Banknote processing method and device, storage medium and electronic equipment
By combining banknote recognition models and anti-counterfeiting detection models, the problem of low accuracy in banknote counting has been solved, enabling effective identification of banknote types and accurate calculation of amounts.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-12-30
- Publication Date
- 2026-04-03
AI Technical Summary
Existing banknote counting methods have limited capabilities in anti-counterfeiting detection, resulting in low accuracy.
A banknote recognition model is used to process banknote images, determine banknote information, and select a matching target anti-counterfeiting detection model from multiple anti-counterfeiting detection models for anti-counterfeiting detection. Combined with a damage detection model, the authenticity and integrity of the banknotes are ensured.
It improves the accuracy of anti-counterfeiting detection and total amount calculation during the banknote counting process, and enables effective identification of normal and abnormal banknotes.
Smart Images
Figure CN121789341A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of artificial intelligence, and more specifically, to a banknote processing method, apparatus, storage medium, and electronic device. Background Technology
[0002] In the financial industry, especially in financial institutions and large commercial organizations, cash counting and management is a daily and crucial task. Currently, most cash counting methods on the market rely on mechanical or photoelectric technology to count and identify banknotes. While these methods can perform basic cash counting functions, their ability to detect counterfeit goods is relatively limited. These methods often depend on fixed detection rules, making it difficult to cope with increasingly sophisticated counterfeit banknote manufacturing techniques, resulting in low accuracy in cash counting.
[0003] There is currently no effective solution to the aforementioned problems in the relevant technologies. Summary of the Invention
[0004] The main objective of this application is to provide a banknote processing method, apparatus, storage medium, and electronic device to solve the problem of low accuracy in banknote counting in related technologies.
[0005] To achieve the above objectives, according to one aspect of this application, a banknote processing method is provided. The method includes: upon detecting that banknotes have been inserted into the banknote inlet of a banknote counter, acquiring an image of each inserted banknote to obtain a banknote image; processing the banknote image using a banknote recognition model to obtain banknote information, wherein the banknote information includes at least one of the following: banknote denomination, banknote region; determining a target anti-counterfeiting detection model matching the banknote information from multiple anti-counterfeiting detection models; performing anti-counterfeiting detection on the banknote image using the target anti-counterfeiting detection model to obtain a first detection result; and determining the quantity and total amount of normal banknotes inserted into the banknote inlet based on the first detection result of the banknotes already inserted into the inlet.
[0006] Optionally, the banknote processing method further includes: acquiring an image of the front of the banknote to obtain a first banknote sub-image; acquiring an image of the back of the banknote to obtain a second banknote sub-image; and determining a banknote image based on the first banknote sub-image and the second banknote sub-image.
[0007] Optionally, the banknote processing method further includes: for each banknote, determining a target damage detection model that matches the banknote information from multiple damage detection models; performing damage detection on the banknote image using the target damage detection model to obtain a second detection result; and determining the number and total amount of normal banknotes included in the banknote inlet based on the first and second detection results of the banknotes already inserted into the banknote inlet.
[0008] Optionally, the banknote processing method further includes: for each banknote, if the first detection result indicates that the banknote is genuine and the second detection result indicates that the banknote is undamaged, the banknote is determined to be a normal banknote; if the first detection result indicates that the banknote is counterfeit, or if the second detection result indicates that the banknote is damaged, the banknote is determined to be an abnormal banknote; after the anti-counterfeiting detection and damage detection of all banknotes in the banknote inlet are completed, the number of normal banknotes is counted, and the total amount is determined based on the face value of the normal banknotes.
[0009] Optionally, the banknote processing method further includes: after determining the number and total amount of normal banknotes included in the banknote inlet based on the first detection result of the banknotes already placed in the banknote inlet, displaying the number and total amount of normal banknotes through the human-computer interaction interface of the banknote counter, and displaying the number and type of abnormal banknotes.
[0010] Optionally, the banknote processing method further includes: after determining the quantity and total amount of normal banknotes included in the banknote inlet based on the first detection result of the banknotes already placed in the banknote inlet, determining the serial numbers of the normal banknotes and the serial numbers of the abnormal banknotes; uploading the serial numbers, quantity, and total amount of the normal banknotes to the cloud, and uploading the serial numbers, abnormality type, and quantity of the abnormal banknotes to the cloud.
[0011] Optionally, the banknote processing method further includes: acquiring a training sample set, wherein the training samples in the training sample set are sample banknote images of sample banknotes, and the real labels of the training samples are sample banknote information of sample banknotes; and training an initial banknote recognition model through the training sample set to obtain a banknote recognition model.
[0012] To achieve the above objectives, according to another aspect of this application, a banknote processing apparatus is provided. The apparatus includes: an acquisition module, configured to acquire an image of each banknote inserted into the banknote inlet of a banknote counter when banknotes are detected being inserted, thereby obtaining a banknote image; a processing module, configured to process the banknote image using a banknote recognition model to obtain banknote information of the banknote image, wherein the banknote information includes at least one of the following: banknote denomination and banknote region; a first determination module, configured to determine a target anti-counterfeiting detection model matching the banknote information from a plurality of anti-counterfeiting detection models; a detection module, configured to perform anti-counterfeiting detection on the banknote image using the target anti-counterfeiting detection model to obtain a first detection result; and a second determination module, configured to determine the quantity and total amount of normal banknotes inserted into the banknote inlet based on the first detection result of the banknotes already inserted into the inlet.
[0013] Optionally, the acquisition module further includes: a first acquisition submodule for acquiring an image of the front of the banknote to obtain a first banknote sub-image; a second acquisition submodule for acquiring an image of the back of the banknote to obtain a second banknote sub-image; and a first determination submodule for determining a banknote image based on the first banknote sub-image and the second banknote sub-image.
