Multi-currency banknote denomination and orientation combined identification method, device and equipment based on multi-template matching, and storage medium

Abstract

The invention discloses a multi-currency banknote denomination and orientation combined identification method, device and equipment based on multi-template matching, and a storage medium, and relates to the technical field of banknote identification, and the method comprises the steps: obtaining to-be-identified banknote sensor information and banknote sample information of banknotes of different currencies and denominations in a plurality of preset banknote input directions; constructing a corresponding banknote template library based on currency sample information, denomination sample information and banknote input direction sample information in the banknote sample information; matching the to-be-identified banknote sensor information with a target template corresponding to the banknote template library by using a similarity matching function, and determining a target similarity matching result; and based on the target similarity matching result, identifying the currency, the denomination and the orientation of the paper currency, and determining the attribute information of the paper currency. According to the application, reliable matching identification of denominations and orientations of multi-currency banknotes is carried out by constructing the multi-dimensional banknote template library, and the identification accuracy and the interaction experience are improved without strictly limiting the banknote inlet angle.

Description

Technical Field

[0001] This application relates to the field of banknote recognition technology, and in particular to a method, apparatus, device and storage medium for joint recognition of multi-currency banknotes based on multi-template matching. Background Technology

[0002] In banknote processing equipment, accurate identification of banknote denominations and orientations is a crucial step in the processes of counterfeit detection, counting, and circulation. The identification results directly affect the selection of counterfeit detection strategies and the normal operation of the equipment. With the increasing prevalence of multi-currency circulation environments, equipment needs to have the ability to quickly identify banknotes of different denominations and orientations in order to conduct efficient transactions in self-service scenarios such as vending machines and public transportation.

[0003] Currently, existing methods utilize templates with fixed orientations or limited features for identification. For example, only standard templates for new banknotes are collected, and the insertion direction and angle are strictly limited to ensure signal stability. However, in actual circulation environments, banknotes often develop creases, dirt, wear, or even partial damage due to long-term use, leading to weakening or loss of some inherent feature signals. Therefore, with existing methods, when banknotes are significantly worn or soiled, the difference between their optical signal characteristics and the standard template increases significantly, easily causing recognition anomalies and reducing the recognition rate for banknotes still in circulation. Furthermore, the strict insertion posture requirements not only increase the user's operational burden but also lead to a higher insertion failure rate, affecting the efficiency of the equipment and the user experience. Therefore, how to more accurately and effectively perform joint recognition of multiple currency banknote denominations and orientations has become an urgent problem to be solved.

[0004] The above content is only used to help understand the technical solution of this application and does not represent an admission that the above content is prior art. Summary of the Invention

[0005] The main objective of this application is to provide a method, apparatus, device, and storage medium for joint identification of multi-currency banknote denominations and orientations based on multi-template matching, aiming to solve the technical problem of how to more accurately and effectively perform joint identification of multi-currency banknote denominations and orientations.

[0006] To achieve the above objectives, this application proposes a method for joint identification of multi-currency banknote denominations based on multi-template matching, the method comprising:

[0007] Acquire sensor information and banknote sample information of banknotes of different currencies and denominations in multiple preset banknote insertion directions; A corresponding banknote template library is constructed based on the currency sample information, denomination sample information, and banknote insertion direction sample information in the banknote sample information. The similarity matching function is used to match the sensor information of the banknote to be identified with the target template corresponding to the banknote template library to determine the target similarity matching result; Based on the target similarity matching results, the currency type, denomination, and orientation of the banknote are identified to determine the banknote attribute information.

[0008] In one embodiment, the step of acquiring sensor information and sample information of banknotes of different currencies and denominations in multiple preset banknote insertion directions includes: The sensor signals of banknotes of different currencies and denominations in multiple preset banknote insertion directions are acquired. The sensor signals include at least one of infrared reflection signals, visible light signals and transmission signals. The sensor signal is smoothed and transformed to determine the sensor information of the banknote to be identified; The sensor information of the banknotes to be identified is classified to determine the banknote sample information.

[0009] In one embodiment, the step of constructing a corresponding banknote template library based on the currency sample information, denomination sample information, and banknote insertion direction sample information in the banknote sample information includes: Obtain the length of the signal sequence; Based on the currency sample information, denomination sample information and banknote insertion direction sample information in the banknote sample information, the corresponding template timing signal sequence is determined; A corresponding banknote template library is constructed based on the template timing signal sequence and the length of the signal sequence.

[0010] In one embodiment, the step of matching the sensor information of the banknote to be identified with the target template corresponding to the banknote template library using a similarity matching function to determine the target similarity matching result includes: Based on the sensor information of the banknote to be identified, the signal sequence to be identified is determined according to a predefined strategy; The similarity matching function is used to match the signal sequence to be identified with the target template corresponding to the banknote template library to determine the similarity matching result set; The corresponding target similarity matching result is determined based on the set of similarity matching results.

[0011] In one embodiment, the step of determining the corresponding target similarity matching result based on the similarity matching result set includes: When the maximum similarity matching value in the similarity matching result set is greater than a preset threshold, the target similarity matching result is that the banknote is identified as genuine. When the maximum similarity match value in the similarity match result set is less than or equal to a preset threshold, the target similarity match result is that the banknote is identified as counterfeit.

[0012] In one embodiment, the step of identifying the currency, denomination, and orientation of the banknote based on the target similarity matching result to determine the banknote attribute information includes: When the target similarity matching result indicates that the banknote is genuine, the position number corresponding to the target similarity matching result is calculated according to a predefined remainder rule to determine the position number information and remainder information; Based on the location sequence information and the remainder information, the currency type, denomination, and orientation of the banknote are identified to determine the banknote attribute information.

[0013] In one embodiment, the step of identifying the currency type, denomination, and orientation of the banknote based on the location sequence information and the remainder information, and determining the banknote attribute information, includes: Based on the location sequence information, the banknote type and denomination corresponding to the position under the preset sequence range are detected to determine the banknote type information and banknote denomination information; Based on the remainder information, the corresponding banknote orientation information is determined, including front facing, front facing backward, back facing forward, and back facing backward. Based on the banknote type information, the banknote denomination information, and the banknote orientation information, the banknote type, denomination, and orientation are identified to obtain banknote attribute information.

[0014] Furthermore, to achieve the above objectives, this application also proposes a multi-currency banknote denomination and orientation joint recognition device based on multi-template matching, wherein the multi-currency banknote denomination and orientation joint recognition device based on multi-template matching includes: The acquisition module is used to acquire sensor information and banknote sample information of banknotes of different currencies and denominations in multiple preset banknote insertion directions; The processing module is used to construct a corresponding banknote template library based on the currency sample information, denomination sample information and banknote insertion direction sample information in the banknote sample information; The processing module is also used to match the sensor information of the banknote to be identified with the target template corresponding to the banknote template library using a similarity matching function, and determine the target similarity matching result; The execution module is used to identify the currency, denomination, and orientation of the banknote based on the target similarity matching result, and to determine the banknote attribute information.

[0015] Furthermore, to achieve the above objectives, this application also proposes a multi-currency banknote denomination and orientation joint recognition device based on multi-template matching. The device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor. The computer program is configured to implement the steps of the multi-currency banknote denomination and orientation joint recognition method based on multi-template matching as described above.

