CN107808444A - Bank note information identifying method, device, equipment and storage medium - Google Patents
Bank note information identifying method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN107808444A CN107808444A CN201711146634.8A CN201711146634A CN107808444A CN 107808444 A CN107808444 A CN 107808444A CN 201711146634 A CN201711146634 A CN 201711146634A CN 107808444 A CN107808444 A CN 107808444A
- Authority
- CN
- China
- Prior art keywords
- bank note
- signal
- signal value
- paper money
- measured
- 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.)
- Pending
Links
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
- G07D7/02—Testing electrical properties of the materials thereof
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07F—COIN-FREED OR LIKE APPARATUS
- G07F19/00—Complete banking systems; Coded card-freed arrangements adapted for dispensing or receiving monies or the like and posting such transactions to existing accounts, e.g. automatic teller machines
- G07F19/20—Automatic teller machines [ATMs]
- G07F19/201—Accessories of ATMs
Abstract
The embodiment of the invention discloses a kind of bank note information identifying method, device, equipment and storage medium.Methods described includes：Gathered during paper money is walked using transmission channel sensor and put signal corresponding to bank note to be measured；Using signal value sequence corresponding to described signal as characteristic vector, it is input in housebroken identification model and is identified, to identify the bank note information of the bank note to be measured.By technical scheme, identification process of the bank note in module for recognizing paper money can be reduced, shortens the paper money recognition time, improves business handling speed, lifts Consumer's Experience.
Description
Technical field
The present embodiments relate to paper money recognition technology, more particularly to a kind of bank note information identifying method, device, equipment and
Storage medium.
Background technology
With the gradual popularization of financial self-service equipment, such as ATM (Automatic Teller Machine, automated teller
Machine) widely use, the business handling speed to ATM proposes higher requirement.
ATM business handling speed largely also depends on bank note in addition to the restriction by the hardware speed of service
Recognition speed, complete in the module for recognizing paper money that existing paper money recognition process is mainly set in ATM, and paper money recognition mould
For block due to the limitation of various objective condition, the speed of service is slower, is that whole bank note walks speed bottle-neck during paper money.
The content of the invention
The present invention provides a kind of bank note information identifying method, device, equipment and storage medium, and bank note is reduced in paper to realize
Identification process in coin identification module, shorten the paper money recognition time, improve business handling speed, lift Consumer's Experience.
In a first aspect, the invention provides a kind of bank note information identifying method, including：
Gathered during paper money is walked using transmission channel sensor and put signal corresponding to bank note to be measured；
Signal value sequence corresponding to described signal as characteristic vector, is input in housebroken identification model and carried out
Identification, to identify the bank note information of the bank note to be measured.
Further, the transmission channel sensor is included at least one set of same straight line positioned at walking paper money path orthogonal
Sensor node at the same level, and the transmission channel sensor be located at it is described walk the module for recognizing paper money that communicates of paper money path it
Before.
Further, described gathered during paper money is walked using transmission channel sensor puts signal corresponding to bank note to be measured,
Including：
During walking paper money when detecting that the sensor node at the same level is blocked by the bank note to be measured, by described same
At least two groups of point signals corresponding at least two sensors collection bank note difference to be measured that level sensor node includes, directly
No longer blocked to the sensor node at the same level by the bank note to be measured.
Further, it is described as characteristic vector, to be input to signal value sequence corresponding to described signal housebroken
It is identified in identification model, including：
At least two groups of signal value sequences are determined according at least two groups of point signals；
By the characteristic vector of at least two groups signal value sequence compositions, it is input in housebroken identification model and is known
Not；
Wherein, the characteristic vector one-dimensional vector that at least two groups of signal value sequences compose in series for described in, or the spy
Sign vector is the multi-C vector of at least two groups signal value sequence compositions, and the signal value sequence of different groups is corresponding to described more
Different row vector in dimensional vector.
Further, the signal value sequence also includes the acquisition time difference information of at least two groups point signals.
Further, in addition to：
Choose the signal value sequence samples of predetermined number respectively to the bank note with different bank note information；
The signal value sequence samples are trained based on pattern-recognition, are identified model, the identification model
Input and believe for characteristic vector corresponding to the signal value sequence samples, the output of the identification model for the bank note of the bank note
Breath.
Further, the bank note information include bank note face amount and/or bank note towards.
Second aspect, present invention also offers a kind of bank note information recognition device, the device includes：
Signal acquisition module, letter is put corresponding to bank note to be measured for utilizing transmission channel sensor to gather during paper money is walked
Number；
Signal input module, for using signal value sequence corresponding to described signal as characteristic vector, being input to through instruction
It is identified in experienced identification model, to identify the bank note information of the bank note to be measured.
