complete the soft recognition process.
  • the identification method and device are simple to implement and have low structural requirements. Only a small range of changes must be made on the structure of most current financial instrument machines, and the required number of force sensors and their circuits need to be installed according to the actual ticket collection.
  • the processor on the ticket identification unit adds a corresponding software identification control algorithm, so that the soft detection of the ticket can be realized.
  • the identification method is strong in anti-interference, and does not affect the detection of noise and vibration generated by other components. The amount of information detected is small, the system response is fast, and the sound recognition paper is softer, more stable and accurate than the existing voice recognition document.
  • the disclosed system, apparatus, and method may be implemented in other manners.
  • the device embodiments described above are merely illustrative.
  • the division of the unit is only a logical function division.
  • there may be another division manner for example, multiple units or components may be combined or Can be integrated into another system, or some features can be ignored or not executed.
  • the mutual coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection through some interface, device or unit, and may be in an electrical, mechanical or other form.
  • the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, may be located in one place. Square, or it can be distributed to multiple network elements. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of the embodiment.
  • each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.
  • the above integrated unit can be implemented in the form of hardware or in the form of a software functional unit.
  • the integrated unit if implemented in the form of a software functional unit and sold or used as a standalone product, may be stored in a computer readable storage medium.
  • the technical solution of the present invention which is essential or contributes to the prior art, or all or part of the technical solution, may be embodied in the form of a software product stored in a storage medium.
  • a number of instructions are included to cause a computer device (which may be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods described in various embodiments of the present invention.
  • the foregoing storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, and the like. .

Landscapes

  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Image Analysis (AREA)
  • Inspection Of Paper Currency And Valuable Securities (AREA)

Abstract

一种票据绵软识别方法和装置，用于解决目前检测票据绵软准确性低，速度慢和抗干扰差的问题。该方法包括：接收票据（101）；将该票据抽取分张，使得票据以单张的方式进入票据通道（102）；采集抽取后票据的单张票据图像以及相应的票据背景图像（103）；旋转票据使得该票据压触预设的多个力传感器（104）；获取该力传感器反馈的有效力信号（105）；根据该单张票据图像和相应的票据背景图像获取该票据的倾斜角度（106）；根据该倾斜角度确定该票据压触到的有效力传感器（107）；判断该有效力传感器的有效力信号是否满足预置的绵软条件，若是，则该票据为绵软票据（108）。