[0014] Optionally, the second determining module further includes: a second determining submodule, used to determine, for each banknote, a target damage detection model that matches the banknote information from multiple damage detection models; a detection submodule, used to perform damage detection on the banknote image through the target damage detection model to obtain a second detection result; and a third determining submodule, used to determine the number and total amount of normal banknotes included in the banknote inlet based on the first detection result and the second detection result of the banknotes already placed in the banknote inlet.
[0015] Optionally, the third determining submodule further includes: a first determining unit, used to determine that for each banknote, if the first detection result indicates that the banknote is a genuine banknote and the second detection result indicates that the banknote is not damaged; a second determining unit, used to determine that the banknote is an abnormal banknote if the first detection result indicates that the banknote is a counterfeit banknote, or if the second detection result indicates that the banknote is damaged; and a third determining unit, used to count the number of normal banknotes and determine the total amount based on the face value of the normal banknotes after the anti-counterfeiting detection and damage detection of all banknotes in the banknote inlet are completed.
[0016] Optionally, the banknote processing device may also include a display module for displaying the quantity and total amount of normal banknotes and the quantity and type of abnormal banknotes through the human-machine interface of the banknote counter.
[0017] Optionally, the banknote processing device further includes: a third determining module for determining the serial numbers of normal banknotes and abnormal banknotes; and an uploading module for uploading the serial numbers, quantity, and total amount of normal banknotes to the cloud, and uploading the serial numbers, abnormality type, and quantity of abnormal banknotes to the cloud.
[0018] Optionally, the banknote processing device further includes: a second acquisition module for acquiring a training sample set, wherein the training samples in the training sample set are sample banknote images of sample banknotes, and the real labels of the training samples are sample banknote information of sample banknotes; and a training module for training an initial banknote recognition model using the training sample set to obtain a banknote recognition model.
[0019] To achieve the above objectives, according to another aspect of this application, a computer-readable storage medium is provided, the computer-readable storage medium including a stored executable program, wherein, when the executable program is executed, it controls the device where the computer-readable storage medium is located to perform the above-described banknote processing method.
[0020] To achieve the above objectives, according to another aspect of this application, an electronic device is provided, the electronic device including a memory storing an executable program; and a processor for running the program, wherein the program executes the above-described banknote processing method when it runs.
[0021] To achieve the above objectives, according to another aspect of this application, a computer program product is provided, including computer instructions that, when executed by a processor, implement the steps of the above-described banknote processing method.
[0022] In this embodiment, a banknote recognition model is used to process the banknote image to obtain the banknote information, thus achieving effective identification of the banknote type of each banknote placed in the banknote counter. By determining the target anti-counterfeiting detection model that matches the banknote information from multiple anti-counterfeiting detection models, the target anti-counterfeiting detection model to be used is determined based on the banknote type, thereby improving the accuracy of anti-counterfeiting detection. Consequently, when determining the quantity and total amount of normal banknotes based on the anti-counterfeiting detection results, the accuracy of banknote counting can be effectively improved.
[0023] Therefore, the method provided in this application achieves the purpose of using the anti-counterfeiting detection model corresponding to the banknote type for anti-counterfeiting detection during the banknote counting process, thereby reducing the technical effect of low banknote counting accuracy and solving the technical problem of low banknote counting accuracy in related technologies. Attached Figure Description
[0024] The accompanying drawings, which form part of this application, are used to provide a further understanding of this application. The illustrative embodiments and descriptions of this application are used to explain this application and do not constitute an undue limitation of this application. In the drawings:
[0025] Figure 1 This is a hardware structure block diagram of a computer terminal provided according to an embodiment of this application;
[0026] Figure 2 This is a flowchart of a banknote processing method provided according to an embodiment of this application;
[0027] Figure 3 This is a schematic diagram of a banknote processing method provided according to an embodiment of this application;
[0028] Figure 4 This is a schematic diagram of a banknote processing device provided according to an embodiment of this application;
[0029] Figure 5 This is a structural block diagram of an electronic device according to an embodiment of this application. Detailed Implementation
[0030] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.
[0031] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.
[0032] It should be noted that the information collected in this application (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for display, data used for analysis, etc.) are information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, storage, use, processing, transmission, provision, disclosure, and application of this data all comply with relevant laws, regulations, and standards, necessary confidentiality measures have been taken, and they do not violate public order and good morals. Corresponding access points are provided for users to choose to authorize or refuse. For example, interfaces are set up between this system and relevant users or organizations, providing users with corresponding access points to choose to agree to or refuse automated decision-making results; if the user chooses to refuse, the process proceeds to the expert decision-making stage.
[0033] Example 1
[0034] According to an embodiment of this application, an embodiment of a banknote processing method is also provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.
[0035] The method embodiment provided in Embodiment 1 of this application can be executed on a mobile terminal, computer terminal, or similar computing device. Figure 1 A hardware block diagram of a computer terminal (or mobile device) for implementing a banknote processing method is shown. Figure 1 As shown, the computer terminal 10 (or mobile device) may include one or more processors 102 (shown as 102a, 102b, ..., 102n in the figure) 102 (processor 102 may include, but is not limited to, a microprocessor (MCU) or a field-programmable gate array (FPGA), etc.), a memory 104 for storing data, and a transmission device 106 for communication functions. In addition, it may also include: a display, an input / output (I / O) interface, a Universal Serial Bus (USB) port (which may be included as one of the ports of a BUS bus), a network interface, a power supply, and / or a camera. Those skilled in the art will understand that... Figure 1 The structure shown is for illustrative purposes only and does not limit the structure of the aforementioned electronic device. For example, computer terminal 10 may also include... Figure 1 The more or fewer components shown, or having the same Figure 1 The different configurations shown.