Further, the transmission channel sensor is included at least one set of same straight line positioned at walking paper money path orthogonal
Sensor node at the same level, and the transmission channel sensor be located at it is described walk the module for recognizing paper money that communicates of paper money path it
Before.
Further, the signal acquisition module is specifically used for：
During walking paper money when detecting that the sensor node at the same level is blocked by the bank note to be measured, by described same
At least two groups of point signals corresponding at least two sensors collection bank note difference to be measured that level sensor node includes, directly
No longer blocked to the sensor node at the same level by the bank note to be measured.
Further, the signal input module is specifically used for：
At least two groups of signal value sequences are determined according at least two groups of point signals；
By the characteristic vector of at least two groups signal value sequence compositions, it is input in housebroken identification model and is known
Not；
Wherein, the characteristic vector one-dimensional vector that at least two groups of signal value sequences compose in series for described in, or the spy
Sign vector is the multi-C vector of at least two groups signal value sequence compositions, and the signal value sequence of different groups is corresponding to described more
Different row vector in dimensional vector.
Further, the signal value sequence also includes the acquisition time difference information of at least two groups point signals.
Further, in addition to：
Sample chooses module, for choosing the signal value sequence of predetermined number respectively to the bank note with different bank note information
Sample；
Sample training module, for being trained based on pattern-recognition to the signal value sequence samples, it is identified mould
Type, the input of the identification model are for characteristic vector, the output of the identification model corresponding to the signal value sequence samples
The bank note information of the bank note.
Further, the bank note information include bank note face amount and/or bank note towards.
The third aspect, present invention also offers a kind of financial self-service equipment, the equipment includes：
One or more processors；
Memory, for storing one or more programs；
When one or more of programs are by one or more of computing devices so that one or more of processing
Device realizes the bank note information identifying method as described in any in the embodiment of the present invention.
Fourth aspect, present invention also offers a kind of computer-readable recording medium, computer program is stored thereon with, should
The bank note information identifying method as described in any in the embodiment of the present invention is realized when program is executed by processor.
The present invention puts signal by utilizing transmission channel sensor to gather during paper money is walked corresponding to bank note to be measured, and will
Signal value sequence corresponding to point signal is input in housebroken identification model and is identified, treated with identification as characteristic vector
The bank note information of bank note is surveyed, make use of and the advantages of bank note information identifies is being carried out during walking paper money, solve paper in the prior art
Coin identification module needs that the completing of the task is more, and processing speed is limited, caused by whole bank note walk limited speed during paper money
Problem, the identification process for reducing bank note in module for recognizing paper money is realized, shortens the paper money recognition time, improve business handling speed
Degree, lift the effect of Consumer's Experience.
Brief description of the drawings
Fig. 1 is a kind of schematic flow sheet for bank note information identifying method that the embodiment of the present invention one provides；
Fig. 2 is a kind of schematic flow sheet for bank note information identifying method that the embodiment of the present invention two provides；
Fig. 3 is a kind of structural representation for bank note information recognition device that the embodiment of the present invention three provides；
Fig. 4 is a kind of structural representation for financial self-service equipment that the embodiment of the present invention four provides.
Embodiment
The present invention is described in further detail with reference to the accompanying drawings and examples.It is understood that this place is retouched
The specific embodiment stated is used only for explaining the present invention, rather than limitation of the invention.It also should be noted that in order to just
Part related to the present invention rather than entire infrastructure are illustrate only in description, accompanying drawing.
Embodiment one
Fig. 1 is a kind of schematic flow sheet for bank note information identifying method that the embodiment of the present invention one provides.This method can fit
For identifying the situation of bank note information, this method can be performed by bank note information recognition device, the device can by hardware and/or
Software forms, and can typically be integrated in ATM and all financial self-service equipments comprising paper money recognition function.Specifically include
It is as follows：
S110, gathered during paper money is walked using transmission channel sensor and put signal corresponding to bank note to be measured.