Description

票据绵软识别方法和装置
本申请要求2015年03月04日提交中国专利局、申请号为201510097028.6、发明名称为“票据绵软识别方法和装置”的发明专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本发明涉及金融票据处理领域，尤其涉及票据绵软识别方法和装置。
背景技术
在金融票据处理设备中，目前现有的钞票识别模块应用中所采用的厚度传感器、磁传感器、紫外传感器、红外传感器、接触式图像传感器等，都无法对票据的绵软程度进行小信息量的快速识别，即使是高清的接触式图像传感器也只能对票据的新旧进行区分，但在实际应用中，不少新的票据由于受潮等原因造成其绵软，影响了票据的正常循环使用和流通，目前接触式图像传感器无法对此类绵软新票据进行辨别，而目前现有的另一种识别方式是用声音进行识别此类绵软票据，但由于机器本身和周围环境产生的各种频率的噪声，而且各种噪声源频率是不固定的，严重影响了用声音进行识别的准确性和稳定性。
发明内容
本发明实施例提供了票据绵软识别方法和装置，能够解决目前检测票据绵软准确性低，速度慢和抗干扰差的问题。
本发明实施例提供的一种票据绵软识别方法，包括：
接收票据；
将所述票据抽取分张，使得票据以单张的方式进入票据通道；
采集抽取后票据的单张票据图像以及相应的票据背景图像；
旋转票据使得所述票据压触预设的多个力传感器；
获取所述力传感器反馈的有效力信号；
根据所述单张票据图像和相应的票据背景图像获取所述票据的倾斜角度；
根据所述倾斜角度确定所述票据压触到的有效力传感器；
判断所述有效力传感器的有效力信号是否满足预置的绵软条件，若是，则所述票据为绵软票据。
可选地，获取所述力传感器反馈的有效力信号具体包括：
获取在票据开始压触到离开所述力传感器的过程中所述力传感器产生的原始力信号；
根据所述原始力信号计算出所述力传感器的有效力信号。
可选地，判断所述有效力传感器的有效力信号是否满足预置的绵软条件，若是，则所述票据为绵软票据具体包括：
若所有所述有效力传感器的有效力信号均小于预设的绵软临界值，则所述票据为绵软票据；
或，若所述有效力传感器中有效力信号小于预设的绵软临界值的个数超过有效力传感器总数的一半，则所述票据为绵软票据；
或，若存在有效力信号小于预设的绵软临界值的所述有效力传感器，则所述票据为绵软票据。
可选地，所述方法还包括：
若存在有效力信号大于预设的全新票据最大值的所述有效力传感器，则所述票据为异常票据。
可选地，所述方法还包括：
分离出所述绵软票据或异常票据。
本发明实施例提供的一种票据绵软识别装置，包括：
接收单元，用于接收票据；
抽取单元，用于将所述票据抽取分张，使得票据以单张的方式进入票据通道；
图像采集单元，用于采集抽取后票据的单张票据图像以及相应的票据背景图像；
旋转单元，用于旋转票据使得所述票据压触预设的多个力传感器；
力传感单元，用于获取所述力传感器反馈的有效力信号；
图像处理单元，用于根据所述单张票据图像和相应的票据背景图像获取所述票据的倾斜角度；
有效确定单元，用于根据所述倾斜角度确定所述票据压触到的有效力传感器；
识别单元，用于判断所述有效力传感器的有效力信号是否满足预置的绵软条件；
票据确定单元，用于当所述识别单元的判断结果为是时，确定所述票据为绵软票据。
可选地，所述力传感单元具体包括：
力信号获取子单元，用于获取在票据开始压触到离开所述力传感器的过程中所述力传感器产生的原始力信号；
力信号处理子单元，用于根据所述原始力信号计算出所述力传感器的有效力信号。
可选地，所述识别单元具体包括：
第一识别子单元，用于判断所有所述有效力传感器的有效力信号是否均小于预设的绵软临界值；
第二识别子单元，用于判断所述有效力传感器中有效力信号小于预设的绵软临界值的个数是否超过有效力传感器总数的一半；
第三识别子单元，用于判断是否存在有效力信号小于预设的绵软临界值的所述有效力传感器。
可选地，所述装置还包括：
异常识别单元，用于判断是否存在有效力信号大于预设的全新票据最大值的所述有效力传感器；
异常确定单元，用于当所述异常识别单元的判断结果为是时，确定所述票据为异常票据。
可选地，所述装置还包括：
分离单元，用于分离出所述绵软票据或异常票据。
从以上技术方案可以看出，本发明实施例具有以下优点：
本发明实施例中，接收票据；将所述票据抽取分张，使得票据以单张的方式进入票据通道；然后，采集抽取后票据的单张票据图像以及相应的票据背景图像；旋转票据使得所述票据压触预设的多个力传感器；获取所述力传感器反馈的有效力信号；接着，根据所述单张票据图像和相应的票 据背景图像获取所述票据的倾斜角度；根据所述倾斜角度确定所述票据压触到的有效力传感器；最后，判断所述有效力传感器的有效力信号是否满足预置的绵软条件，若是，则所述票据为绵软票据。在本发明实施例中，通过同时采集单张票据图像计算票据倾斜角和采集并计算票据压触的多个力传感器的有效力信号，对票据的绵软程度通过预设的绵软条件进行判断，不受声音传播速度和噪声干扰，有效地解决了目前检测票据绵软准确性低，速度慢和抗干扰差的问题。
附图说明
图1为本发明实施例中票据绵软识别方法一个实施例流程图；
图2.1为票据在走钞通道将进入拐角压触力传感器示意图；
图2.2为票据前端进入拐角通道票据后端即将压触到力传感器示意图；
图2.3为票据前端进入拐角通道票据后端压触到力传感器时刻示意图；
图2.4为票据前端进入拐角通道票据后端即将离开力传感器示意图；
图3为票据三种不同的姿态经过图像传感器示意图；
图4为图像传感器获得的票据三种姿态的图片示意图；
图5为票据无倾斜，触压到全部三个力传感器示意图；
图6为票据右倾斜，触压到左边一个或两个力传感器示意图；
图7为票据左倾斜，触压到右边一个或两个力传感器示意图；
图8为票据倾斜角示意图；
图9为力传感器输出的力信号示意图；
图10为票据三个压触到力传感器位置示意图；
图11为力传感器结构示意图。
具体实施方式
本发明实施例提供了票据绵软识别方法和装置，用于解决目前检测票据绵软准确性低，速度慢和抗干扰差的问题。
为使得本发明的发明目的、特征、优点能够更加的明显和易懂，下面将结合本发明实施例中的附图，对本发明实施例中的技术方案进行清楚、完整地描述，显然，下面所描述的实施例仅仅是本发明一部分实施例，而非全部的实施例。基于本发明中的实施例，本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其它实施例，都属于本发明保护的范围。请参阅图1，本发明实施例中一种票据绵软识别方法一个实施例包括：
101、接收票据；
首先，接收票据。
102、将该票据抽取分张，使得票据以单张的方式进入票据通道；
在接收票据之后，可以将该票据抽取分张，使得票据以单张的方式进入票据通道。