[0036] It should be noted that the aforementioned one or more processors 102 and / or other data processing circuits are generally referred to herein as "data processing circuits". These data processing circuits may be embodied, in whole or in part, in software, hardware, firmware, or any other combination thereof. Furthermore, the data processing circuits may be a single, independent processing module, or may be integrated, in whole or in part, into any other element within the computer terminal 10 (or mobile device). As involved in the embodiments of this application, the data processing circuits serve as a processor control mechanism (e.g., selection of a variable resistor termination path connected to an interface).
[0037] The memory 104 can be used to store software programs and modules of application software, such as the program instructions / data storage device corresponding to the banknote processing method in this embodiment. The processor 102 executes various functional applications and data processing by running the software programs and modules stored in the memory 104, thereby realizing the aforementioned banknote processing method. The memory 104 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include memory remotely located relative to the processor 102, and these remote memories can be connected to the computer terminal 10 via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.
[0038] The transmission device 106 is used to receive or send data via a network. Specific examples of the network described above may include a wireless network provided by the communication provider of the computer terminal 10. In one example, the transmission device 106 includes a Network Interface Controller (NIC), which can connect to other network devices via a base station to communicate with the Internet. In another example, the transmission device 106 may be a Radio Frequency (RF) module, used for wireless communication with the Internet.
[0039] The display can be, for example, a touchscreen liquid crystal display (LCD), which allows the user to interact with the user interface of the computer terminal 10 (or mobile device).
[0040] Under the aforementioned operating environment, this application provides the following: Figure 2 The banknote processing method shown. Figure 2 This is a flowchart of a banknote processing method according to Embodiment 1 of this application.
[0041] Step S201: When banknotes are detected being inserted into the banknote inlet of the banknote counter, an image of each inserted banknote is captured to obtain a banknote image.
[0042] Optionally, electronic devices, application systems, servers, or other similar devices can be used as the executing entity of this application. In this embodiment, the target processing system can be used as the executing entity to execute the above-described banknote processing method. Optionally, the above-described target processing system can be applied to a banknote counting machine.
[0043] In an optional embodiment, when a user inserts banknotes into the banknote feed slot of the banknote counter, the target processing system can activate the image acquisition device inside the banknote counter to acquire an image of each inserted banknote. For example, a high-precision optical scanning system equipped with multiple light sources (such as white light, ultraviolet light, and infrared light) can be used to acquire images of the banknotes and obtain banknote images.
[0044] Optionally, the users mentioned above can be operational staff within a financial institution. Alternatively, the users mentioned above can also be holders of banknotes.
[0045] Step S202: Process the banknote image using a banknote recognition model to obtain banknote information, wherein the banknote information includes at least one of the following: banknote denomination and banknote region.
[0046] Optionally, the banknote recognition model can be a deep learning model, such as a neural network model, which could be a convolutional neural network or other neural networks capable of processing image data. The target processing system can collect a large amount of banknote image data of different denominations and regions, perform annotation and training, so that the model can accurately identify banknote information under various lighting conditions. Through the processing of the banknote recognition model, the automation and accuracy of banknote counting can be improved, reducing reliance on manual identification.
[0047] After obtaining the banknote image, it is input into a banknote recognition model. The model then processes the image to obtain the banknote information. This information includes at least one of the following: the banknote denomination and the region where it was issued. The region can be understood as the area where the banknote was actually issued and circulated. Each banknote has its unique design and anti-counterfeiting features, which are typically associated with the region where it was issued.
[0048] In an optional embodiment, the banknote information includes the region to which the banknote belongs and the banknote denomination.
[0049] Step S203: Determine the target anti-counterfeiting detection model that matches the banknote information from multiple anti-counterfeiting detection models.
[0050] The anti-counterfeiting detection model can be a deep learning model, such as a neural network model, which can be a convolutional neural network or other neural networks capable of processing image data. The anti-counterfeiting detection model can be trained using a first training sample set, where the training samples are sample banknotes, and the true labels of the training samples represent the authenticity of the sample banknotes.
[0051] The target processing system can be configured with multiple anti-counterfeiting detection models. Different models are used to detect banknotes with different information. The mapping relationship between banknote information and anti-counterfeiting detection models can be preset within the target processing system. After obtaining the banknote information of a particular banknote, the target processing system can determine the target anti-counterfeiting detection model that matches the banknote information from among the multiple anti-counterfeiting detection models based on the aforementioned mapping relationship.
[0052] Step S204: Perform anti-counterfeiting detection on the banknote image using the target anti-counterfeiting detection model to obtain the first detection result.
[0053] In an optional embodiment, the target anti-counterfeiting detection model can detect anti-counterfeiting features on banknotes, such as watermarks, microtext, fluorescent marks, holograms, security threads, colored fibers, etc., to verify the authenticity of the banknotes.
[0054] The target processing system can input a banknote image into a target anti-counterfeiting detection model, process it through the model, and obtain a first detection result. This first detection result is used to indicate the authenticity of the banknote.
[0055] Step S205: Determine the number and total amount of normal banknotes entering the banknote inlet based on the first detection result of the banknotes already placed in the banknote inlet.
[0056] For example, banknotes whose first detection result indicates they are genuine are identified as normal banknotes, and banknotes whose first detection result indicates they are counterfeit are identified as abnormal banknotes.
[0057] For example, a damage inspection is performed on banknotes to obtain a second inspection result. Based on the first and second inspection results of the banknotes already inserted into the banknote feed slot, the number and total amount of normal banknotes are determined.