Optionally, point signal can be collected by transmission channel sensor by predetermined way, wherein, transmission channel passes
Sensor can be distributed across the point-like sensor in paper money transmission channel, during bank note walks paper money, with walking about for bank note
The series of points signal corresponding to the bank note by the sensor can be gathered by transmission channel sensor.Optionally, the point is believed
Number can be reflected signal or transmission signal.Specifically, the type of the point signal of the corresponding collection of different acquisition modes
Difference, if for example, sensor is arranged on the same side of bank note plane with detection light source, the bank note to be measured of sensor collection is corresponding
Point signal be reflected signal；If sensor is separately positioned on the not homonymy of bank note plane, sensor collection with detection light source
Bank note to be measured corresponding to point signal be transmission signal.Wherein, light source can use visible light source, can also use infrared light supply,
It is not limited thereto.
Exemplary, the decorative pattern and pattern of different colours is distributed with the different parts of bank note, and infrared sensor can be made corresponding
Produce different analog signal values.By taking RMB as an example, (there is figure under infrared transmission when infrared light supply is irradiated at Chairman Mao's watermark
Case, the transmitted light that the sensor of bank note another side collects are weaker) when, the analog signal values after opto-electronic conversion are smaller, i.e. point
Voltage-mode analog values are smaller corresponding to signal；And when infrared light supply is irradiated at Chairman Mao's head portrait (pattern-free, bank note under infrared transmission
The transmitted light that the sensor of another side collects is stronger) when, the analog signal values after opto-electronic conversion are larger, that is, it is corresponding to put signal
Voltage-mode analog values it is larger.In another example, when visible light source is irradiated at Chairman Mao's watermark (nothing under visible reflectance
Pattern, the reflected light that the sensor of the same side collects are stronger) when, the analog signal values after opto-electronic conversion are larger, i.e. point letter
Voltage-mode analog values are larger corresponding to number；And (there is pattern under visible reflectance, together when visible light source is irradiated at Chairman Mao's head portrait
The reflected light that the sensor of side collects is weaker) when, the analog signal values after opto-electronic conversion are smaller, that is, put corresponding to signal
Voltage-mode analog values are smaller.
Using difference of the bank note under different light sources, gathered during bank note walks paper money and signal is put corresponding to bank note to be measured
Purpose be, the rule sex differernce between point signal that can be by recognizing the corresponding collection of different bank note, to identify bank note to be measured
Bank note information.
Preferably, transmission channel sensor includes the peer at least one set of same straight line positioned at walking paper money path orthogonal
Sensor node, and transmission channel sensor is located at before the module for recognizing paper money communicated with walking paper money path.
Optionally, at least two sensors are may include in sensor node at the same level, transmission channel sensor may include at least
One group of peer's sensor node, wherein, transmission channel sensor can be the biography for being used to monitor paper money information carried in equipment
Sensor, or what is specially set is used to identify the sensor of bank note information.Exemplary, if walking paper money path leads to bank note knowledge
Other module, transmission channel sensor can be placed in before module for recognizing paper money so that bank note to be measured enter module for recognizing paper money it
Preceding can is by the point signal acquisition of transmission channel sensor, and to identify the bank note information of bank note to be measured, and then simplification is to be measured
Identification process of the bank note in module for recognizing paper money, the paper money recognition time is reduced, improve business processing bulk velocity, lift user
Experience.
S120, will point signal corresponding to signal value sequence as characteristic vector, be input in housebroken identification model
Row identification, to identify the bank note information of bank note to be measured.
Optionally, characteristic vector can the signal value corresponding to a signal formed according to preset rules, it can be one-dimensional
Vector, or multi-C vector, be not limited thereto.Specifically, can be using signal value sequence corresponding to a signal as feature
Vector input is into identification model, to carry out paper money recognition, wherein, signal value sequence can be the point letter gathered in chronological order
After number being arranged in order, sequence that magnitude of voltage corresponding to each signal in chronological sequence forms.Identification model is trained complete
Into bank note standard identification model, the input of identification model is used for input feature value, correspondingly, output end it is exportable with should
Bank note information corresponding to characteristic vector.Optionally, bank note information can be that bank note face amount, bank note can towards, tilt of paper money degree etc.
By a signal come the information that identifies.
By the use of the signal value sequence corresponding to the point signal of transmission channel sensor collection as characteristic vector, be input to through
The identification of bank note information is carried out in the identification model of training to be advantageous in that, bank note can be caused just to complete paper during paper money is walked
The identification of coin information, the time dedicated for the identification of bank note information is saved, realize and reduce bank note in module for recognizing paper money
Identification process, shorten the paper money recognition time, improve business handling speed, lift Consumer's Experience.