103、采集抽取后票据的单张票据图像以及相应的票据背景图像；
对该票据进行抽取分张之后，可以采集抽取后票据的单张票据图像以及相应的票据背景图像。
104、旋转票据使得该票据压触预设的多个力传感器；
对该票据进行抽取分张之后，还可以旋转票据使得该票据压触预设的多个力传感器。
105、获取该力传感器反馈的有效力信号；
当票据压触多个力传感器之后，可以获取该力传感器反馈的有效力信号。
106、根据该单张票据图像和相应的票据背景图像获取该票据的倾斜角度；
采集抽取后票据的单张票据图像以及相应的票据背景图像之后，可以根据该单张票据图像和相应的票据背景图像获取该票据的倾斜角度。
107、根据该倾斜角度确定该票据压触到的有效力传感器；
在获取到该倾斜角度之后，可以根据该倾斜角度确定该票据压触到的有效力传感器。可以理解的是，有效力传感器为上述力传感器中的部分或全部。
108、判断该有效力传感器的有效力信号是否满足预置的绵软条件，若是，则执行步骤109，若否，则执行步骤110；
在确定该有效力传感器之后，可以判断该有效力传感器的有效力信号是否满足预置的绵软条件，若是，则执行步骤109，若否，则执行步骤110。
109、该票据为绵软票据；
若该有效力传感器的有效力信号满足预置的绵软条件，则该票据为绵软票据。
110、该票据为可接收票据。
若该有效力传感器的有效力信号不满足预置的绵软条件，则该票据为可接收票据。
本实施例中，接收票据；将该票据抽取分张，使得票据以单张的方式进入票据通道；然后，采集抽取后票据的单张票据图像以及相应的票据背景图像；旋转票据使得该票据压触预设的多个力传感器；获取该力传感器反馈的有效力信号；接着，根据该单张票据图像和相应的票据背景图像获取该票据的倾斜角度；根据该倾斜角度确定该票据压触到的有效力传感器；最后，判断该有效力传感器的有效力信号是否满足预置的绵软条件，若是，则该票据为绵软票据。在本实施例中，通过同时采集单张票据图像计算票据倾斜角和采集并计算票据压触的多个力传感器的有效力信号，对票据的绵软程度通过预设的绵软条件进行判断，不受声音传播速度和噪声干扰，有效地解决了目前检测票据绵软准确性低，速度慢和抗干扰差的问题。为便于理解，下面对本发明实施例中的一种票据绵软识别方法进行详细描述，请参阅图2至11：
接收票据，机器将票据接收入内。
将整叠的票据抽取分离，票据抽取分张后，根据设定的速度将票据分成单张进入票据通道，相邻票据的间隔按照预设的间隔，确保与后续单元工作节拍吻合。抽取速度可按照如下方法计算：假设机器处理票据速度为每分钟600张，则处理每张票据的时间为60/600＝0.1S，每0.1S抽取一张票据进入票据通道，假如票据通道带动票据的速度为2m/s,则票据间距为0.2m。
如图3所示，票据抽取分张后进入票据通道，图3中A为图像传感器，优选为接触式图像传感器，图像传感器扫描票据方向与票据前进方向垂直。更加容易获取票据的倾斜角度。票据的倾斜度为票据前进方向的边与前进 方向的夹角。每张票据的图像同时包括整张票据范围内的背景，以便后续步骤计算票据的倾斜角度。票据的图像优选为可见光图像或者红外光图像。
如图3所示，票据以三种不同的姿态经过图像传感器：无倾斜、左倾斜和右倾斜。图中A为图像传感器，B为票据，C为票据前进方向。
如图4所示，图像传感器获得的票据三种姿态的图片示意图。图中B为票据，D为票据背景。
完成票据图像采集后，票据以相同的速度和角度进入下一步骤对钞票的后端进行触压力传感器，每张票据以固定的速度、角度和弯曲度触压到固定位置的力传感器，力传感器获取票据各个触压点在力传感器上产生的力信号。本发明所选用的力传感器是采用硅半导体集成了压电电阻并构成一个电桥，当外界的压力作用在传感器的触点上，触点直接作用于检测的压电电阻上，压电电阻的阻值随作用力的大小对应变化，从而引起电桥输出电压的变化。如图11所示，图中K为力传感器的触点(检测点)，J为传感器壳体。当有外力作用在力传感器的触点K上时，触点直接作用于传感器内的压电电阻上，使压电电阻的阻值产生变化，从而实现力信号到电信号的转换。
如图2.1，2.2，2.3，2.4所示，票据压触力传感器在走钞通道的90度拐角处进行实施。图中1为图像传感器，2为票据，3为力传感器，4为主动轮。票据在主动轮4的带动下旋转进入走钞的拐弯通道，3和4的位置是设定的距离，可以设定为2在4上的切点与3的中心点距离为38mm。
图2.1所示为票据在走钞通道将进入拐角压触力传感器，票据在走钞通道由传动轮带动进入拐弯通道。
图2.2所示为票据前端在主动轮4带动进入拐弯通道，票据后端翘起，以固定的速度和角度向力传感器的触点拍打过去。
图2.3所示票据后端旋转触压到力传感器的触点，向力传感器触点施加力的作用。票据为柔性薄片状物体，票据后端压触到力传感器后票据产生形变，即产生一定的弹性形变力作用到力传感器上，票据的拍打力和弹性形变力的合力共同作用在力传感器上，构成力传感器检测的力信号。
图2.4所示票据在主动轮带动下即将离开力传感器，完成一张票据对力传感器的压触过程。力传感器获得从票据开始压触到力传感器到离开力 传感器过程的原始力信号。
本实施例以三个力传感器进行原理说明，票据三种触压力传感器的姿态，图中B为票据，E为力传感器.
如图5所示，票据无倾斜，触压到全部三个力传感器。
如图6所示，票据右倾斜，触压到左边一个或两个力传感器。
如图7所示，票据左倾斜，触压到右边一个或两个力传感器。
在获取票据图像和力信号后，对票据的图像和力信号做处理。如图8所示，根据获取到的票据图像B和票据背景图像D，可计算出票据的倾斜角G，可定义右倾斜为正，左倾斜为负，图像左倾斜或者右倾斜小于1度时可定义倾斜角G为0。
对力传感器获得的模拟信号转换成处理芯片可用的数字信号，为确保对票据绵软的高区分度，优选16位的ADC芯片转换信号，以2.048V为参考电压时，分辨率可达31uV，确保力信号0.01N的分辨率。从票据开始触压到力传感器到离开是一个过程，即检测到的模拟信号是一个过程量，需要进行取样。如图9所示，单张票据从开始压触到力传感器到离开接触力传感器，力传感器输出的力信号示意图。ADC芯片对图中曲线顶端H段进行多次采样并求得平均值，该值即为该张票据作用在该力传感器上的有效力信号。同样的方法求得票据作用在另外两个力传感器上的有效力信号。
机器对处理后的多个有效力信号和倾斜角进行综合识别判断。根据票据的三种姿态，如图10所示三个位置E1，E2，E3分别为三个位置上获得的有效力信号，可定义如下三种模式：
倾斜角为0度时，三个力传感器的有效力信号均在可接收的范围内0.26N到0.4N之间，(0.26N为绵软票据的最低临界值，0.4N为全新票据最大值)则票据判定为可接收票据，若三个有效力信号均小于设定的绵软临界值，则判定票据为绵软票据；如果其中一个或两个有效力信号小于设定的绵软临界值，根据预设的严格等级来进行评判，最高严格等级则一个有效力信号小于设定的绵软临界值则票据判定为绵软票据，最低的严格等级则要三个有效力信号均小于设定的绵软临界值才判定为绵软票据，若一个或以上力信号高于全新票据最大值，则判定为异常票据，与绵软票据做 相同处理。