[0016] In addition, to achieve the above objectives, this application also proposes a storage medium, which is a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it implements the steps of the multi-currency banknote denomination and joint recognition method based on multi-template matching as described above.

[0017] One or more technical solutions proposed in this application have at least the following technical effects: This embodiment proposes a method for joint recognition of multi-currency banknotes by denomination and orientation based on multi-template matching. The method acquires sensor information and sample information of banknotes of different currencies and denominations in multiple preset insertion directions. Based on the currency sample information, denomination sample information, and insertion direction sample information in the banknote sample information, a corresponding banknote template library is constructed. A similarity matching function is used to match the sensor information of the banknotes to be recognized with the target templates corresponding to the banknote template library to determine the target similarity matching result. Based on the target similarity matching result, the currency, denomination, and orientation of the banknotes are identified to determine the banknote attribute information. This application collects sensor information and sample information of banknotes of different currencies and denominations in multiple preset banknote insertion directions to construct a multi-dimensional banknote template library containing currency, denomination, and insertion direction. It uses a similarity matching function to match the signal to be identified with the target templates in the template library, and jointly determines the currency, denomination, and orientation attributes of the banknote based on the matching results. This enables reliable identification of multiple currencies, new and old banknotes, and damaged banknotes without strictly limiting the insertion angle, effectively reducing dependence on banknote condition and insertion posture, improving recognition accuracy and device adaptability, while simplifying user operation and improving the interactive experience. Attached Figure Description

[0018] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0019] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0020] Figure 1 This is a flowchart illustrating an embodiment of the multi-currency banknote denomination and joint recognition method based on multi-template matching in this application. Figure 2 This is a schematic diagram illustrating the banknote insertion direction of the multi-currency banknote denomination based on multi-template matching and the joint recognition method in this application. Figure 3 This is a schematic diagram illustrating the different banknote insertion angles for the multi-currency banknote denominations based on multi-template matching and the joint recognition method in this application. Figure 4 This is a flowchart illustrating Embodiment 2 of the method for joint identification of multi-currency banknotes based on multi-template matching in this application; Figure 5 This is a schematic diagram of the module structure of a multi-currency banknote denomination based on multi-template matching and a joint recognition device according to an embodiment of this application; Figure 6 This is a schematic diagram of the device structure of the hardware operating environment involved in the multi-currency banknote denomination and joint identification method based on multi-template matching in the embodiments of this application.

[0021] The purpose, features, and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0022] It should be understood that the specific embodiments described herein are merely illustrative of the technical solutions of this application and are not intended to limit this application.

[0023] To better understand the technical solution of this application, a detailed description will be provided below in conjunction with the accompanying drawings and specific implementation methods.

[0024] The main solution of this application embodiment is as follows: acquiring banknote sensor information and banknote sample information of different currencies and denominations in multiple preset banknote insertion directions; constructing a corresponding banknote template library based on the currency sample information, denomination sample information, and banknote insertion direction sample information in the banknote sample information; matching the banknote sensor information to be identified with the target template corresponding to the banknote template library using a similarity matching function to determine the target similarity matching result; and identifying the currency, denomination, and orientation of the banknote based on the target similarity matching result to determine the banknote attribute information.

[0025] In this embodiment, for ease of description, the following description focuses on recognizing multi-currency banknote denominations based on multi-template matching and using a joint recognition device as the main execution subject.

[0026] Because existing technologies significantly increase the difference between the optical signal characteristics of banknotes and the standard template when banknotes are obviously worn or contaminated, they are prone to recognition anomalies, thereby reducing the recognition rate of banknotes that still have circulation value. In addition, the strict requirements for banknote insertion posture not only increase the user's operational burden, but also lead to an increase in the banknote insertion failure rate, affecting the efficiency of the device and the user experience.

[0027] This application provides a solution that utilizes a C100-B50-A banknote reader equipped with multiple optical sensors. When constructing templates, sample signals from four directions of banknotes of different denominations are collected and templates are created. In addition to collecting sample templates for new banknotes, samples are also collected for worn banknotes and banknotes with damage not exceeding a preset proportion. Furthermore, based on the angle limitation of the banknote inlet, samples are also collected for banknotes at different inlet angles to create templates. When performing template matching, multi-template matching is used for identification, and the denomination and orientation of the banknote are determined based on the maximum value of the matching result and the location of the maximum value. For other different currencies, this method can still be used to perform multi-template matching to identify the denomination and orientation.

[0028] As can be seen from the above embodiments, this application collects sensor information and sample information of banknotes of different currencies and denominations in multiple preset banknote insertion directions to construct a multi-dimensional banknote template library containing currency, denomination, and insertion direction. It uses a similarity matching function to match the signal to be identified with the target template in the template library, and jointly determines the currency, denomination, and orientation attributes of the banknote based on the matching results. Thus, without strictly limiting the insertion angle, it can reliably identify multiple currencies, new and old banknotes, and damaged banknotes, effectively reducing the dependence on the banknote state and insertion posture, improving the recognition accuracy and device adaptability, while simplifying user operation and improving the interactive experience.

[0029] Based on this, embodiments of this application provide a method for joint identification of multi-currency banknote denominations and orientations based on multi-template matching, referring to... Figure 1 , Figure 1 This is a flowchart illustrating the first embodiment of the multi-currency banknote denomination identification method based on multi-template matching in this application.

[0030] In this embodiment, the multi-currency banknote denomination and orientation joint recognition method based on multi-template matching includes steps S10~S40: Step S10: Obtain the sensor information and banknote sample information of banknotes of different currencies and denominations in multiple preset banknote insertion directions; It should be noted that the banknote sensor information to be identified is the signal data of the banknote to be identified collected in real time by the optical sensor, and the banknote sample information is the signal data collected by the same optical sensor for banknotes of known currency type, denomination, orientation, and condition.

[0031] It is understood that the acquisition of the banknote sensor information and banknote sample information relies on the multi-optical sensor structure of the C100 banknote reader series. The multi-optical sensor structure includes at least an infrared reflection sensor, a visible light sensor, and a transmission sensor. When the banknote passes through the preset sampling area, these sensors will capture the signal sequence of different physical characteristics of the banknote according to the predetermined sampling time sequence. The acquired raw sensor signals usually contain noise and fluctuations, so they need to be smoothed and transformed (e.g., filtering, normalization) to obtain a stable and reliable one-dimensional time sequence signal. This signal is the sensor information of the banknote to be identified or the banknote sample information used to construct the template.