The technical scheme of the present embodiment, it is corresponding by utilizing transmission channel sensor to gather bank note to be measured during paper money is walked
Point signal, and will point signal corresponding to signal value sequence as characteristic vector, be input in housebroken identification model and carry out
Identification, to identify the bank note information of bank note to be measured, it make use of and the advantages of bank note information identifies is being carried out during walking paper money, solve
Module for recognizing paper money needs that the completing of the task is more, and processing speed is limited in the prior art, caused by whole bank note walk paper money process
The problem of medium velocity is limited, the identification process for reducing bank note in module for recognizing paper money is realized, shortens the paper money recognition time, carries
High business handling speed, lift the effect of Consumer's Experience.
Embodiment two
Fig. 2 is a kind of schematic flow sheet for bank note information identifying method that the embodiment of the present invention two provides.The present embodiment with
Optimized based on above-described embodiment, there is provided preferable bank note information identifying method, be specifically, to sharp during paper money is walked
Point signal has carried out further optimization corresponding to transmission channel sensor gathers bank note to be measured.Specifically include as follows：
S210, when detecting that sensor node at the same level is blocked by bank note to be measured, sensed during walking paper money by peer
At least two sensors that device node includes gather at least two groups of point signals corresponding to bank note difference to be measured, until sensing at the same level
Device node is no longer blocked by bank note to be measured.
Optionally, at least two sensors that sensor node at the same level includes can be symmetrical as center line to walk paper money path
Be distributed in and walk on the straight line of paper money path orthogonal, in general, bank note to walk paper money direction vertical with the long side of bank note, therefore, treating
Survey bank note do not have it is inclined in the case of, bank note to be measured that at least two sensors in sensor node at the same level can be passed through simultaneously
Blocked, when i.e. determination is blocked when sensor can collect data, carry out the collection of a signal, each sensor can correspond to
One group of point signal is gathered, due to the position point letters that are different, thus collecting that each sensor is set in sensor node at the same level
The different lines that number group corresponds on bank note to be measured, its signal value tag presented also differ, and then can be believed according to multigroup point
Number signal value tag identify bank note information.Determined when sensor can no longer collect data the sensor no longer by
Bank note to be measured is blocked, you can no longer collection point signal.
Preferably, multiple sensors can be set in sensor node at the same level, and then multigroup signal can be gathered, with reference to each group
The signal value rule of point signal, comprehensive identification bank note information, to improve accuracy of identification.
S220, basis at least two groups of point signals determine at least two groups of signal value sequences.
Optionally, signal value sequence can arrange institute's group by magnitude of voltage as corresponding to the point signal gathered by acquisition time order
Into sequence, one group of point signal can be to should determine that one group of signal value sequence.
Preferably, signal value sequence also includes the acquisition time difference information of at least two groups point signals.
It is exemplary, if the bank note run-off the straight to be measured during paper money is walked, sensor node at the same level include at least two
Time that individual sensor is blocked is different, and corresponding acquisition time is also different, and it is poor acquisition time to be present, and acquisition length also can phase
It should increase, therefore, can be in every group of signal in order to improve the identification accuracy of bank note information more than the narrow edge lengths of bank note to be measured
The time difference information for correction is added in value sequence, specifically, corresponding bank note can be carried out according to the different gradients of bank note
Identification, rather than only with single criterion of identification, meanwhile, the inclination angle of bank note is also calculated using the acquisition time difference information,
So as to contribute to module for recognizing paper money to carry out other paper money recognition work.
S230, the characteristic vector by least two groups signal value sequence compositions, are input in housebroken identification model and carry out
Identification.
Wherein, characteristic vector is the one-dimensional vector that at least two groups of signal value sequences compose in series, or characteristic vector is at least
The multi-C vector of two groups of signal value sequences composition, and the signal value sequence of different groups correspond to row different in multi-C vector to
Amount.
Optionally, two groups of signal value sequences can be formed to a characteristic vector in a predetermined manner, it is exemplary, it can incite somebody to action
At least two groups of signal value sequences form one-dimensional vector by way of tandem connection between sequence and sequence, can also will at least two
Group signal value sequence forms a multi-C vector in the way of one group of sequence is a row vector, and then is input to housebroken
It is identified in identification model.The characteristic vector of at least two groups signal value sequence compositions is input in housebroken identification model
Being identified is advantageous in that, can increase identification feature by the characteristic vector being made up of multigroup signal value sequence, and then
Improve accuracy of identification.
The technical scheme of the present embodiment, by least two sensors that are set in sensor node at the same level by bank note to be measured
When blocking, at least two groups of point signals corresponding to bank note difference to be measured are gathered, until sensor is no longer blocked by bank note to be measured, and will
By the characteristic vector that at least two groups of signal value sequences form that at least two groups of point signals determine, housebroken identification model is input to
In be identified, so as to improve the accuracy of identification of bank note, while also achieve during paper money is walked accurately identification bank note information,
Improve the effect of paper money recognition efficiency.