票据右倾斜时，三个力传感器的有效力信号关系有E1>E2>E3,其中E3可等于零，即票据倾斜角度大，没有压触到E3位置的力传感器。对应不同倾斜角，E1，E2，E3在不同的倾斜角的情况下根据零倾斜时的0.26N到0.4N接收范围进行计算，分别得到三个值的范围。若三个值均在接收范围内，则票据判定为可接收票据，若三个有效力信号均小于设定的绵软临界值，则判定票据为绵软票据；如果其中一个或两个有效力信号小于设定的绵软临界值，根据预设的严格等级来进行评判，最高严格等级则一个有效力信号小于设定的绵软临界值且票据都压触到三个力传感器，则票据判定为绵软票据，若E3没有压触到力传感器，则E1和E2要大于设定的绵软临界值才可判定为可接收票据；最低的严格等级则要三个有效力信号均小于设定的绵软临界值才判定为绵软票据，在E3没有压触到力传感器时，E3＝0，E1和E2均小于绵软临界值才判定为绵软票据。若有一个或以上的力信号高于全新票据最大值，则判定为异常票据，与绵软票据做相同处理。票据左倾斜时，三个力传感器的有效力信号关系有E1<E2<E3，其中E1可等于零，票据绵软的判定方法与右倾斜相似。
处理芯片根据对票据的绵软判定结果，控制相应的结构使票据进入不同的通道，分离出绵软票据，完成绵软识别过程。
上面主要对一种票据绵软识别方法进行描述，下面将详细描述一种票据绵软识别装置，本发明实施例中一种票据绵软识别装置一个实施例包括：
接收单元，用于接收票据；
抽取单元，用于将该票据抽取分张，使得票据以单张的方式进入票据通道；
图像采集单元，用于采集抽取后票据的单张票据图像以及相应的票据背景图像；
旋转单元，用于旋转票据使得该票据压触预设的多个力传感器；
力传感单元，用于获取该力传感器反馈的有效力信号；
图像处理单元，用于根据该单张票据图像和相应的票据背景图像获取该票据的倾斜角度；
有效确定单元，用于根据该倾斜角度确定该票据压触到的有效力传感 器；
识别单元，用于判断该有效力传感器的有效力信号是否满足预置的绵软条件；
票据确定单元，用于当该识别单元的判断结果为是时，确定该票据为绵软票据。
优选地，该力传感单元具体可以包括：
力信号获取子单元，用于获取在票据开始压触到离开该力传感器的过程中该力传感器产生的原始力信号；
力信号处理子单元，用于根据该原始力信号计算出该力传感器的有效力信号。
优选地，该识别单元具体可以包括：
第一识别子单元，用于判断所有该有效力传感器的有效力信号是否均小于预设的绵软临界值；
第二识别子单元，用于判断该有效力传感器中有效力信号小于预设的绵软临界值的个数是否超过有效力传感器总数的一半；
第三识别子单元，用于判断是否存在有效力信号小于预设的绵软临界值的该有效力传感器。
优选地，该票据绵软识别装置还可以包括：
异常识别单元，用于判断是否存在有效力信号大于预设的全新票据最大值的该有效力传感器；
异常确定单元，用于当该异常识别单元的判断结果为是时，确定该票据为异常票据。
优选地，该票据绵软识别装置还可以包括：
分离单元，用于分离出该绵软票据或异常票据。
本实施例中，首先，接收单元接收票据；抽取单元将该票据抽取分张，使得票据以单张的方式进入票据通道；然后，图像采集单元采集抽取后票据的单张票据图像以及相应的票据背景图像；旋转单元旋转票据使得该票据压触预设的多个力传感器；接着，力传感单元获取该力传感器反馈的有效力信号；图像处理单元根据该单张票据图像和相应的票据背景图像获取该票据的倾斜角度；有效确定单元根据该倾斜角度确定该票据压触到的有 效力传感器；最后，识别单元判断该有效力传感器的有效力信号是否满足预置的绵软条件；当该识别单元的判断结果为是时，票据确定单元确定该票据为绵软票据。在本实施例中，通过同时采集单张票据图像计算票据倾斜角和采集并计算票据压触的多个力传感器的有效力信号，对票据的绵软程度通过预设的绵软条件进行判断，不受声音传播速度和噪声干扰，有效地解决了目前检测票据绵软准确性低，速度慢和抗干扰差的问题。为便于理解，下面对本发明实施例中的一种票据绵软识别装置进行详细描述，请参阅图2至11：
接收单元，将票据接收入内。
抽取单元将整叠的票据抽取分离，票据抽取分张将票根据设定的速度将票据分成单张进入票据通道，相邻票据的间隔按照预设的间隔，确保与后续单元工作节拍吻合。抽取速度可按照如下方法计算：假设机器处理票据速度为每分钟600张，则处理每张票据的时间为60/600＝0.1S，每0.1S抽取一张票据进入票据通道，假如票据通道带动票据的速度为2m/s,则票据间距为0.2m。
图像采集单元采集抽取后票据的单张票据图像以及相应的票据背景图像，如图3所示，图中A为图像传感器，优选为接触式图像传感器，图像传感器扫描票据方向与票据前进方向垂直。更加容易获取票据的倾斜角度。票据的倾斜度为票据前进方向的边与前进方向的夹角。每张票据的图像同时包括整张票据范围内的背景，以便后续步骤计算票据的倾斜角度。票据的图像优选为可见光图像或者红外光图像。
如图3所示，票据以三种不同的姿态经过图像传感器：无倾斜、左倾斜和右倾斜。图中A为图像传感器，B为票据，C为票据前进方向。
如图4所示，图像传感器获得的票据三种姿态的图片示意图。图中B为票据，D为票据背景。
完成票据图像采集后，旋转单元让票据以相同的速度和角度进入下一步骤对钞票的后端进行触压力传感器，每张票据以固定的速度、角度和弯曲度触压到固定位置的力传感器，力传感单元获取票据各个触压点在力传感器上产生的力信号。
本发明所选用的力传感器是采用硅半导体集成了压电电阻并构成一个 电桥，当外界的压力作用在传感器的触点上，触点直接作用于检测的压电电阻上，压电电阻的阻值随作用力的大小对应变化，从而引起电桥输出电压的变化。如图11所示，图中K为力传感器的触点(检测点)，J为传感器壳体。当有外力作用在力传感器的触点K上时，触点直接作用于传感器内的压电电阻上，使压电电阻的阻值产生变化，从而实现力信号到电信号的转换。
如图2.1，2.2，2.3，2.4所示，票据压触力传感器在走钞通道的90度拐角处进行实施。图中1为图像传感器，2为票据，3为力传感器，4为主动轮。票据在主动轮4的带动下旋转进入走钞的拐弯通道，3和4的位置是设定的距离，设定为2在4上的切点与3的中心点距离为38mm。
图2.1所示为票据在走钞通道将进入拐角压触力传感器，票据在走钞通道由传动轮带动进入拐弯通道。
图2.2所示为票据前端在主动轮4带动进入拐弯通道，票据后端翘起，以固定的速度和角度向力传感器的触点拍打过去。