[0032] In a specific embodiment, as an optional implementation, sensor signals of banknotes of different currencies and denominations are acquired in multiple preset banknote insertion directions. These sensor signals include at least one of infrared reflection signals, visible light signals, and transmitted signals. The sensor signals are then smoothed and transformed to determine the sensor information of the banknote to be identified. This banknote sensor information is then classified to determine banknote sample information, i.e., as shown below. Figure 2 As shown, Figure 2 This diagram illustrates the banknote insertion direction of the multi-currency banknote denomination based on multi-template matching and the joint recognition method of this application. It shows four forward orientations of the banknotes during insertion. For each currency to be supported (e.g., RMB, USD, EUR), banknotes of different denominations (e.g., 100 RMB, 50 RMB, 20 RMB) are selected. For each denomination, sensor signals are collected in four preset insertion directions (A: front facing, B: front facing backward, C: back facing, D: back facing backward). Therefore, the process of acquiring the sensor information of the banknote to be recognized is real-time. When the user inserts a banknote to be paid into the banknote inlet of the device, the optical sensors (infrared, visible light, transmission) of the device are automatically triggered. As the banknote passes through the transmission channel in any orientation, sensor signals are collected in real time. The collected raw signals are processed by smoothing and transformation algorithms to generate a set of one-dimensional time-series signal sequences, i.e., the sensor information of the banknote to be recognized.

[0033] In addition to sampling new banknotes, to improve the ability to identify banknotes in circulation, a batch of representative old banknotes with varying degrees of wear, stains, or damage not exceeding a preset threshold (e.g., damaged area less than 5%) will also be selected. Signals from these banknotes in all four input directions will be collected. Furthermore, such as... Figure 3 As shown, Figure 3This diagram illustrates the multi-currency banknote denominations based on multi-template matching and different banknote insertion angles for the joint recognition method. To reduce sensitivity to insertion angles and further enhance the template library's adaptability to complex insertion situations, signals from four insertion directions of banknotes at multiple different tilt angles can be collected, taking into account the allowable angle range of the device's banknote inlet. Corresponding templates are then generated to cover possible changes in banknote insertion posture during actual use. All collected signals, along with their corresponding currency type, denomination, insertion direction, and banknote condition label information, are stored together to obtain banknote sample information.

[0034] In a specific embodiment, as another optional implementation, in order to cope with the effects of sensor aging or changes in ambient light, the system can periodically collect signals to obtain reference signals. The reference signals are then used to dynamically calibrate the information of the sensor to be identified and the banknote sample information to eliminate system drift and ensure the long-term stability of the recognition results.

[0035] In a specific embodiment, if the quality of the sensor signal to be identified is too poor during the real-time identification stage, such as the signal amplitude being too low or the signal-to-noise ratio being lower than a preset threshold, it is determined that the acquisition has failed, and the device will enter the abnormal handling process, prompting the user to insert coins again.

[0036] In one feasible implementation, step S10 may include steps A11 to A13: Step A11: Acquire sensor signals of banknotes of different currencies and denominations in multiple preset banknote insertion directions. The sensor signals include at least one of infrared reflection signals, visible light signals, and transmission signals. It should be noted that the sensor signal is the raw signal data collected in real time by the optical sensor according to the preset sampling sequence when the banknote passes through the preset sampling area. It is the raw analog or digital quantity that characterizes the physical characteristics and state of the banknote.

[0037] It is understood that the infrared reflection signal is an electrical signal converted from the intensity of the reflected light when the banknote is illuminated by an infrared emitting tube and received by a receiving tube. It is used to detect the material, thickness, and some security features of the banknote and is particularly sensitive to the toner component in the ink. The visible light signal is an electrical signal converted from the intensity of the reflected or transmitted light when the banknote is illuminated by visible light (such as white light). It is used to obtain visual features such as the banknote's color image information, watermark, and printed patterns. The transmission signal is an electrical signal converted from the intensity attenuation of light after it passes through the banknote when the light source is located on one side of the banknote and the receiver is located on the other side. It is used to observe the light transmission features of the banknote, such as the distribution of paper fibers, watermark, and security thread.

[0038] Additionally, it should be noted that the preset banknote insertion direction refers to the physical posture of the banknote relative to the sensor array when it enters the recognition channel. This includes the four basic orientations of the banknote: orientation A (front facing forward), orientation B (front facing backward), orientation C (back facing forward), and orientation D (back facing backward). Furthermore, in order to cover changes in the banknote insertion posture that may occur during actual use, the preset banknote insertion direction may also include, based on the above four basic orientations and combined with the allowable angle range of the banknote reader's inlet, the orientation of banknote samples collected at different tilt angles (such as tilting to the left or to the right at a certain angle).

[0039] Step A12: Smooth and transform the sensor signal to determine the sensor information of the banknote to be identified; Understandably, smoothing can employ filtering algorithms (such as median filtering, mean filtering, or Gaussian filtering) to remove high-frequency noise and random interference from the signal, making the waveform smoother and thus more realistically reflecting the inherent physical characteristics of the banknote itself. Transformation can employ normalization to eliminate signal amplitude fluctuations caused by differences in sensor sensitivity or changes in ambient light, as well as time-domain or frequency-domain transformations (such as Fourier transform or wavelet transform) to extract key features of the signal, thereby determining the banknote sensor information that can be used for template matching.

[0040] Step A13: Classify the sensor information of the banknote to be identified to determine the banknote sample information.

[0041] It is understandable that classifying the sensor information of the banknotes to be identified involves classifying and storing each banknote used to construct the template, given its currency, denomination, orientation, condition, and insertion angle. This classification includes the banknote's currency label (e.g., RMB, USD), denomination label (e.g., 100 yuan, 50 yuan), insertion direction label (four basic orientations A / B / C / D and their tilt angles), and banknote status label (new banknote, worn banknote, slightly damaged banknote). Essentially, this process assigns semantic labels to the signal data, transforming it from a simple numerical sequence into indexable sample information, thus forming a database.

[0042] Step S20: Construct a corresponding banknote template library based on the currency sample information, denomination sample information, and banknote insertion direction sample information in the banknote sample information; It should be noted that the banknote template library is a structured database containing multiple template time-series signal sequences. Each sequence corresponds to a standard signal under a specific recognition scenario. Each template is essentially a processed standard one-dimensional signal waveform representing a specific type of banknote (specific currency, denomination, insertion direction, and condition) passing through the sensor.

[0043] It is understood that the currency sample information refers to the type of currency used to distinguish the currency systems of different countries (e.g., RMB, USD, EUR), the denomination sample information refers to the value of the banknote used to distinguish different denominations of the same currency (e.g., 100 yuan, 50 yuan, 20 yuan), and the banknote insertion direction sample information refers to the posture of the banknote relative to the sensor, used to identify the basic orientation of the banknote's physical posture relative to the sensor array, such as front facing, front facing backward, back facing forward, back facing backward, and can be further refined to different tilt angles.

[0044] In a specific embodiment, as an optional implementation, the signal sequence length is obtained; the corresponding template timing signal sequence is determined based on the currency sample information, denomination sample information, and insertion direction sample information in the banknote sample information; a corresponding banknote template library is constructed based on the template timing signal sequence and the signal sequence length, that is, key label information can be extracted from the banknote sample information: currency sample information (e.g., RMB, USD, EUR), denomination sample information (e.g., 100 yuan, 50 yuan, 20 yuan), and insertion direction sample information (e.g., front, back, front). (Front-back, back-front, back-back reverse) For multiple sample signals with the same label combination (same currency, same denomination, same orientation), alignment, smoothing, and averaging methods are used to eliminate individual differences and random noise, generating a most representative template time-series signal sequence. For example, for the front-front orientation of a 100 RMB note, sample signals from ten brand-new banknotes can be collected. After aligning these ten signals along the time axis, the average value is taken point by point to obtain the standard template for that category, which is then stored in a banknote template library for matching during the recognition stage. The obtained template is the first... The one-dimensional timing signal corresponding to each standard template, i.e., the template timing signal sequence, is represented as follows:

[0045] in, This indicates information about a specific currency, denomination, and deposit direction. This indicates the length of the signal sequence.