On the basis of the various embodiments described above, in order to train and establish identification model, it is preferred that also include：
Choose the signal value sequence samples of predetermined number respectively to the bank note with different bank note information；
Signal value sequence samples are trained based on pattern-recognition, are identified model, the input of identification model is letter
Number characteristic vector corresponding to value sequence sample, the output of identification model for bank note bank note information.
Wherein, signal value sequence samples can be by being obtained, herein with above-mentioned acquisition signal value sequence identical mode
Repeat no more.Optionally, the signal value sequence samples of selection can be trained based on mode identification technology, specifically, pattern
Identification refer to carry out various forms of (numerical value, word the and logical relation) information for characterizing things or phenomenon processing and
Analysis, it is the important of information science and artificial intelligence with the process that things or phenomenon are described, recognize, classify and explained
Part, mode identification procedure may include four parts：Acquisition and pretreatment, feature extraction and feature to initial data are selected
Select, classify or cluster, post-process.Used mode identification technology for example may be used when identification model is trained and established in the present embodiment
Be ANNs (Artificial Neural Networks, artificial neural network), K-NN (K-Nearest Neighbor, most
Proximity rules classify), bayes method (Bayes Classifier), PCA (Principle Component Analysis,
Principal component analysis), LDA (Linear Discriminant Analysis, linear discriminant analysis), NMF (Non-negative
Matrix Factorization, Non-negative Matrix Factorization), GMM (Gaussian Mixture Model, gauss hybrid models)
Deng.By choosing the signal value sequence samples of predetermined number respectively to the bank note with bank note information known to difference, can summarize not
The sample of signal value under paper money state is walked in difference with bank note information, to improve the identification accuracy of identification model.In model training
During, characteristic vector corresponding to sample can be input in identification model, and by the actual banknote information of output with it is known
Bank note information is compared, continuous correctly identified model, to obtain housebroken identification model.
Preferably, bank note information include bank note face amount and/or bank note towards.Wherein, bank note towards can include front just
To, front reversely, reverse side is positive and reverse side is reverse.
Embodiment three
Fig. 3 is a kind of structural representation for bank note information recognition device that the embodiment of the present invention three provides.With reference to figure 3, paper
Coin information recognition device includes：Signal acquisition module 310 and signal input module 320, each module is specifically described below.
Signal acquisition module 310, for utilizing transmission channel sensor to gather corresponding to bank note to be measured during paper money is walked
Point signal；
Signal input module 320, for point signal value sequence corresponding to signal as characteristic vector, to be input to trained
Identification model in be identified, to identify the bank note information of bank note to be measured.
A kind of bank note information recognition device is present embodiments provided, the device during paper money is walked by utilizing transmission channel
Sensor gathers point signal corresponding to bank note to be measured, and point signal value sequence corresponding to signal as characteristic vector, is input to
It is identified in housebroken identification model, to identify the bank note information of bank note to be measured, make use of and paper is carried out during paper money is walked
The advantages of coin information identifies, solving module for recognizing paper money in the prior art needs the completing of the task more, and processing speed is limited, and
Caused whole bank note walks the problem of limited speed during paper money, realizes the identification stream for reducing bank note in module for recognizing paper money
Journey, shorten the paper money recognition time, improve business handling speed, lift the effect of Consumer's Experience.
Optionally, transmission channel sensor includes the peer at least one set of same straight line positioned at walking paper money path orthogonal
Sensor node, and transmission channel sensor is located at before the module for recognizing paper money communicated with walking paper money path.
Optionally, signal acquisition module specifically can be used for：
, when detecting that sensor node at the same level is blocked by bank note to be measured, passing through sensor node at the same level during walking paper money
At least two sensors included gather at least two groups of point signals corresponding to bank note difference to be measured, until sensor node at the same level
No longer blocked by bank note to be measured.
Optionally, signal input module specifically can be used for：
At least two groups of signal value sequences are determined according at least two groups of point signals；
By the characteristic vector of at least two groups signal value sequence compositions, it is input in housebroken identification model and is identified；
Wherein, characteristic vector is the one-dimensional vector that at least two groups of signal value sequences compose in series, or characteristic vector is at least
The multi-C vector of two groups of signal value sequences composition, and the signal value sequence of different groups correspond to row different in multi-C vector to
Amount.