[0058] After identifying normal / abnormal banknotes in the banknote inlet, count the number of normal banknotes and add up the face value of all normal banknotes to get the total amount.
[0059] In this embodiment, a banknote recognition model is used to process the banknote image to obtain the banknote information, thus achieving effective identification of the banknote type of each banknote placed in the banknote counter. By determining the target anti-counterfeiting detection model that matches the banknote information from multiple anti-counterfeiting detection models, the target anti-counterfeiting detection model to be used is determined based on the banknote type, thereby improving the accuracy of anti-counterfeiting detection. Consequently, when determining the quantity and total amount of normal banknotes based on the anti-counterfeiting detection results, the accuracy of banknote counting can be effectively improved.
[0060] Therefore, the method provided in this application achieves the goal of using an anti-counterfeiting detection model corresponding to the banknote type for anti-counterfeiting detection during the banknote counting process, thereby improving the technical effect of banknote counting accuracy and solving the technical problem of low accuracy in related banknote counting technologies.
[0061] Optionally, in the banknote processing method provided in this application embodiment, the banknote image acquisition to obtain a banknote image includes: acquiring an image of the front of the banknote to obtain a first banknote sub-image; acquiring an image of the back of the banknote to obtain a second banknote sub-image; and determining a banknote image based on the first banknote sub-image and the second banknote sub-image.
[0062] Optionally, the image acquisition device inside the banknote counter can capture an image of the front of the banknote to obtain a first banknote sub-image, and capture an image of the back of the banknote to obtain a second banknote sub-image. For example, one set of cameras can capture images of the front of the banknote, and another set of cameras can capture images of the back of the banknote.
[0063] After obtaining the front image of the banknote (i.e., the first banknote sub-image) and the back image of the banknote (i.e., the second banknote sub-image), the front and back images of the banknote are determined as the banknote image. For example, the front and back images of the banknote are stitched together to obtain the banknote image.
[0064] It should be noted that determining the banknote image based on images of the front and back of the banknote improves the completeness of the banknote image content, thereby improving the accuracy of subsequent detection (such as anti-counterfeiting detection).
[0065] Optionally, in the banknote processing method provided in this application embodiment, determining the number and total amount of normal banknotes included in the banknote inlet based on the first detection result of the banknotes already placed in the banknote inlet includes: for each banknote, determining a target damage detection model that matches the banknote information from multiple damage detection models; performing damage detection on the banknote image through the target damage detection model to obtain a second detection result; and determining the number and total amount of normal banknotes included in the banknote inlet based on the first and second detection results of the banknotes already placed in the banknote inlet.
[0066] The damage detection model can be a deep learning model, such as a neural network model. This could be an image segmentation model or any other neural network capable of processing image data. The damage detection model can be trained using a second training sample set, where the training samples are banknotes, and the true labels of the training samples indicate whether the banknotes are damaged.
[0067] The target processing system can be configured with multiple damage detection models. Different damage detection models are used to detect whether banknotes with different information are damaged. The mapping relationship between banknote information and damage detection models can be preset within the target processing system. After obtaining the banknote information of a certain banknote, the target processing system can determine the target damage detection model that matches the banknote information from the multiple damage detection models based on the aforementioned mapping relationship.
[0068] After determining the target damage detection model, the banknote image is input into the target damage detection model, which processes the image and outputs a second detection result. This second detection result characterizes whether the banknote is damaged. Damage detection includes, but is not limited to, detecting creases, tears, stains, and worn areas on the banknote.
[0069] After obtaining the authenticity detection results (first detection result) and damage detection results (second detection result) of the banknotes, the system will combine these two pieces of information to determine which banknotes are considered normal banknotes. For example, a banknote will only be counted as a normal banknote if it passes both the authenticity detection (i.e., it is not counterfeit) and damage detection (i.e., the degree of damage is within the acceptable range, i.e., it is not damaged).
[0070] It should be noted that banknotes issued in different regions may have design differences, such as material hardness and printing clarity. These differences will affect the standards and methods for damage detection. For example, for some thinner banknotes, a more sensitive detection model may be needed to identify minor abrasions or tears; while for harder polymer banknotes, the focus may need to be on detecting larger physical damage. Therefore, the above steps improve the targeting of damage detection, thereby improving the accuracy of banknote counting.
[0071] Optionally, in the banknote processing method provided in this application embodiment, the quantity and total amount of normal banknotes included in the banknote inlet are determined based on the first detection result and the second detection result of the banknotes already placed in the banknote inlet. This includes: for each banknote, if the first detection result indicates that the banknote is a genuine banknote and the second detection result indicates that the banknote is not damaged, the banknote is determined to be a normal banknote; if the first detection result indicates that the banknote is a counterfeit banknote, or if the second detection result indicates that the banknote is damaged, the banknote is determined to be an abnormal banknote; after the anti-counterfeiting detection and damage detection of all banknotes in the banknote inlet are completed, the quantity of normal banknotes is counted, and the total amount is determined based on the face value of the normal banknotes.
[0072] Optionally, a banknote will only be considered a normal banknote if it passes both the system's authenticity verification and physical condition check. Conversely, if a banknote fails either detection criterion, whether it is judged to be counterfeit (first detection result indicates counterfeit) or damaged beyond acceptable limits (second detection result indicates damage), it will be marked as an abnormal banknote.
[0073] After the system has completed the inspection of all banknotes inserted into the cash inlet, it will count the number of banknotes marked as normal and calculate the total amount of cash based on the face value of each normal banknote. For example, the face values of the normal banknotes will be added together to obtain the total amount of normal banknotes.