[0046] In a specific embodiment, as another optional implementation method, in order to cover different conditions of banknotes, multiple templates can be generated for the same currency type, denomination, and insertion direction. For example, in addition to generating a standard template based on brand-new banknotes, corresponding old banknote templates can also be generated based on collected old banknote samples of different grades such as slightly worn and moderately soiled. These templates of different conditions all have the same currency type, denomination, and insertion direction labels, but there are differences in signal waveforms. All generated templates are stored in the above manner and indexed to form a complete banknote template library.

[0047] In specific embodiments, the construction of the banknote template library can also be combined with the physical characteristics of the banknote reader's inlet. Based on the allowable inlet angle range, multiple angle templates can be generated for signals collected at different tilt angles for the same currency, denomination, and orientation. For example, templates can be established for angles such as zero degrees, ±5 degrees, and ±10 degrees. In this way, the index information in the template library will include not only currency, denomination, and orientation, but also dimensions such as new / old grade and inlet angle range, thereby more precisely covering various changes in banknote inlet posture that may occur in actual use. This enables reliable identification of multiple currencies, new / old banknotes, and damaged banknotes without relying on strict inlet posture control.

[0048] In one feasible implementation, step S20 may include steps B11-B13: Step B11: Obtain the signal sequence length; It should be noted that the signal sequence length is the number of discrete sampling points contained in each one-dimensional time-series signal obtained after smoothing and transforming the sensor signal, denoted as N. This length is a fixed preset value, which is determined by the duration of the sampling time sequence, the sampling frequency, and the requirements of the matching operation, to ensure that all signal sequences used for template construction and real-time recognition have the same dimension, thereby enabling effective similarity calculation and matching.

[0049] Step B12: Determine the corresponding template timing signal sequence based on the currency sample information, denomination sample information, and banknote insertion direction sample information in the banknote sample information; It should be noted that the template timing signal sequence is a one-dimensional signal data that can characterize the typical characteristics of a certain type of banknote in a specific orientation, after smoothing and transforming the sensor signals of multiple representative banknote samples (including new banknotes, worn banknotes, and slightly damaged banknotes) collected.

[0050] Step B13: Construct a corresponding banknote template library based on the template timing signal sequence and the length of the signal sequence.

[0051] It is understood that each template entry in the banknote template library contains a complete signal sequence and its corresponding multi-dimensional label information. During the recognition stage, the real-time collected signal sequence to be recognized can be matched with each template in the library. Based on the maximum value of the matching result and its position information, the currency, denomination and banknote insertion direction corresponding to the template can be reversed to achieve joint recognition of banknote attributes.

[0052] Step S30: Use a similarity matching function to match the sensor information of the banknote to be identified with the target template corresponding to the banknote template library to determine the target similarity matching result; It is understood that the similarity matching function is a mathematical algorithm used to measure the degree of similarity between the signal sequence to be identified and a template sequence in the template library. This function can be a normalized cross-correlation algorithm, an inverse Euclidean distance function, a cosine similarity algorithm, or a dynamic time warping algorithm. The selection criteria are based on the ability to effectively cope with the signal waveform stretching and distortion caused by the wear, stains, or slight changes in the banknote insertion angle, so as to accurately output a numerical value that quantifies the degree of matching between two sets of one-dimensional time-series signals. The target template is the template sequence corresponding to the maximum matching value generated during the template matching process. This template carries complete label information, including its corresponding currency, denomination, and insertion direction. Therefore, when the target similarity matching result is determined, the banknote attribute represented by the template is identified as the attribute of the currently inserted banknote.

[0053] In a specific embodiment, the sensor information of the banknote to be identified is processed according to a predefined strategy to determine the signal sequence to be identified. That is, during identification, multiple sample signals with the same tag combination are aligned and averaged to eliminate individual differences and random noise, generating a most representative template time-series signal sequence. Specifically, when the banknote enters the banknote reader, the optical sensor collects sensor signals in real time during the banknote's passage according to a predetermined sampling strategy, and after the same smoothing and transformation, the signal sequence to be identified is formed. , represented as:

[0054] The similarity matching function is used to match the signal sequence to be identified with the target templates in the banknote template library to determine the similarity matching result set. That is, the collected signal to be identified is matched with multiple templates in the template library to obtain the corresponding matching result values. :

[0055] In the above formula, This represents a matching function used to measure the similarity between two sets of one-dimensional time-series signals, for templates in a template library containing characteristic signals. Calculate the similarity to obtain a set of similarity matching results:

[0056] The target similarity matching result is determined based on the set of similarity matching results, that is, the maximum similarity is found among all template matching results. This yields the target similarity matching result, expressed as:

[0057] Step S40: Based on the target similarity matching result, the currency type, denomination, and orientation of the banknote are identified to determine the banknote attribute information.

[0058] It should be noted that the banknote attribute information refers to the various identified feature data of the currently deposited banknotes, that is, the category features and their specific values ​​required for a banknote.

[0059] In a specific embodiment, as an optional implementation, when the target similarity matching result indicates that the banknote is genuine, the position number corresponding to the target similarity matching result is calculated according to a predefined remainder rule to determine the position number information and remainder information, i.e., the maximum matching value in the target similarity matching result. Higher than the preset threshold If the target similarity matching result indicates that the banknote is genuine, the recognition is considered successful; otherwise, the exception handling process begins. The determination is expressed as follows:

[0060] After successful identification, based on the determined denomination and orientation of the banknote, the corresponding authentication strategy is selected to further determine the banknote. Specifically, when the target similarity matching result indicates that the banknote is genuine, the storage location number of the template corresponding to the maximum similarity value in the template library is extracted using the target similarity matching result. Since the template library is arranged according to preset organizational rules during construction, such as storing all templates in the order of currency, denomination, and orientation, the serial number of each template essentially implies its corresponding currency, denomination, and orientation information. By taking the remainder of the serial number divided by 4, the remainder information can be determined.

[0061] Based on the position number information, the banknote type and denomination corresponding to the position within the preset number range are detected to determine the banknote type and denomination information. Based on the remainder information, the corresponding banknote orientation information is determined, including front facing, front reverse, back facing, and back reverse. Based on the banknote type information, the banknote denomination information, and the banknote orientation information, the banknote type, denomination, and orientation are identified to obtain banknote attribute information. That is, based on the position number information and remainder information, the denomination and insertion direction of the currently inserted banknote can be determined. For example, assuming that the template library stores four orientation templates (front facing, front reverse, back facing, back reverse) for each combination of banknote type and denomination, and multiple templates may be stored under each orientation according to their condition or insertion angle, if the number of templates under each orientation is preset to K (K is an integer greater than or equal to 1), then the sequence arrangement rule of the template library is: every 4K consecutive numbers correspond to a complete banknote denomination group. In this system, K consecutive serial numbers correspond to the same orientation. The serial number of the best matching template is divided by 4K and rounded down to determine its currency and denomination range. The remainder of the serial number divided by K (or based on its offset within each group), combined with the preset orientation order, determines the specific orientation information. For example, assuming K equals 2, meaning two templates (old and new) are stored for each orientation, serial numbers 1 and 2 correspond to the two templates for the first orientation (e.g., front facing), serial numbers 3 and 4 correspond to the two templates for the second orientation (e.g., front facing backwards), serial numbers 5 and 6 correspond to the two templates for the third orientation (e.g., back facing forwards), serial numbers 7 and 8 correspond to the two templates for the fourth orientation (e.g., back facing backwards), and serial numbers 9 to 16 correspond to the next currency and denomination combination. When the serial number of the best matching template is 3, the system calculates that it is located in the first group (serial numbers 1 to 8) and belongs to the second orientation of that group, thus determining the currency and denomination of the current banknote as the currency and denomination corresponding to the first group (e.g., RMB 100), and the orientation as front facing backwards.