Optionally, signal value sequence can also include the acquisition time difference information of at least two groups point signals.
Optionally, can also include：
Sample chooses module, for choosing the signal value sequence of predetermined number respectively to the bank note with different bank note information
Sample；
Sample training module, for being trained based on pattern-recognition to signal value sequence samples, model is identified, known
The input of other model is characteristic vector corresponding to signal value sequence samples, and the output of identification model is the bank note information of bank note.
Optionally, bank note information can include bank note face amount and/or bank note towards.
The said goods can perform the method that any embodiment of the present invention is provided, and possess the corresponding functional module of execution method
And beneficial effect.
Example IV
Fig. 4 is a kind of structural representation for financial self-service equipment that the embodiment of the present invention four provides, as shown in figure 4, this reality
A kind of financial self-service equipment of example offer is provided, including：Processor 41 and memory 42.Processor in the financial self-service equipment can
To be one or more, in Fig. 4 by taking a processor 41 as an example, processor 41 and memory 42 in the financial self-service equipment
It can be connected by bus or other modes, in Fig. 4 exemplified by being connected by bus.
The bank note information identification of above-described embodiment offer is provided in the present embodiment in the processor 41 of financial self-service equipment
Device.In addition, the memory 42 in the financial self-service equipment is used as a kind of computer-readable recording medium, available for storage one
Or multiple programs, described program can be software program, computer executable program and module, such as paper in the embodiment of the present invention
Programmed instruction/module corresponding to coin information identifying method is (for example, the module in bank note information recognition device shown in accompanying drawing 3, bag
Include：Signal acquisition module 310 and signal input module 320).Processor 41 is stored in the software journey in memory 42 by operation
Sequence, instruction and module, so as to perform the various function application of equipment and data processing, that is, realize in above method embodiment
Bank note information identifying method.
Memory 42 may include storing program area and storage data field, wherein, storing program area can storage program area, extremely
Application program needed for few One function；Storage data field can store uses created data etc. according to equipment.In addition, deposit
Reservoir 42 can include high-speed random access memory, can also include nonvolatile memory, and a for example, at least disk is deposited
Memory device, flush memory device or other non-volatile solid state memory parts.In some instances, memory 42 can further comprise
Relative to the remotely located memory of processor 41, these remote memories can pass through network connection to equipment.Above-mentioned network
Example include but is not limited to internet, intranet, LAN, mobile radio communication and combinations thereof.
Also, when one or more program included by above-mentioned financial self-service equipment is by one or more of processors
During 41 execution, program proceeds as follows：
Gathered during paper money is walked using transmission channel sensor and put signal corresponding to bank note to be measured；It will put corresponding to signal
Signal value sequence is input in housebroken identification model and is identified, to identify the bank note of bank note to be measured as characteristic vector
Information.
Embodiment five
The embodiment of the present invention five additionally provides a kind of computer-readable recording medium, is stored thereon with computer program, should
The bank note information identifying method provided such as the embodiment of the present invention one, this method are provided when program is performed by bank note information recognition device
Including：Gathered during paper money is walked using transmission channel sensor and put signal corresponding to bank note to be measured；It will believe corresponding to point signal
Number value sequence is input in housebroken identification model and is identified, to identify that the bank note of bank note to be measured is believed as characteristic vector
Breath.
Certainly, a kind of computer-readable recording medium that the embodiment of the present invention is provided, the computer program stored thereon
It is not limited to realize method operation as described above when being performed, the bank note letter that any embodiment of the present invention is provided can also be realized
Cease the associative operation in recognition methods.
By the description above with respect to embodiment, it is apparent to those skilled in the art that, the present invention
It can be realized by software and required common hardware, naturally it is also possible to realized by hardware, but the former is more in many cases
Good embodiment.Based on such understanding, what technical scheme substantially contributed to prior art in other words
Part can be embodied in the form of software product, and the computer software product can be stored in computer-readable recording medium
In, floppy disk, read-only storage (Read-Only Memory, ROM), random access memory (Random such as computer
Access Memory, RAM), flash memory (FLASH), hard disk or CD etc., including some instructions are causing a computer to set
Standby (can be personal computer, server, or network equipment etc.) performs the method described in each embodiment of the present invention.
It is worth noting that, in the embodiment of above-mentioned bank note information recognition device, included unit and module are only
Divided according to function logic, but be not limited to above-mentioned division, as long as corresponding function can be realized；Separately
Outside, the specific name of each functional unit is also only to facilitate mutually distinguish, the protection domain being not intended to limit the invention.