[0074] It should be noted that the above method enables accurate identification of normal and abnormal banknotes, thereby effectively improving the accuracy of banknote counting.
[0075] Optionally, in the banknote processing method provided in this application embodiment, after determining the number and total amount of normal banknotes included in the banknote inlet based on the first detection result of the banknotes already placed in the banknote inlet, the method further includes: displaying the number and total amount of normal banknotes through the human-computer interaction interface of the banknote counter, and displaying the number and type of abnormal banknotes.
[0076] Optionally, after counting the number and total amount of normal banknotes entering the banknote inlet, the target processing system can display the number and total amount of banknotes identified as normal on the human-machine interface of the banknote counter. For example, one optional display could be: "X normal banknotes identified, total amount Y yuan".
[0077] In addition to displaying information about normal banknotes, the interface can also list the quantity and specific type of abnormal banknotes. The abnormality type can be "counterfeit" or "severely damaged," among others.
[0078] In an optional embodiment, the target processing system may also provide voice prompts via a voice broadcasting device for the following: the number and total amount of normal banknotes, and the number and type of abnormal banknotes.
[0079] It should be noted that through real-time data display and detailed explanations of anomaly types, operators can have a comprehensive understanding of the banknote counting machine's operating status, promptly address any potential problems, and facilitate manual verification by operators.
[0080] Optionally, in the banknote processing method provided in this application embodiment, after determining the quantity and total amount of normal banknotes included in the banknote inlet based on the first detection result of the banknotes already placed in the banknote inlet, the method further includes: determining the serial numbers of normal banknotes and abnormal banknotes; uploading the serial numbers, quantity, and total amount of normal banknotes to the cloud, and uploading the serial numbers, abnormality types, and quantity of abnormal banknotes to the cloud.
[0081] Optionally, after completing the banknote inspection, the system will read and record the serial number (also known as the serial number) on each banknote, for both normal and abnormal banknotes. The serial number is a unique string of numbers or alphanumeric characters used to identify the banknote. This operation can be achieved using image recognition technology, for example, identifying the banknote serial number from a banknote image.
[0082] After identifying the serial numbers of the legitimate and fraudulent banknotes, the serial numbers, quantity, and total amount of the legitimate banknotes are uploaded to the cloud, as are the serial numbers, fraud type, and quantity of the fraudulent banknotes. Fraud types can include counterfeit banknotes, damaged banknotes, etc. The data uploaded to the cloud can be structured data or image files.
[0083] In an optional embodiment, the banknote counting data is uploaded to a cloud server (i.e., the aforementioned cloud) in real time via a wireless network, supporting data synchronization across multiple devices and improving data real-time performance and consistency. The cloud server can employ a highly secure storage solution to ensure data privacy and security. Financial institutions can view real-time banknote flow through the cloud server, supporting data visualization functions such as charts and reports for intuitive analysis of banknote flow trends and distribution. Furthermore, the cloud also supports historical data querying and analysis, allowing financial institutions to trace historical banknote counting records and provide reliable data support for auditing, financial decision-making, and other tasks.
[0084] In an optional embodiment, the cloud can automatically generate a banknote counting report based on the banknote data uploaded by the system (i.e., the data corresponding to normal banknotes and abnormal banknotes mentioned above), including the total amount, the number of banknotes, the damage status, etc.
[0085] In an optional embodiment, the cloud can send the banknote data uploaded by the system to the user's email address or a third-party system (such as a financial institution's management system). If counterfeit or damaged banknotes are detected, the cloud can simultaneously generate an alert message.
[0086] It should be noted that the above methods improve the traceability of banknote counting data.
[0087] Optionally, in the banknote processing method provided in this application embodiment, the banknote recognition model is obtained in the following way: obtaining a training sample set, wherein the training samples in the training sample set are sample banknote images of sample banknotes, and the real labels of the training samples are sample banknote information of sample banknotes; and training an initial banknote recognition model through the training sample set to obtain the banknote recognition model.
[0088] The sample banknotes can cover different denominations, years of issue, regions, and conditions (new / old, damaged) to ensure the model maintains a high recognition rate in various real-world scenarios. For each sample banknote, its sample banknote information should also be included; this information serves as the "true label" during training and is used to compare the accuracy of the model's predictions. Optionally, the sample banknote information for the sample banknotes has the same content format as the aforementioned banknote information, so it will not be repeated here.
[0089] After obtaining the training sample set, the initial banknote recognition model is trained using the training sample set to obtain the banknote recognition model.
[0090] It should be noted that the above method enables effective training of the initial banknote recognition model, thereby improving the recognition accuracy of the trained banknote recognition model.
[0091] In an optional embodiment, the aforementioned banknote counter may include a high-speed banknote counting module equipped with a high-speed conveyor belt and precise counting sensors. Through optimized mechanical design, this module can achieve rapid banknote counting at a rate of one banknote per minute, meeting the needs of financial institutions for efficient banknote processing. The conveyor belt can be made of highly wear-resistant materials to ensure stability during long-term operation. It can also be equipped with an intelligent adjustment system that automatically adjusts the conveyor speed according to the thickness, material, and other characteristics of the banknotes, reducing the probability of banknote jamming and misjudgment. Furthermore, the high-speed banknote counting module can support the simultaneous detection of multiple banknotes. Through sensor technology, it can effectively identify overlapping or creased banknotes, avoiding counting errors. The module also features intelligent calibration, automatically calibrating sensor parameters periodically to ensure accuracy and stability over long-term use.