[0062] In a specific embodiment, as another optional implementation method, in order to simplify the parsing process, an index mapping table can be established simultaneously when constructing the banknote template library. The serial number of each template is associated with and stored with its corresponding currency, denomination, orientation, new / old grade, insertion angle, and other attribute information. When the best matching template serial number is obtained, the system can directly read the corresponding attribute information by looking up the table. Although this method occupies a small amount of storage space, the parsing speed is fast and it is easy to flexibly adjust the organizational structure of the template library. For example, when adding a template or adjusting the arrangement order, there is no need to modify the parsing algorithm; only the mapping table needs to be updated.

[0063] In a specific embodiment, when the maximum similarity value in the target similarity matching result exceeds a preset threshold, but there are multiple templates with very close matching values ​​that all exceed the threshold, the system can make a joint judgment by combining the serial numbers of these candidate templates. For example, if the serial numbers corresponding to multiple high matching value templates all fall within the same currency denomination range, but the information they face is slightly different, a voting mechanism can be used or the template with the highest matching value can be taken as the final result. If there is a cross-currency or cross-denomination situation, it is determined to be an identification ambiguity, and a secondary identification process can be triggered or the user can be required to re-insert coins to ensure the accuracy of identification.

[0064] In one feasible implementation, step S40 may include steps C11-C12: Step C11: When the target similarity matching result indicates that the banknote is genuine, the position number corresponding to the target similarity matching result is calculated according to a predefined remainder rule to determine the position number information and remainder information. It should be noted that the position number information is the index position of the target similarity matching result in the similarity set composed of all template matching results, and the remainder information is the remainder value obtained after dividing the position number according to the predefined rules. The remainder has a one-to-one mapping relationship with the four basic cash entry directions.

[0065] Understandably, the predefined remainder rule is a mathematical operation method used to decouple the banknote orientation information from the position number. It usually uses a modulo 4 operation. This rule is based on the construction logic of the template library. That is, for each currency and denomination, it is always stored continuously in the template library in the order of the four basic banknote insertion directions (A / B / C / D). Therefore, by taking the remainder of 4 on the matched template position number, the remainder (0, 1, 2 or 3) can uniquely determine the orientation of the banknote being inserted. The numerical range of the position number can be used to determine the corresponding currency and denomination.

[0066] Step C12: Based on the location sequence information and the remainder information, the currency type, denomination, and orientation of the banknote are identified to determine the banknote attribute information.

[0067] It is understood that the banknote attribute information may include banknote currency type information, banknote denomination information, and banknote orientation information. Among them, banknote currency type information is the type of currency to which the banknote belongs (such as RMB, USD, EUR, etc.), banknote denomination information is the monetary value of the banknote (such as 100 yuan, 50 yuan, 20 yuan, etc.), and banknote orientation information is the physical posture of the banknote relative to the sensor channel, such as the four basic states of front facing, front facing backward, back facing forward, and back facing backward.

[0068] In one feasible implementation, step C12 may include steps D11-D13: Step D11: Based on the position number information, detect the banknote type and denomination corresponding to the position within the preset number range to determine the banknote type information and banknote denomination information; Understandably, the preset serial number range is a continuous range of serial numbers assigned to each currency and each denomination according to specific storage rules. For example, the four facing templates of RMB 100 may occupy serial numbers 1-4, the four facing templates of RMB 50 may occupy serial numbers 5-8, the four facing templates of USD 100 may occupy serial numbers 9-12, and so on. Therefore, when the position number of the target similarity matching result falls into a certain preset serial number range, it can be determined that the current banknote belongs to the currency and denomination corresponding to that range.

[0069] Step D12: Determine the corresponding banknote orientation information based on the remainder information, wherein the banknote orientation information includes front facing, front facing backward, back facing forward, and back facing backward; Understandably, "front facing" means the front of the banknote faces the sensor and the top of the banknote is inserted first; "front reversed" means the front of the banknote faces the sensor but the bottom of the banknote is inserted first (i.e., upside down); "back facing" means the back of the banknote faces the sensor and the top of the banknote is inserted first; and "back reversed" means the back of the banknote faces the sensor and the bottom of the banknote is inserted first. These four directions cover all the basic orientations that the banknote may present at the banknote insertion slot, thus achieving orientation-free recognition.

[0070] Step D13: Based on the banknote type information, banknote denomination information, and banknote orientation information, the banknote type, denomination, and orientation are identified to obtain banknote attribute information.

[0071] It is understandable that identifying the currency, denomination, and orientation of banknotes is essentially a process of jointly decoding position sequence information and remainder information. That is, based on the preset value range where the position sequence information is located, which corresponds to the storage location occupied by each currency and denomination when the template library is built, the currency and denomination of the banknote currently being deposited can be uniquely determined, and its orientation can be uniquely determined based on the remainder information.

[0072] This embodiment proposes a method for joint recognition of multi-currency banknotes by denomination and orientation based on multi-template matching. The method acquires sensor information and sample information of banknotes of different currencies and denominations in multiple preset insertion directions. Based on the currency sample information, denomination sample information, and insertion direction sample information in the banknote sample information, a corresponding banknote template library is constructed. A similarity matching function is used to match the sensor information of the banknotes to be recognized with the target templates corresponding to the banknote template library to determine the target similarity matching result. Based on the target similarity matching result, the currency, denomination, and orientation of the banknotes are identified to determine the banknote attribute information. This invention addresses the technical challenge of more accurately and effectively recognizing multiple currencies and banknote denominations and orientations. Compared to existing technologies, this application collects sensor and sample information from banknotes of different currencies and denominations in multiple preset insertion directions. It constructs a multi-dimensional banknote template library containing currency, denomination, and insertion direction information. A similarity matching function is used to match the signal to be identified with target templates in the library. Based on the matching results, the currency, denomination, and orientation attributes of the banknote are jointly determined. This allows for reliable recognition of multiple currencies, new and old banknotes, and damaged banknotes without strictly limiting the insertion angle. It effectively reduces reliance on banknote condition and insertion posture, improves recognition accuracy and device adaptability, simplifies user operation, and enhances the user experience.

[0073] Based on the first embodiment of this application, in the second embodiment of this application, the same or similar content as the first embodiment can be referred to the above description, and will not be repeated hereafter.