Pay attention to, above are only presently preferred embodiments of the present invention and institute's application technology principle.It will be appreciated by those skilled in the art that
The invention is not restricted to specific embodiment described here, can carry out for a person skilled in the art various obvious changes,
Readjust and substitute without departing from protection scope of the present invention.Therefore, although being carried out by above example to the present invention
It is described in further detail, but the present invention is not limited only to above example, without departing from the inventive concept, also
Other more equivalent embodiments can be included, and the scope of the present invention is determined by scope of the appended claims.
Claims (10)
- A kind of 1. bank note information identifying method, it is characterised in that including：Gathered during paper money is walked using transmission channel sensor and put signal corresponding to bank note to be measured；Signal value sequence corresponding to described signal as characteristic vector, is input in housebroken identification model and known Not, to identify the bank note information of the bank note to be measured.
- 2. according to the method for claim 1, it is characterised in that the transmission channel sensor include it is at least one set of be located at The sensor node at the same level on the same straight line of paper money path orthogonal is walked, and the transmission channel sensor is located at and the Zou Chao roads Before the module for recognizing paper money that footpath communicates.
- 3. according to the method for claim 2, it is characterised in that described to be adopted during paper money is walked using transmission channel sensor Collect point signal corresponding to bank note to be measured, including：, when detecting that the sensor node at the same level is blocked by the bank note to be measured, passing through the biography at the same level during walking paper money At least two groups of point signals corresponding at least two sensors collection bank note difference to be measured that sensor node includes, until institute Sensor node at the same level is stated no longer to be blocked by the bank note to be measured.
- 4. according to the method for claim 3, it is characterised in that it is described using signal value sequence corresponding to described signal as Characteristic vector, it is input in housebroken identification model and is identified, including：At least two groups of signal value sequences are determined according at least two groups of point signals；By the characteristic vector of at least two groups signal value sequence compositions, it is input in housebroken identification model and is identified；Wherein, the characteristic vector is the one-dimensional vector that at least two groups of signal value sequences compose in series, or the feature to Measure as the multi-C vector of at least two groups of signal value sequences composition, and the signal value sequence of different groups correspond to the multidimensional to Different row vector in amount.
- 5. according to the method for claim 4, it is characterised in that the signal value sequence is also comprising at least two groups of point letters Number acquisition time difference information.
- 6. according to the method described in claim any one of 1-5, it is characterised in that also include：Choose the signal value sequence samples of predetermined number respectively to the bank note with different bank note information；The signal value sequence samples are trained based on pattern-recognition, are identified model, the input of the identification model For characteristic vector corresponding to the signal value sequence samples, the output of the identification model is the bank note information of the bank note.
- 7. according to the method for claim 6, it is characterised in that the bank note information includes bank note face amount and/or bank note face To.
- A kind of 8. bank note information recognition device, it is characterised in that including：Signal acquisition module, signal is put for utilizing transmission channel sensor to gather corresponding to bank note to be measured during paper money is walked；Signal input module, for signal value sequence corresponding to described signal as characteristic vector, to be input to housebroken It is identified in identification model, to identify the bank note information of the bank note to be measured.
- 9. a kind of financial self-service equipment, it is characterised in that the equipment includes：One or more processors；Memory, for storing one or more programs；When one or more of programs are by one or more of computing devices so that one or more of processors are real The now bank note information identifying method as described in any in claim 1-7.