[0092] In an optional embodiment, the human-machine interface of the banknote counter is equipped with a touchscreen and voice prompts. The touchscreen can be a high-resolution display that supports multi-touch operation, facilitating equipment settings, data queries, and function selection for operators. The voice prompt function provides clear voice announcements, real-time feedback on banknote counting progress, recognition results, and error alerts, improving operational convenience and efficiency. Furthermore, the user interface can support multilingual switching to adapt to the needs of users in different regions.
[0093] In an alternative embodiment, Figure 3 This is a schematic diagram of a banknote processing method provided according to an embodiment of this application. Figure 3 An optional application process of this embodiment will be described. For example... Figure 3 As shown, when the target processing system detects banknotes being inserted into the banknote feed slot of the banknote counter, it acquires an image of each inserted banknote. Then, a model performs type recognition, anti-counterfeiting detection, and damage detection on the banknote images, identifying normal and abnormal banknotes based on the model's processing results. Afterward, the banknote data for normal and abnormal banknotes is uploaded to the cloud for storage and analysis, such as generating a banknote counting report. The cloud can then send the banknote data or the generated banknote counting report to the user's email address or a third-party system (such as a financial institution management system).
[0094] Therefore, the method provided in this application achieves the goal of using an anti-counterfeiting detection model corresponding to the banknote type for anti-counterfeiting detection during the banknote counting process, thereby improving the technical effect of banknote counting accuracy and solving the technical problem of low accuracy in related banknote counting technologies.
[0095] It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases the steps shown or described may be executed in a different order than that shown here.
[0096] Example 2
[0097] This application also provides a banknote processing apparatus. It should be noted that the banknote processing apparatus of this application can be used to execute the banknote processing method provided in this application. The banknote processing apparatus provided in this application is described below.
[0098] According to an embodiment of this application, an apparatus for implementing the above-described banknote processing method is also provided, such as... Figure 4 As shown, the device includes:
[0099] The acquisition module 401 is used to acquire images of each banknote when it detects that banknotes have been put into the banknote inlet of the banknote counter, and to obtain banknote images.
[0100] Processing module 402 is used to process banknote images through a banknote recognition model to obtain banknote information of the banknote image, wherein the banknote information includes at least one of the following: banknote denomination and banknote region;
[0101] The first determining module 403 is used to determine the target anti-counterfeiting detection model that matches the banknote information from multiple anti-counterfeiting detection models.
[0102] Detection module 404 is used to perform anti-counterfeiting detection on banknote images using a target anti-counterfeiting detection model to obtain a first detection result;
[0103] The second determining module 405 is used to determine the number and total amount of normal banknotes entering the banknote inlet based on the first detection result of the banknotes already placed in the banknote inlet.
[0104] In this embodiment, a banknote recognition model is used to process the banknote image to obtain the banknote information, thus achieving effective identification of the banknote type of each banknote placed in the banknote counter. By determining the target anti-counterfeiting detection model that matches the banknote information from multiple anti-counterfeiting detection models, the target anti-counterfeiting detection model to be used is determined based on the banknote type, thereby improving the accuracy of anti-counterfeiting detection. Consequently, when determining the quantity and total amount of normal banknotes based on the anti-counterfeiting detection results, the accuracy of banknote counting can be effectively improved.
[0105] Therefore, the method provided in this application achieves the goal of using an anti-counterfeiting detection model corresponding to the banknote type for anti-counterfeiting detection during the banknote counting process, thereby improving the technical effect of banknote counting accuracy and solving the technical problem of low accuracy in related banknote counting technologies.
[0106] Optionally, in the banknote processing apparatus provided in this application embodiment, the acquisition module further includes: a first acquisition submodule, used to acquire an image of the front of the banknote to obtain a first banknote sub-image; a second acquisition submodule, used to acquire an image of the back of the banknote to obtain a second banknote sub-image; and a first determination submodule, used to determine a banknote image based on the first banknote sub-image and the second banknote sub-image.
[0107] Optionally, in the banknote processing apparatus provided in this application embodiment, the second determining module further includes: a second determining submodule, used to determine, for each banknote, a target damage detection model that matches the banknote information from multiple damage detection models; a detection submodule, used to perform damage detection on the banknote image through the target damage detection model to obtain a second detection result; and a third determining submodule, used to determine the number and total amount of normal banknotes included in the banknote inlet based on the first detection result and the second detection result of the banknotes already placed in the banknote inlet.
[0108] Optionally, in the banknote processing apparatus provided in this application embodiment, the third determining submodule further includes: a first determining unit, configured to determine that for each banknote, if the first detection result indicates that the banknote is a genuine banknote and the second detection result indicates that the banknote is not damaged; a second determining unit, configured to determine that the banknote is an abnormal banknote if the first detection result indicates that the banknote is a counterfeit banknote, or if the second detection result indicates that the banknote is damaged; and a third determining unit, configured to count the number of normal banknotes and determine the total amount based on the face value of the normal banknotes after the anti-counterfeiting detection and damage detection of all banknotes in the banknote inlet are completed.
[0109] Optionally, in the banknote processing apparatus provided in this application embodiment, the banknote processing apparatus further includes: a display module, used to display the quantity and total amount of normal banknotes through the human-computer interaction interface of the banknote counter, and to display the quantity and type of abnormal banknotes.
[0110] Optionally, in the banknote processing device provided in this application embodiment, the banknote processing device further includes: a third determining module, used to determine the serial number of normal banknotes and the serial number of abnormal banknotes; and an uploading module, used to upload the serial number, quantity, and total amount of normal banknotes to the cloud, and upload the serial number, abnormality type, and quantity of abnormal banknotes to the cloud.
[0111] Optionally, in the banknote processing apparatus provided in this application embodiment, the banknote processing apparatus further includes: a second acquisition module, used to acquire a training sample set, wherein the training samples in the training sample set are sample banknote images of sample banknotes, and the real labels of the training samples are sample banknote information of sample banknotes; and a training module, used to train an initial banknote recognition model through the training sample set to obtain a banknote recognition model.