[0074] In this embodiment, refer to Figure 4 , Figure 4 This is a flowchart illustrating the second embodiment of the multi-currency banknote denomination identification method based on multi-template matching in this application. Step S30 specifically includes steps S31 to S33: Step S31: Based on the sensor information of the banknote to be identified, process it according to a predefined strategy to determine the signal sequence to be identified; It should be noted that the signal sequence to be identified is a one-dimensional time-series signal data sequence obtained by preprocessing the original sensor signal collected in real time by the optical sensor. It can be composed of several signal sampling points arranged in chronological order, and each sampling point corresponds to the signal strength value detected by the sensor at a certain moment.

[0075] Understandably, a predefined strategy is a set of processing rules and methods that are pre-set to convert the raw sensor signals into a standard signal sequence suitable for template matching. This strategy is dynamically determined during the system design phase based on sensor characteristics, signal features, and the requirements of the matching algorithm, and remains consistent throughout the recognition process.

[0076] In a specific embodiment, as an optional implementation, when the banknote passes through the optical sensor, the sensor continuously collects signals according to a predetermined sampling sequence to generate the original sensor signal. Since the original signal may contain distortions introduced by factors such as ambient light interference, sensor noise, and fluctuations in the banknote's movement speed, it needs to be preprocessed. Preprocessing typically includes two stages: smoothing and transformation. Smoothing filters out high-frequency noise, including moving average filtering, median filtering, or low-pass filtering. Transformation is used to correct the signal baseline, unify the signal amplitude range, or adjust the signal length, including normalization, baseline correction, interpolation resampling, etc. After these processes, the resulting one-dimensional time-series data is the signal sequence to be identified.

[0077] In a specific embodiment, as another optional implementation, predefined strategies can be differentiated for different currencies or different sensor types. For example, for infrared reflection signals, since they are greatly affected by the surface texture of the banknote, a smaller smoothing window can be used to retain detailed features. For transmission signals, since their noise level is high, a larger smoothing window can be used to better suppress noise. These strategy parameters are loaded from the configuration file during system initialization or automatically optimized and determined based on the statistical characteristics of the samples during the template construction stage. When the banknote passes through the sensor area, it is continuously sampled at a fixed sampling rate (e.g., 1,000 points per second) or triggered by the banknote position. The smoothing processing strategy specifies which filtering algorithm and its parameters to use, such as the window size of the moving average and the order of the median filter. The transformation processing strategy specifies which transformation method and its parameters to use, such as the target range of normalization and the selection rules for the reference point of baseline correction, thereby obtaining the signal sequence to be identified.

[0078] Step S32: Use a similarity matching function to match the signal sequence to be identified with the target template corresponding to the banknote template library to determine the similarity matching result set; It should be noted that the similarity matching result set is a set composed of matching the signal sequence to be identified with each target template in the banknote template library. This set is a data structure containing multiple matching values, where each matching value corresponds to the degree of similarity between the signal sequence to be identified and a specific template.

[0079] In a specific embodiment, as an optional implementation, the similarity matching result set can be represented as a one-dimensional array. The length of the array is equal to the total number of templates participating in the matching. Each element in the array corresponds to the matching score of a template. The subscript position of the element corresponds one-to-one with the storage sequence number of the template in the template library. For example, if the template library stores a total of one hundred templates, then the similarity matching result set is an array containing one hundred values, where the first value represents the degree of matching between the signal to be identified and the first template, the second value represents the degree of matching with the second template, and so on.

[0080] In a specific embodiment, as another optional implementation, in order to balance recognition efficiency and accuracy, a matching range filtering strategy can be set. For some application scenarios, if the device can narrow down the possible currency range based on preliminary detection information (such as a rough judgment of banknote size), it can choose to match only the signal to be identified with some related templates. At this time, the similarity matching result set only contains the matching results of this part of the templates. When the maximum value in this part of the matching results is lower than a preset threshold, it is then expanded to the entire database of templates for matching to confirm whether there are other possibilities.

[0081] In a specific embodiment, the similarity matching result set can not only store the matching score, but also store the template number or other identification information corresponding to each match, so as to quickly locate the best matching template. During the calculation process, if the matching score of a certain template is found to be obviously abnormal, such as being much higher than the normal range or an error occurs during the calculation process, the system can mark or remove the score to ensure the validity of the data in the set.

[0082] Step S33: Determine the corresponding target similarity matching result based on the similarity matching result set.

[0083] It should be noted that the target similarity matching result is the quantitative numerical result of the banknote attributes obtained after similarity calculation. It is the maximum value among all matching values. This maximum value not only represents the best matching degree between the banknote to be identified and a specific template, but its value is also used to compare with a preset threshold to determine whether the identification is successful, that is, to determine whether the banknote is genuine or counterfeit. Its position number in the entire similarity set is used to reverse index the currency, denomination and banknote insertion direction information corresponding to the template.

[0084] In a specific embodiment, as an optional implementation, the banknote type and denomination corresponding to the position within the preset sequence interval are detected based on the position number information to determine the banknote type and denomination information; the corresponding banknote orientation information is determined based on the remainder information, including front facing, front facing backward, back facing forward, and back facing backward; the banknote type, denomination, and orientation are identified based on the banknote type, denomination, and orientation information to obtain banknote attribute information. That is, the system traverses the similarity matching result set and finds the maximum value by comparing them one by one. In specific operation, a temporary variable can be initialized to store the current maximum value and its initial value is set as the first element in the set. At the same time, the position number corresponding to the maximum value is recorded. Subsequent elements in the set are compared with the current maximum value in turn. If the value of an element is greater than the current maximum value, the current maximum value is updated to the value of that element, and the recorded position number is updated to the index of that element in the set. After the traversal is completed, the maximum value and its corresponding position number are obtained, thereby obtaining the target similarity matching result.

[0085] In a specific embodiment, as another optional implementation, if the maximum value in the similarity matching result set exceeds the threshold, but the template indicated by its corresponding position number belongs to the same currency denomination but different orientations as the template corresponding to the second largest value, and the second largest value is also very close to the maximum value, then the system can preferentially select the template with the highest matching value to determine the orientation, but at the same time mark the credibility of the recognition result as low.

[0086] In one feasible implementation, step S33 may include steps E11-E12: Step E11: When the maximum similarity matching value in the similarity matching result set is greater than a preset threshold, the target similarity matching result is that the banknote is identified as a genuine banknote. Understandably, when the highest similarity score obtained after matching the real-time acquired signal sequence to be identified with all templates in the template library exceeds the confidence threshold preset by the system, it indicates that the characteristics of the current banknote are highly consistent with the characteristics of a certain template in the template library, and the degree of matching is sufficient to confirm that the banknote is genuine. At this time, not only is the banknote determined to be genuine, but the currency, denomination and orientation will also be decoded based on the position of the maximum value.

[0087] Step E12: When the maximum similarity matching value in the similarity matching result set is less than or equal to a preset threshold, the target similarity matching result is that the banknote is identified as counterfeit.

[0088] Understandably, when the highest similarity score is lower than or equal to the system's preset confidence threshold, it indicates that the current banknote's features do not match the credibility standard of all known genuine banknote templates in the template library. This may be due to the banknote being counterfeit, severely damaged, or a non-supported currency. In this case, the system determines that the recognition has failed, classifies the banknote as counterfeit or unrecognizable, and directly triggers anomaly processing.