- 10. a kind of computer-readable recording medium, is stored thereon with computer program, it is characterised in that the program is by processor The bank note information identifying method as described in any in claim 1-7 is realized during execution.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711146634.8A CN107808444A (en) | 2017-11-17 | 2017-11-17 | Bank note information identifying method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711146634.8A CN107808444A (en) | 2017-11-17 | 2017-11-17 | Bank note information identifying method, device, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107808444A true CN107808444A (en) | 2018-03-16 |
Family
ID=61590447
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711146634.8A Pending CN107808444A (en) | 2017-11-17 | 2017-11-17 | Bank note information identifying method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107808444A (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1491405A (en) * | 2001-12-13 | 2004-04-21 | �ձ����տ�˹�ɷ�����˾ | Banknote identifying machine and banknote identifying method |
| JP2004185174A (en) * | 2002-12-02 | 2004-07-02 | Toshiba Corp | Apparatus for discriminating paper sheets |
| CN1971636A (en) * | 2005-11-25 | 2007-05-30 | 南京理工大学科技贸易公司 | Method and device for true-false identifying of paper ticket based on infrared identifying watermark |
| CN1979564A (en) * | 2005-12-02 | 2007-06-13 | 南京理工大学科技贸易公司 | Method and apparatus for identifying paper-ticket, certificate based on visible light to identify water mark |
| CN101082999A (en) * | 2006-06-02 | 2007-12-05 | 日立欧姆龙金融系统有限公司 | Paper sheet identifying and checking apparatus |
| CN101520912A (en) * | 2008-02-29 | 2009-09-02 | 富士通先端科技株式会社 | Paper type identifying apparatus and method |
| CN101777205A (en) * | 2009-12-29 | 2010-07-14 | 广州广电运通金融电子股份有限公司 | Paper currency high-speed identification device and method thereof |
| CN105574981A (en) * | 2015-12-10 | 2016-05-11 | 武汉大学 | RMB banknote denomination identification method based on safety line magnetic information |
-
2017
- 2017-11-17 CN CN201711146634.8A patent/CN107808444A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1491405A (en) * | 2001-12-13 | 2004-04-21 | �ձ����տ�˹�ɷ�����˾ | Banknote identifying machine and banknote identifying method |
| JP2004185174A (en) * | 2002-12-02 | 2004-07-02 | Toshiba Corp | Apparatus for discriminating paper sheets |
| CN1971636A (en) * | 2005-11-25 | 2007-05-30 | 南京理工大学科技贸易公司 | Method and device for true-false identifying of paper ticket based on infrared identifying watermark |
| CN1979564A (en) * | 2005-12-02 | 2007-06-13 | 南京理工大学科技贸易公司 | Method and apparatus for identifying paper-ticket, certificate based on visible light to identify water mark |
| CN101082999A (en) * | 2006-06-02 | 2007-12-05 | 日立欧姆龙金融系统有限公司 | Paper sheet identifying and checking apparatus |
| CN101520912A (en) * | 2008-02-29 | 2009-09-02 | 富士通先端科技株式会社 | Paper type identifying apparatus and method |
| CN101777205A (en) * | 2009-12-29 | 2010-07-14 | 广州广电运通金融电子股份有限公司 | Paper currency high-speed identification device and method thereof |
| CN105574981A (en) * | 2015-12-10 | 2016-05-11 | 武汉大学 | RMB banknote denomination identification method based on safety line magnetic information |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| KR102207533B1 (en) | Bill management method and system | |
| Balaji et al. | Chart-text: A fully automated chart image descriptor | |
| CN104464079B (en) | Multiple Currencies face amount recognition methods based on template characteristic point and topological structure thereof | |
| CN104809187A (en) | Indoor scene semantic annotation method based on RGB-D data | |
| CN106056751A (en) | Prefix number identification method and system | |
| Reinders et al. | Learning convolutional neural networks for object detection with very little training data | |
| Sun et al. | Monte Carlo convex hull model for classification of traditional Chinese paintings | |
| CN104992496A (en) | Paper money face identification method and apparatus | |
| CN107203775A (en) | A kind of method of image classification, device and equipment | |
| CN108647595A (en) | Vehicle recognition methods again based on more attribute depth characteristics | |
| Ali et al. | DeepMoney: counterfeit money detection using generative adversarial networks | |
| CN106530489B (en) | A kind of banknote handling device and method | |
| CN108665603A (en) | Identify the method, apparatus and electronic equipment of bank note currency type | |
| CN105957237B (en) | A kind of version recognition methods of bank note and device | |
| Wu et al. | Automatic gear sorting system based on monocular vision | |
| CN107680246B (en) | Method and equipment for positioning curve boundary in paper money pattern | |
| Shinde et al. | Feedforward back propagation neural network (FFBPNN) based approach for the identification of handwritten math equations | |
| CN107808444A (en) | Bank note information identifying method, device, equipment and storage medium | |
| Jain et al. | Online signature verification using energy, angle and directional gradient feature with neural network | |
| Azam et al. | Leaf Detection Using Histogram of Oriented Gradients (HOG), Local Binary Patterns (LBP), and Classifying with SVM Utilizing Claim Dataset | |
| Prabu et al. | Indian coin detection and recognition using deep learning algorithm | |
| Huang et al. | A unified hierarchical convolutional neural network for fine-grained traffic sign detection | |
| Umam et al. | A light deep learning based method for bank serial number recognition | |
| CN106652168B (en) | Method and device for identifying currency value of paper money | |
| CN108537945A (en) | Bill method of detecting watermarks, system and self-service device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180316 |
|
| RJ01 | Rejection of invention patent application after publication |