图2.3所示票据后端旋转触压到力传感器的触点，向力传感器触点施加力的作用。票据为柔性薄片状物体，票据后端压触到力传感器后票据产生形变，即产生一定的弹性形变力作用到力传感器上，票据的拍打力和弹性形变力的合力共同作用在力传感器上，构成力传感器检测的力信号。
图2.4所示票据在主动轮带动下即将离开力传感器，完成一张票据对力传感器的压触过程。力传感器获得从票据开始压触到力传感器到离开力传感器过程的原始力信号。
本实施例以三个力传感器进行原理说明，票据三种触压力传感器的姿态，图中B为票据，E为力传感器.
如图5所示，票据无倾斜，触压到全部三个力传感器。
如图6所示，票据右倾斜，触压到左边一个或两个力传感器。
如图7所示，票据左倾斜，触压到右边一个或两个力传感器。
在图像采集单元和力传感单元获取到单张票据图像、相应的票据背景图像和力信号后，图像处理单元对票据图像进行处理。如图8所示，根据获取到的单张票据图像B和票据背景图像D，可计算出票据的倾斜角G，可定义右倾斜为正，左倾斜为负，图像左倾斜或者右倾斜小于1度时可定 义倾斜角G为0。
力传感单元中的力信号获取子单元还可以将获得的模拟力信号转换成处理芯片可用的数字信号，为确保对票据绵软的高区分度，优选16位的ADC芯片转换信号，以2.048V为参考电压时，分辨率可达31uV，确保力信号0.01N的分辨率。从票据开始触压到力传感器到离开是一个过程，即检测到的模拟信号是一个过程量，需要力信号处理子单元进行取样处理。如图9所示，单张票据从开始压触到力传感器到离开接触力传感器，力传感器输出的力信号示意图。ADC芯片对图中曲线顶端H段进行多次采样并求得平均值，该值即为该张票据作用在该力传感器上的有效力信号。同样的方法求得票据作用在另外两个力传感器上的有效力信号。
有效确定单元根据该倾斜角度确定该票据压触到的有效力传感器，以及识别单元根据有效力传感器的有效力信号进行综合识别判断。根据票据的三种姿态，如图10所示三个位置E1，E2，E3分别为三个位置上获得的有效力信号，可定义如下三种模式：
倾斜角为0度时，三个力传感器的有效力信号均在可接收的范围内0.26N到0.4N之间，(0.26N为绵软票据的最低临界值，0.4N为全新票据的最大值)则票据判定为可接收票据，若三个有效力信号均小于设定的绵软临界值，则判定票据为绵软票据；如果其中一个或两个有效力信号小于设定的绵软临界值，根据预设的严格等级来进行评判，最高严格等级则一个有效力信号小于设定的绵软临界值则票据判定为绵软票据，最低的严格等级则要三个有效力信号均小于设定的绵软临界值才判定为绵软票据。若一个或以上力信号高于全新票据的最大值，则判定为异常票据，与绵软票据做相同处理。
票据右倾斜时，三个力传感器的有效力信号关系有E1>E2>E3，其中E3可等于零，即票据倾斜角度大，没有压触到E3位置的力传感器。对应不同倾斜角，E1，E2，E3在不同的倾斜角的情况下根据零倾斜时的0.26N到0.4N接收范围进行计算，分别得到三个值的范围。若三个值均在接收范围内，则票据判定为可接收票据，若三个有效力信号均小于设定的绵软临界值，则票据确定单元确定该票据为绵软票据；如果其中一个或两个有效力信号小于设定的绵软临界值，根据预设的严格等级来进行评判，最高严 格等级则一个有效力信号小于设定的绵软临界值且票据都压触到三个力传感器，则票据确定单元确定该票据为绵软票据，若E3没有压触到力传感器，则E1和E2要大于设定的绵软临界值才可判定为可接收票据；最低的严格等级则要三个有效力信号均小于设定的绵软临界值才判定为绵软票据，在E3没有压触到力传感器时，E3＝0，E1和E2均小于绵软临界值才判定为绵软票据。异常识别单元判断是否有一个或以上的力信号高于全新票据的最大值，若是则异常确定单元确定该票据为异常票据，与绵软票据做相同处理。
票据左倾斜时，三个力传感器的有效力信号关系有E1<E2<E3，其中E1可等于零，票据绵软的判定方法与右倾斜相似。
处理芯片根据对票据的绵软判定结果，控制相应的结构使票据进入不同的通道，分离单元分离出绵软票据或异常票据，完成绵软识别过程。
本识别方法和装置实现简单，对结构要求低，只需要在目前大多数金融票据机器的结构基础上做小范围的改动，根据实际票据采集需要安装需要数量的力传感器及其电路，在现有票据识别单元上的处理器增加对应的软件识别控制算法，即可实现票据绵软检测区分。该识别方法抗干扰强，对其他部件产生的噪声、振动都不会影响检测，检测的信息量少，系统响应快，比现有的声音识别票据绵软更加快速稳定准确。
所属领域的技术人员可以清楚地了解到，为描述的方便和简洁，上述描述的系统，装置和单元的具体工作过程，可以参考前述方法实施例中的对应过程，在此不再赘述。
在本申请所提供的几个实施例中，应该理解到，所揭露的系统，装置和方法，可以通过其它的方式实现。例如，以上所描述的装置实施例仅仅是示意性的，例如，所述单元的划分，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式，例如多个单元或组件可以结合或者可以集成到另一个系统，或一些特征可以忽略，或不执行。另一点，所显示或讨论的相互之间的耦合或直接耦合或通信连接可以是通过一些接口，装置或单元的间接耦合或通信连接，可以是电性，机械或其它的形式。
所述作为分离部件说明的单元可以是或者也可以不是物理上分开的，作为单元显示的部件可以是或者也可以不是物理单元，即可以位于一个地 方，或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部单元来实现本实施例方案的目的。
另外，在本发明各个实施例中的各功能单元可以集成在一个处理单元中，也可以是各个单元单独物理存在，也可以两个或两个以上单元集成在一个单元中。上述集成的单元既可以采用硬件的形式实现，也可以采用软件功能单元的形式实现。
所述集成的单元如果以软件功能单元的形式实现并作为独立的产品销售或使用时，可以存储在一个计算机可读取存储介质中。基于这样的理解，本发明的技术方案本质上或者说对现有技术做出贡献的部分或者该技术方案的全部或部分可以以软件产品的形式体现出来，该计算机软件产品存储在一个存储介质中，包括若干指令用以使得一台计算机设备(可以是个人计算机，服务器，或者网络设备等)执行本发明各个实施例所述方法的全部或部分步骤。而前述的存储介质包括：U盘、移动硬盘、只读存储器(ROM，Read-Only Memory)、随机存取存储器(RAM，Random Access Memory)、磁碟或者光盘等各种可以存储程序代码的介质。
以上所述，以上实施例仅用以说明本发明的技术方案，而非对其限制；尽管参照前述实施例对本发明进行了详细的说明，本领域的普通技术人员应当理解：其依然可以对前述各实施例所记载的技术方案进行修改，或者对其中部分技术特征进行等同替换；而这些修改或者替换，并不使相应技术方案的本质脱离本发明各实施例技术方案的精神和范围。