[0089] This embodiment proposes a multi-currency banknote denomination and orientation joint recognition method based on multi-template matching. The method processes the sensor information of the banknote to be recognized according to a predefined strategy to determine the signal sequence to be recognized; it then uses a similarity matching function to match the signal sequence to be recognized with the target template corresponding to the banknote template library to determine a similarity matching result set; finally, it determines the corresponding target similarity matching result based on the similarity matching result set. This invention addresses the technical challenge of more accurately and effectively recognizing multiple denominations and orientations of banknotes. Compared to existing technologies, this application transforms the sensor information of the banknotes to be recognized into a signal sequence. A similarity matching function is then used to match this sequence with each target template in a banknote template library. The target similarity matching result is selected from the set of similarity matching results. This allows for comparison of the real-time signal with a rich template library covering multiple currencies, denominations, orientations, and banknotes in various new and old states. This significantly improves the recognition accuracy of worn, soiled, and slightly damaged banknotes without strictly limiting the angle of entry and the banknote's condition, while effectively reducing false recognition and rejection rates, and enhancing the adaptability of banknote recognition equipment in complex circulation environments.

[0090] This application also provides a multi-currency banknote denomination and orientation joint recognition device based on multi-template matching. Please refer to... Figure 5 The multi-currency banknote denomination and orientation joint recognition device based on multi-template matching includes: The acquisition module 10 is used to acquire sensor information and banknote sample information of banknotes of different currencies and denominations in multiple preset banknote insertion directions; Processing module 20 is used to construct a corresponding banknote template library based on the currency sample information, denomination sample information and banknote insertion direction sample information in the banknote sample information; The processing module 20 is also used to match the sensor information of the banknote to be identified with the target template corresponding to the banknote template library using a similarity matching function, and determine the target similarity matching result; The execution module 30 is used to identify the currency, denomination, and orientation of the banknote based on the target similarity matching result, and to determine the banknote attribute information.

[0091] The acquisition module 10 is also used to acquire sensor signals of banknotes of different currencies and denominations in multiple preset banknote insertion directions. The sensor signals include at least one of infrared reflection signals, visible light signals and transmission signals. The sensor signal is smoothed and transformed to determine the sensor information of the banknote to be identified; The sensor information of the banknotes to be identified is classified to determine the banknote sample information.

[0092] The processing module 20 is also used to obtain the signal sequence length; Based on the currency sample information, denomination sample information and banknote insertion direction sample information in the banknote sample information, the corresponding template timing signal sequence is determined; A corresponding banknote template library is constructed based on the template timing signal sequence and the length of the signal sequence.

[0093] The processing module 20 is also used to process the banknote sensor information to be identified according to a predefined strategy to determine the signal sequence to be identified; The similarity matching function is used to match the signal sequence to be identified with the target template corresponding to the banknote template library to determine the similarity matching result set; The corresponding target similarity matching result is determined based on the set of similarity matching results.

[0094] The processing module 20 is further configured to identify the banknote as genuine when the maximum similarity matching value in the similarity matching result set is greater than a preset threshold. When the maximum similarity match value in the similarity match result set is less than or equal to a preset threshold, the target similarity match result is that the banknote is identified as counterfeit.

[0095] The execution module 30 is further configured to, when the target similarity matching result indicates that the banknote is genuine, calculate the position number corresponding to the target similarity matching result according to a predefined remainder rule, and determine the position number information and remainder information; Based on the location sequence information and the remainder information, the currency type, denomination, and orientation of the banknote are identified to determine the banknote attribute information.

[0096] The execution module 30 is also used to detect the banknote type and denomination corresponding to the position in the preset sequence number range based on the position number information, and determine the banknote type information and banknote denomination information; Based on the remainder information, the corresponding banknote orientation information is determined, including front facing, front facing backward, back facing forward, and back facing backward. Based on the banknote type information, the banknote denomination information, and the banknote orientation information, the banknote type, denomination, and orientation are identified to obtain banknote attribute information.

[0097] The multi-currency banknote denomination and orientation joint recognition device based on multi-template matching provided in this application, employing the multi-currency banknote denomination and orientation joint recognition method based on multi-template matching in the above embodiments, can solve the technical problem of how to perform multi-currency banknote denomination and orientation joint recognition more accurately and effectively. Compared with the prior art, the beneficial effects of the multi-currency banknote denomination and orientation joint recognition device based on multi-template matching provided in this application are the same as the beneficial effects of the multi-currency banknote denomination and orientation joint recognition method based on multi-template matching provided in the above embodiments, and other technical features in the multi-currency banknote denomination and orientation joint recognition device based on multi-template matching are the same as the features disclosed in the methods of the above embodiments, and will not be repeated here.

[0098] This application provides a multi-currency banknote denomination and orientation joint recognition device based on multi-template matching. The multi-currency banknote denomination and orientation joint recognition device based on multi-template matching includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the multi-currency banknote denomination and orientation joint recognition method based on multi-template matching in the first embodiment described above.

[0099] The following is for reference. Figure 6 This document illustrates a structural diagram suitable for implementing a multi-currency banknote denomination and joint recognition device based on multi-template matching, as described in the embodiments of this application. The multi-currency banknote denomination and joint recognition device based on multi-template matching in the embodiments of this application may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital radio receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), and in-vehicle terminals (e.g., in-vehicle navigation terminals), as well as fixed terminals such as digital TVs and desktop computers. Figure 6 The multi-currency banknote denominations based on multi-template matching shown are merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of this application.

[0100] like Figure 6As shown, a multi-currency banknote denomination recognition device based on multi-template matching may include a processing unit 1001 (e.g., a central processing unit, a graphics processor, etc.), which can perform various appropriate actions and processes according to a program stored in ROM (Read Only Memory) 1002 or a program loaded from storage device 1003 into RAM (Random Access Memory) 1004. RAM 1004 also stores various programs and data required for the operation of the multi-currency banknote denomination recognition device based on multi-template matching. The processing unit 1001, ROM 1002, and RAM 1004 are interconnected via bus 1005. Input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to I / O interface 1006: input devices 1007 including, for example, touchscreens, touchpads, keyboards, mice, image sensors, microphones, accelerometers, gyroscopes, etc.; output devices 1008 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 1003 including, for example, magnetic tapes, hard disks, etc.; and communication devices 1009. Communication device 1009 allows the multi-currency banknote denomination and oriented joint identification device based on multi-template matching to exchange data wirelessly or via wired communication with other devices. Although the figure shows a multi-currency banknote denomination and oriented joint identification device based on multi-template matching with various systems, it should be understood that it is not required to implement or possess all of the systems shown. More or fewer systems may be implemented alternatively.

[0101] Specifically, according to the embodiments disclosed in this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device, or installed from storage device 1003, or installed from ROM 1002. When the computer program is executed by processing device 1001, it performs the functions defined in the methods of the embodiments disclosed in this application.