[0112] It should be noted that the acquisition module 401, processing module 402, first determination module 403, detection module 404, and second determination module 405 mentioned above correspond to steps S201 to S205 in Embodiment 1. The five modules and their corresponding steps implement the same examples and application scenarios, but are not limited to the content disclosed in Embodiment 1. It should be noted that the above modules or units can be hardware or software components stored in memory (e.g., memory 104) and processed by one or more processors (e.g., processors 102a, 102b, ..., 102n). The above modules can also be part of a device and run in the computer terminal 10 provided in Embodiment 1.
[0113] Example 3
[0114] Embodiments of this application may provide an electronic device. Figure 5 This is a structural block diagram of an electronic device according to an embodiment of this application. Figure 5 As shown, the electronic device may include: one or more ( Figure 5 (Only one is shown) processor 1002, memory 1004, memory controller, and peripheral interface, wherein the peripheral interface is connected to the radio frequency module, audio module and display.
[0115] The memory can be used to store software programs and modules, such as the program instructions / modules corresponding to the methods and apparatus in the embodiments of this application. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory, thereby implementing the above-described methods. The memory may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory may further include memory remotely located relative to the processor, and these remote memories can be connected to the terminal via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.
[0116] The processor can access information and applications stored in the memory via a transmission device to perform the following steps: upon detecting that banknotes have been inserted into the banknote feed slot of the banknote counter, for each inserted banknote, an image of the banknote is captured to obtain a banknote image; the banknote image is processed using a banknote recognition model to obtain banknote information, wherein the banknote information includes at least one of the following: banknote denomination, banknote region; a target anti-counterfeiting detection model matching the banknote information is determined from multiple anti-counterfeiting detection models; the banknote image is subjected to anti-counterfeiting detection using the target anti-counterfeiting detection model to obtain a first detection result; based on the first detection result of the banknotes inserted into the banknote feed slot, the number and total amount of normal banknotes included in the banknote feed slot are determined.
[0117] The processor can also call the information and application program stored in the memory through the transmission device to perform the following steps: capture an image of the front of the banknote to obtain a first banknote sub-image; capture an image of the back of the banknote to obtain a second banknote sub-image; and determine a banknote image based on the first banknote sub-image and the second banknote sub-image.
[0118] The processor can also call the information and application stored in the memory through the transmission device to perform the following steps: for each banknote, determine the target damage detection model that matches the banknote information from multiple damage detection models; perform damage detection on the banknote image through the target damage detection model to obtain a second detection result; based on the first and second detection results of the banknotes already placed in the banknote inlet, determine the number and total amount of normal banknotes included in the banknote inlet.
[0119] The processor can also call the information and application programs stored in the memory through the transmission device to perform the following steps: for each banknote, if the first detection result indicates that the banknote is a genuine banknote and the second detection result indicates that the banknote is not damaged, the banknote is determined to be a normal banknote; if the first detection result indicates that the banknote is a counterfeit banknote, or if the second detection result indicates that the banknote is damaged, the banknote is determined to be an abnormal banknote; after the anti-counterfeiting detection and damage detection of all banknotes in the banknote inlet are completed, the number of normal banknotes is counted, and the total amount is determined based on the face value of the normal banknotes.
[0120] The processor can also call the information and application stored in the memory through the transmission device to perform the following steps: after determining the number and total amount of normal banknotes entered into the banknote inlet based on the first detection result of the banknotes already placed in the banknote inlet, the number and total amount of normal banknotes are displayed through the human-machine interface of the banknote counter, and the number and type of abnormal banknotes are also displayed.
[0121] The processor can also call the information and application stored in the memory through the transmission device to perform the following steps: after determining the number and total amount of normal banknotes entered into the banknote inlet based on the first detection result of the banknotes already placed in the banknote inlet, determine the serial number of the normal banknotes and the serial number of the abnormal banknotes; upload the serial number, quantity, and total amount of the normal banknotes to the cloud, and upload the serial number, abnormal type, and quantity of the abnormal banknotes to the cloud.
[0122] The processor can also call the information and application stored in the memory through the transmission device to perform the following steps: obtain a training sample set, wherein the training samples in the training sample set are sample banknote images of sample banknotes, and the real labels of the training samples are sample banknote information of sample banknotes; train an initial banknote recognition model through the training sample set to obtain a banknote recognition model.
[0123] In this embodiment, a banknote recognition model is used to process the banknote image to obtain the banknote information, thus achieving effective identification of the banknote type of each banknote placed in the banknote counter. By determining the target anti-counterfeiting detection model that matches the banknote information from multiple anti-counterfeiting detection models, the target anti-counterfeiting detection model to be used is determined based on the banknote type, thereby improving the accuracy of anti-counterfeiting detection. Consequently, when determining the quantity and total amount of normal banknotes based on the anti-counterfeiting detection results, the accuracy of banknote counting can be effectively improved.
[0124] Therefore, the method provided in this application achieves the goal of using an anti-counterfeiting detection model corresponding to the banknote type for anti-counterfeiting detection during the banknote counting process, thereby improving the technical effect of banknote counting accuracy and solving the technical problem of low accuracy in related banknote counting technologies.
[0125] Those skilled in the art will understand that Figure 5 The structure shown is for illustrative purposes only. Electronic devices can also be smartphones, tablets, handheld computers, mobile internet devices (MIDs), PADs, and other terminal devices. Figure 5 This does not limit the structure of the aforementioned electronic device. For example, electronic devices may also include components that are more... Figure 5 The more or fewer components shown (such as network interfaces, display devices, etc.), or having the same Figure 5 The different configurations shown.