Claims (10)

  1. 一种票据绵软识别方法，其特征在于，包括：
    接收票据；
    将所述票据抽取分张，使得票据以单张的方式进入票据通道；
    采集抽取后票据的单张票据图像以及相应的票据背景图像；
    旋转票据使得所述票据压触预设的多个力传感器；
    获取所述力传感器反馈的有效力信号；
    根据所述单张票据图像和相应的票据背景图像获取所述票据的倾斜角度；
    根据所述倾斜角度确定所述票据压触到的有效力传感器；
    判断所述有效力传感器的有效力信号是否满足预置的绵软条件，若是，则所述票据为绵软票据。
  2. 根据权利要求1所述的方法，其特征在于，获取所述力传感器反馈的有效力信号具体包括：
    获取在票据开始压触到离开所述力传感器的过程中所述力传感器产生的原始力信号；
    根据所述原始力信号计算出所述力传感器的有效力信号。
  3. 根据权利要求1所述的方法，其特征在于，判断所述有效力传感器的有效力信号是否满足预置的绵软条件，若是，则所述票据为绵软票据具体包括：
    若所有所述有效力传感器的有效力信号均小于预设的绵软临界值，则所述票据为绵软票据；
    或，若所述有效力传感器中有效力信号小于预设的绵软临界值的个数超过有效力传感器总数的一半，则所述票据为绵软票据；
    或，若存在有效力信号小于预设的绵软临界值的所述有效力传感器，则所述票据为绵软票据。
  4. 根据权利要求3所述的方法，其特征在于，所述方法还包括：
    若存在有效力信号大于预设的全新票据最大值的所述有效力传感器，则所述票据为异常票据。
  5. 根据权利要求4所述的方法，其特征在于，所述方法还包括：
    分离出所述绵软票据或异常票据。
  6. 一种票据绵软识别装置，其特征在于，包括：
    接收单元，用于接收票据；
    抽取单元，用于将所述票据抽取分张，使得票据以单张的方式进入票据通道；
    图像采集单元，用于采集抽取后票据的单张票据图像以及相应的票据背景图像；
    旋转单元，用于旋转票据使得所述票据压触预设的多个力传感器；
    力传感单元，用于获取所述力传感器反馈的有效力信号；
    图像处理单元，用于根据所述单张票据图像和相应的票据背景图像获取所述票据的倾斜角度；
    有效确定单元，用于根据所述倾斜角度确定所述票据压触到的有效力传感器；
    识别单元，用于判断所述有效力传感器的有效力信号是否满足预置的绵软条件；
    票据确定单元，用于当所述识别单元的判断结果为是时，确定所述票据为绵软票据。
  7. 根据权利要求6所述的装置，其特征在于，所述力传感单元具体包括：
    力信号获取子单元，用于获取在票据开始压触到离开所述力传感器的过程中所述力传感器产生的原始力信号；
    力信号处理子单元，用于根据所述原始力信号计算出所述力传感器的有效力信号。
  8. 根据权利要求6所述的装置，其特征在于，所述识别单元具体包括：
    第一识别子单元，用于判断所有所述有效力传感器的有效力信号是否均小于预设的绵软临界值；
    第二识别子单元，用于判断所述有效力传感器中有效力信号小于预设的绵软临界值的个数是否超过有效力传感器总数的一半；
    第三识别子单元，用于判断是否存在有效力信号小于预设的绵软临界值的所述有效力传感器。
  9. 根据权利要求8所述的装置，其特征在于，所述装置还包括：
    异常识别单元，用于判断是否存在有效力信号大于预设的全新票据最大值的所述有效力传感器；
    异常确定单元，用于当所述异常识别单元的判断结果为是时，确定所述票据为异常票据。
  10. 根据权利要求9所述的装置，其特征在于，所述装置还包括：
    分离单元，用于分离出所述绵软票据或异常票据。
PCT/CN2015/086464 2015-03-04 2015-08-10 票据绵软识别方法和装置 WO2016138740A1 (zh)