[0102] The multi-currency banknote denomination and orientation joint recognition device based on multi-template matching provided in this application, employing the multi-currency banknote denomination and orientation joint recognition method based on multi-template matching in the above embodiments, can solve the technical problem of how to perform multi-currency banknote denomination and orientation joint recognition more accurately and effectively. Compared with the prior art, the beneficial effects of the multi-currency banknote denomination and orientation joint recognition device based on multi-template matching provided in this application are the same as the beneficial effects of the multi-currency banknote denomination and orientation joint recognition method based on multi-template matching provided in the above embodiments, and other technical features in this multi-currency banknote denomination and orientation joint recognition device are the same as those disclosed in the previous embodiment method, and will not be repeated here.

[0103] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any suitable manner in one or more embodiments or examples.

[0104] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0105] This application provides a computer-readable storage medium having computer-readable program instructions (i.e., a computer program) stored thereon, which are used to execute the multi-currency banknote denomination and orientation joint recognition method based on multi-template matching in the above embodiments.

[0106] The computer-readable storage medium provided in this application may be, for example, a USB flash drive, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, system, or device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.

[0107] The aforementioned computer-readable storage medium may be included in a multi-currency banknote denomination and joint recognition device based on multi-template matching; or it may exist independently and not assembled into a multi-currency banknote denomination and joint recognition device based on multi-template matching.

[0108] The aforementioned computer-readable storage medium carries one or more programs. When these programs are executed by a multi-currency banknote denomination and orientation joint recognition device based on multi-template matching, the device performs the following: acquires sensor information and sample information of banknotes of different currencies and denominations in multiple preset banknote insertion directions; constructs a corresponding banknote template library based on the currency sample information, denomination sample information, and insertion direction sample information in the banknote sample information; matches the sensor information of the banknotes to be recognized with the target template corresponding to the banknote template library using a similarity matching function to determine the target similarity matching result; and identifies the currency, denomination, and orientation of the banknotes based on the target similarity matching result to determine the banknote attribute information.

[0109] Computer program code for performing the operations of this application can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a Local Area Network (LAN) or a Wide Area Network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0110] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0111] The modules described in the embodiments of this application can be implemented in software or hardware. The names of the modules do not necessarily limit the functionality of the unit itself.

[0112] The readable storage medium provided in this application is a computer-readable storage medium that stores computer-readable program instructions (i.e., a computer program) for executing the above-described multi-currency banknote denomination and joint recognition method based on multi-template matching. This solves the technical problem of how to more accurately and effectively perform multi-currency banknote denomination and joint recognition. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as those of the multi-currency banknote denomination and joint recognition method based on multi-template matching provided in the above embodiments, and will not be repeated here.

[0113] The above description is only a part of the embodiments of this application and does not limit the patent scope of this application. All equivalent structural transformations made under the technical concept of this application and using the contents of the specification and drawings of this application, or direct / indirect applications in other related technical fields, are included in the patent protection scope of this application.

Claims

1. A method for joint recognition of denominations and orientations of multi-currency banknotes based on multi-template matching, characterized in that, The method includes: Acquire sensor information and banknote sample information of banknotes of different currencies and denominations in multiple preset banknote insertion directions; A corresponding banknote template library is constructed based on the currency sample information, denomination sample information, and banknote insertion direction sample information in the banknote sample information. The similarity matching function is used to match the sensor information of the banknote to be identified with the target template corresponding to the banknote template library to determine the target similarity matching result; Based on the target similarity matching results, the currency type, denomination, and orientation of the banknote are identified to determine the banknote attribute information.

2. The method as described in claim 1, characterized in that, The steps of acquiring sensor information and sample information of banknotes of different currencies and denominations in multiple preset banknote insertion directions include: The sensor signals of banknotes of different currencies and denominations in multiple preset banknote insertion directions are acquired. The sensor signals include at least one of infrared reflection signals, visible light signals and transmission signals. The sensor signal is smoothed and transformed to determine the sensor information of the banknote to be identified; The sensor information of the banknotes to be identified is classified to determine the banknote sample information.

3. The method as described in claim 1, characterized in that, The step of constructing a corresponding banknote template library based on the currency sample information, denomination sample information, and banknote insertion direction sample information in the banknote sample information includes: Obtain the length of the signal sequence; Based on the currency sample information, denomination sample information and banknote insertion direction sample information in the banknote sample information, the corresponding template timing signal sequence is determined; A corresponding banknote template library is constructed based on the template timing signal sequence and the length of the signal sequence.

4. The method as described in claim 1, characterized in that, The step of matching the sensor information of the banknote to be identified with the target template corresponding to the banknote template library using a similarity matching function to determine the target similarity matching result includes: Based on the sensor information of the banknote to be identified, the signal sequence to be identified is determined according to a predefined strategy; The similarity matching function is used to match the signal sequence to be identified with the target template corresponding to the banknote template library to determine the similarity matching result set; The corresponding target similarity matching result is determined based on the set of similarity matching results.

5. The method as described in claim 4, characterized in that, The step of determining the corresponding target similarity matching result based on the similarity matching result set includes: When the maximum similarity matching value in the similarity matching result set is greater than a preset threshold, the target similarity matching result is that the banknote is identified as genuine. When the maximum similarity match value in the similarity match result set is less than or equal to a preset threshold, the target similarity match result is that the banknote is identified as counterfeit.

6. The method as described in claim 1, characterized in that, The step of identifying the currency, denomination, and orientation of the banknote based on the target similarity matching result, and determining the banknote attribute information, includes: When the target similarity matching result indicates that the banknote is genuine, the position number corresponding to the target similarity matching result is calculated according to a predefined remainder rule to determine the position number information and remainder information; Based on the location sequence information and the remainder information, the currency type, denomination, and orientation of the banknote are identified to determine the banknote attribute information.

7. The method as described in claim 6, characterized in that, The step of identifying the currency, denomination, and orientation of the banknote based on the location sequence information and the remainder information, and determining the banknote attribute information, includes: Based on the location sequence information, the banknote type and denomination corresponding to the position under the preset sequence range are detected to determine the banknote type information and banknote denomination information; Based on the remainder information, the corresponding banknote orientation information is determined, which includes front facing information, front reverse information, back facing information, and back reverse information. Based on the banknote type information, the banknote denomination information, and the banknote orientation information, the banknote type, denomination, and orientation are identified to obtain banknote attribute information.

8. A multi-currency banknote denomination and orientation joint recognition device based on multi-template matching, characterized in that, The device includes: The acquisition module is used to acquire sensor information and banknote sample information of banknotes of different currencies and denominations in multiple preset banknote insertion directions; The processing module is used to construct a corresponding banknote template library based on the currency sample information, denomination sample information and banknote insertion direction sample information in the banknote sample information; The processing module is also used to match the sensor information of the banknote to be identified with the target template corresponding to the banknote template library using a similarity matching function, and determine the target similarity matching result; The execution module is used to identify the currency, denomination, and orientation of the banknote based on the target similarity matching result, and to determine the banknote attribute information.

9. A multi-currency banknote denomination and orientation joint recognition device based on multi-template matching, characterized in that, The device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the multi-currency banknote denomination and joint identification method based on multi-template matching as described in any one of claims 1 to 7.

10. A storage medium, characterized in that, The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, it implements the steps of the multi-currency banknote denomination and joint identification method based on multi-template matching as described in any one of claims 1 to 7.

Images