[0126] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be implemented by a program instructing the hardware related to the terminal device. The program can be stored in a computer-readable storage medium, which may include: flash drive, read-only memory (ROM), random access memory (RAM), disk or optical disk, etc.
[0127] Example 4
[0128] Embodiments of this application also provide a storage medium. Optionally, in this embodiment, the storage medium can be used to store the program code executed by the banknote processing method provided in Embodiment 1.
[0129] Optionally, in this embodiment, the storage medium may be located in any computer terminal in a group of computer terminals in a computer network, or in any mobile terminal in a group of mobile terminals.
[0130] This application also provides a computer program product that, when executed on a data processing device, is suitable for performing banknote processing method steps.
[0131] The sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.
[0132] In the above embodiments of this application, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.
[0133] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual coupling, direct coupling, or communication connection may be through some interfaces; the indirect coupling or communication connection between units or modules may be electrical or other forms.
[0134] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.
[0135] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.
[0136] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as a USB flash drive, read-only memory (ROM), random access memory (RAM), portable hard drive, magnetic disk, or optical disk.
[0137] The above description is only a preferred embodiment of this application. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of this application, and these improvements and modifications should also be considered within the scope of protection of this application.
Claims
1. A banknote processing method, characterized in that, include: When a banknote is detected being inserted into the banknote inlet of the banknote counter, an image of each inserted banknote is captured to obtain a banknote image. The banknote image is processed by a banknote recognition model to obtain banknote information, wherein the banknote information includes at least one of the following: banknote denomination and banknote region; Determine the target anti-counterfeiting detection model that matches the banknote information from multiple anti-counterfeiting detection models; The banknote image is subjected to anti-counterfeiting detection using the target anti-counterfeiting detection model to obtain a first detection result; The quantity and total amount of normal banknotes received by the banknotes in the banknote inlet are determined based on the first detection result of the banknotes already inserted into the banknote inlet.
2. The method according to claim 1, characterized in that, The banknote is image acquired to obtain a banknote image, including: An image of the front of the banknote is captured to obtain a first banknote sub-image; An image of the back of the banknote is captured to obtain a second banknote sub-image; The banknote image is determined based on the first banknote sub-image and the second banknote sub-image.
3. The method according to claim 1, characterized in that, Based on the first detection result of the banknotes already inserted into the banknote inlet, the quantity and total amount of normal banknotes inserted into the banknote inlet are determined, including: For each banknote, a target damage detection model that matches the banknote information is determined from multiple damage detection models; The banknote image is subjected to damage detection using the target damage detection model to obtain a second detection result; Based on the first and second detection results of the banknotes already placed in the banknote inlet, the quantity and total amount of normal banknotes included in the banknote inlet are determined.
4. The method according to claim 3, characterized in that, Based on the first and second detection results of the banknotes already inserted into the banknote inlet, the quantity and total amount of normal banknotes inserted into the banknote inlet are determined, including: For each banknote, if the first detection result indicates that the banknote is genuine and the second detection result indicates that the banknote is undamaged, the banknote is determined to be a normal banknote. If the first detection result indicates that the banknote is counterfeit, or if the second detection result indicates that the banknote is damaged, the banknote is determined to be an abnormal banknote. After completing the anti-counterfeiting and damage detection of all banknotes in the banknote inlet, the number of normal banknotes is counted, and the total amount is determined based on the face value of the normal banknotes.
5. The method according to claim 1, characterized in that, After determining the quantity and total amount of normal banknotes received by the banknote inlet based on the first detection result of the banknotes already inserted into the inlet, the method further includes: The human-computer interaction interface of the banknote counter displays the quantity and total amount of normal banknotes, as well as the quantity and type of abnormal banknotes.
6. The method according to claim 1, characterized in that, After determining the quantity and total amount of normal banknotes received by the banknote inlet based on the first detection result of the banknotes already inserted into the inlet, the method further includes: Determine the serial numbers of the normal banknotes and the abnormal banknotes; The serial number, quantity, and total amount of the normal banknotes are uploaded to the cloud, as are the serial number, abnormality type, and quantity of the abnormal banknotes.
7. The method according to claim 1, characterized in that, The banknote recognition model is obtained through the following method: Obtain a training sample set, wherein the training samples in the training sample set are sample banknote images of sample banknotes, and the true labels of the training samples are sample banknote information of the sample banknotes; The initial banknote recognition model is trained using a training sample set to obtain the banknote recognition model.
8. A banknote processing device, characterized in that, include: The acquisition module is used to acquire images of each banknote when it detects that banknotes have been inserted into the banknote inlet of the banknote counter, thereby obtaining banknote images. The processing module is used to process the banknote image through a banknote recognition model to obtain banknote information of the banknote image, wherein the banknote information includes at least one of the following: banknote denomination and banknote region; The first determining module is used to determine the target anti-counterfeiting detection model that matches the banknote information from multiple anti-counterfeiting detection models; The detection module is used to perform anti-counterfeiting detection on the banknote image using the target anti-counterfeiting detection model to obtain a first detection result; The second determining module is used to determine the quantity and total amount of normal banknotes entering the banknote inlet based on the first detection result of the banknotes already placed in the banknote inlet.
9. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored executable program, wherein, when the executable program is executed, it controls the device on which the computer-readable storage medium is located to perform the banknote processing method according to any one of claims 1 to 7.
10. An electronic device, characterized in that, include: Memory, which stores executable programs; A processor for running the program, wherein the program, when running, performs the banknote processing method according to any one of claims 1 to 7.