Priority Applications (4)

Application Number Priority Date Filing Date Title
RU2017132261A RU2666472C1 (ru) 2015-03-04 2015-08-10 Устройство и способ распознавания мягкости банкноты
EP15883791.4A EP3267402B1 (en) 2015-03-04 2015-08-10 Bill softness recognition method and device
US15/549,628 US10102704B2 (en) 2015-03-04 2015-08-10 Bill softness recognition method and device
HK18107482.0A HK1248387A1 (zh) 2015-03-04 2018-06-08 票據綿軟識別方法和裝置

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201510097028.6A CN104680642B (zh) 2015-03-04 2015-03-04 票据绵软识别方法和装置
CN201510097028.6 2015-03-04

Publications (1)

Publication Number Publication Date
WO2016138740A1 true WO2016138740A1 (zh) 2016-09-09

Family

ID=53315630

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2015/086464 WO2016138740A1 (zh) 2015-03-04 2015-08-10 票据绵软识别方法和装置

Country Status (6)

Country Link
US (1) US10102704B2 (zh)
EP (1) EP3267402B1 (zh)
CN (1) CN104680642B (zh)
HK (1) HK1248387A1 (zh)
RU (1) RU2666472C1 (zh)
WO (1) WO2016138740A1 (zh)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104680642B (zh) * 2015-03-04 2017-08-25 广州广电运通金融电子股份有限公司 票据绵软识别方法和装置
CN109815954A (zh) * 2019-01-31 2019-05-28 科大讯飞股份有限公司 增值税发票图像的方向校正方法、装置、设备及存储介质

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1400567A (zh) * 2001-07-30 2003-03-05 株式会社日立制作所 自动现金交易机
CN1576818A (zh) * 2003-07-10 2005-02-09 株式会社东芝 纸张鉴别器、纸张鉴别方法及纸张鉴别阈值决定方法
CN202205260U (zh) * 2011-09-15 2012-04-25 湖南辰泰电子信息技术有限公司 纸币清分机
CN202205261U (zh) * 2011-09-15 2012-04-25 湖南辰泰电子信息技术有限公司 纸币清分机
EP2680238A1 (en) * 2011-02-22 2014-01-01 Glory Ltd. Money processing device, money processing system, money-conveying cassette, paper-currency-processing device, and paper-currency-processing method
CN104680642A (zh) * 2015-03-04 2015-06-03 广州广电运通金融电子股份有限公司 票据绵软识别方法和装置

Family Cites Families (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US4365508A (en) * 1980-08-01 1982-12-28 Brandt, Inc. Limpness detector for documents and the like
US6345104B1 (en) * 1994-03-17 2002-02-05 Digimarc Corporation Digital watermarks and methods for security documents
EP1158469A3 (en) 1994-03-08 2005-06-29 Cummins-Allison Corporation Method and apparatus for discriminating and counting documents
JPH08180239A (ja) * 1994-08-09 1996-07-12 Cummins Allison Corp 書類識別装置および方法
JP3451135B2 (ja) * 1994-09-09 2003-09-29 太平洋セメント株式会社 金属検出装置の検出ヘッド
JP3674289B2 (ja) * 1998-01-30 2005-07-20 富士電機リテイルシステムズ株式会社 紙葉類媒体の画像取得方法および装置
WO1999050797A1 (fr) * 1998-03-27 1999-10-07 Omron Corporation Capteur d'identification de la qualite du papier et dispositif de tri du papier defectueux
DE19821871A1 (de) * 1998-05-15 1999-11-18 Giesecke & Devrient Gmbh Vorrichtung und Verfahren zum Vereinzeln eines Stapels blattförmiger Aufzeichnungsträger
EP1160737A4 (en) * 1999-02-04 2006-08-09 Obshestvo S Ogranichennoi Otve METHOD FOR DETERMINING THE AUTHENTICITY, VALUE AND LEVEL OF VETUSTE OF BANKNOTE TICKETS, AND SORTING AND COUNTING DEVICE
JP4641776B2 (ja) * 2004-09-30 2011-03-02 沖電気工業株式会社 シャッタ機構及び自動取引装置
CA2516561A1 (en) 2005-08-19 2007-02-19 Cashcode Company Inc. Photo sensor array for banknote evaluation
DE102011051934A1 (de) * 2011-07-19 2013-01-24 Wincor Nixdorf International Gmbh Verfahren und Vorrichtung zur OCR-Erfassung von Wertdokumenten mittels einer Matrixkamera
EP2843631B1 (en) * 2013-08-20 2019-05-22 Kabushiki Kaisha Toshiba Sheet discriminating device and sheet processing apparatus
CN104346858B (zh) * 2014-10-10 2016-11-02 新达通科技股份有限公司 一种基于磁图像的纸币面值识别方法与装置

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1400567A (zh) * 2001-07-30 2003-03-05 株式会社日立制作所 自动现金交易机
CN1576818A (zh) * 2003-07-10 2005-02-09 株式会社东芝 纸张鉴别器、纸张鉴别方法及纸张鉴别阈值决定方法
EP2680238A1 (en) * 2011-02-22 2014-01-01 Glory Ltd. Money processing device, money processing system, money-conveying cassette, paper-currency-processing device, and paper-currency-processing method
CN202205260U (zh) * 2011-09-15 2012-04-25 湖南辰泰电子信息技术有限公司 纸币清分机
CN202205261U (zh) * 2011-09-15 2012-04-25 湖南辰泰电子信息技术有限公司 纸币清分机
CN104680642A (zh) * 2015-03-04 2015-06-03 广州广电运通金融电子股份有限公司 票据绵软识别方法和装置

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP3267402A4 *

Also Published As

Publication number Publication date
CN104680642B (zh) 2017-08-25
EP3267402A4 (en) 2018-07-18
EP3267402A1 (en) 2018-01-10
US20180061167A1 (en) 2018-03-01
US10102704B2 (en) 2018-10-16
CN104680642A (zh) 2015-06-03
HK1248387A1 (zh) 2018-10-12
EP3267402B1 (en) 2019-10-09
RU2666472C1 (ru) 2018-09-07

Similar Documents

Publication Publication Date Title
EP2945097B1 (en) Fingerprint recognition method and electronic device performing the method
CN102194100B (zh) 手指静脉认证装置
TWI652628B (zh) 指紋識別方法及電子裝置
TWI591546B (zh) 指紋識別系統及指紋識別方法及電子設備
JP5930166B2 (ja) 偽指判別装置
WO2017071131A1 (zh) 触控设备和在触控设备上进行指纹检测的方法
WO2015188556A1 (zh) 一种基于多线索融合的票据定位识别方法及系统
US10126858B2 (en) Touch display device and touch method thereof
US8259092B2 (en) Method for writing motion and trajectory recognition and writing apparatus and recognizing system
JP5332519B2 (ja) タッチパネル、操作検出方法および電子機器
KR20170073927A (ko) 사용자 인증 장치 및 방법
KR101783565B1 (ko) 지문인식 기능이 구비된 단말기
CN104932753A (zh) 一种触摸屏及其触摸方法和显示装置
TWI437501B (zh) 基於生物特徵之身分驗證裝置及其方法
TW201814571A (zh) 指紋感測器及其指紋辨識方法
CN107885989A (zh) 签名信息采集方法、签名验证方法及电子签名系统
WO2016138740A1 (zh) 票据绵软识别方法和装置
WO2016082251A1 (zh) 触摸信号处理方法及设备
CN102981671A (zh) 多类物体触控点检测方法
CN107368816B (zh) 生物特征识别方法、生物特征识别装置和检测系统
JP6241230B2 (ja) 生体情報判定装置及びプログラム
WO2020186477A1 (zh) 一种基于骨传导的智能输入方法和系统
CN112861783A (zh) 一种手部检测方法及系统
TW202001644A (zh) 指紋辨識系統
KR102104275B1 (ko) 스타일러스 펜을 이용하는 터치 시스템 및 이를 이용한 터치 검출 방법

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 15883791

Country of ref document: EP

Kind code of ref document: A1

WWE Wipo information: entry into national phase

Ref document number: 15549628

Country of ref document: US

REEP Request for entry into the european phase

Ref document number: 2015883791

Country of ref document: EP

NENP Non-entry into the national phase

Ref country code: DE

WWE Wipo information: entry into national phase

Ref document number: 2017132261

Country of ref document: RU