CN114255540A - Method, device, equipment and storage medium for identifying stained paper money - Google Patents
Method, device, equipment and storage medium for identifying stained paper money Download PDFInfo
- Publication number
- CN114255540A CN114255540A CN202210086424.9A CN202210086424A CN114255540A CN 114255540 A CN114255540 A CN 114255540A CN 202210086424 A CN202210086424 A CN 202210086424A CN 114255540 A CN114255540 A CN 114255540A
- Authority
- CN
- China
- Prior art keywords
- paper money
- banknote
- paper
- stained
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 50
- 238000003860 storage Methods 0.000 title claims abstract description 17
- 238000005520 cutting process Methods 0.000 claims abstract description 53
- 238000012549 training Methods 0.000 claims abstract description 22
- 238000011109 contamination Methods 0.000 claims description 39
- 238000004590 computer program Methods 0.000 claims description 15
- 238000013135 deep learning Methods 0.000 claims description 9
- 230000006378 damage Effects 0.000 claims description 3
- 230000001788 irregular Effects 0.000 claims description 2
- 230000002159 abnormal effect Effects 0.000 claims 1
- 238000001514 detection method Methods 0.000 abstract description 12
- 238000004891 communication Methods 0.000 description 8
- 238000012545 processing Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 5
- 230000008569 process Effects 0.000 description 4
- 230000001010 compromised effect Effects 0.000 description 3
- 238000013527 convolutional neural network Methods 0.000 description 3
- 230000007547 defect Effects 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 238000009826 distribution Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 230000001771 impaired effect Effects 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000002372 labelling Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000000356 contaminant Substances 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000009526 moderate injury Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 239000000049 pigment Substances 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000001953 sensory effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07D—HANDLING OF COINS OR VALUABLE PAPERS, e.g. TESTING, SORTING BY DENOMINATIONS, COUNTING, DISPENSING, CHANGING OR DEPOSITING
- G07D7/00—Testing specially adapted to determine the identity or genuineness of valuable papers or for segregating those which are unacceptable, e.g. banknotes that are alien to a currency
- G07D7/181—Testing mechanical properties or condition, e.g. wear or tear
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07D—HANDLING OF COINS OR VALUABLE PAPERS, e.g. TESTING, SORTING BY DENOMINATIONS, COUNTING, DISPENSING, CHANGING OR DEPOSITING
- G07D7/00—Testing specially adapted to determine the identity or genuineness of valuable papers or for segregating those which are unacceptable, e.g. banknotes that are alien to a currency
- G07D7/181—Testing mechanical properties or condition, e.g. wear or tear
- G07D7/187—Detecting defacement or contamination, e.g. dirt
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Inspection Of Paper Currency And Valuable Securities (AREA)
Abstract
The embodiment of the invention discloses a method, a device, equipment and a storage medium for identifying stained paper money, which relate to the technical field of paper money detection and comprise the following steps: clustering sample paper currencies to obtain a plurality of paper currency groups, wherein each paper currency group comprises the sample paper currencies with the same characteristics; adding a label to each paper money group to obtain labeled paper money data; cutting the labeled paper money data to obtain cutting sample data, and training through the cutting sample data to obtain a stained paper money identification model; and identifying the paper money to be detected through the stained paper money identification model to obtain a stained result of the paper money to be detected. The method has the advantages that various types of data samples can be obtained by clustering sample paper money and adding labels and the like, the number of the samples of the stained paper money can be increased through cutting treatment, the accuracy of stained paper money recognition model training is ensured, the stained result of the paper money can be accurately obtained through paper money recognition of the stained paper money recognition model, and the recognition efficiency of the stained paper money is improved.
Description
Technical Field
The invention relates to the technical field of paper money detection, in particular to a method, a device, equipment and a storage medium for identifying stained paper money.
Background
Paper money plays an important role in the life of people as a main currency circulation means, and because the currency circulation scale is huge in China, the paper money is inevitably polluted.
The method is characterized in that the defect identification of the paper currency is an important link in the paper currency sorting process, a teller can be adopted for manual identification usually, and under the condition that the number of the paper currency to be identified is large, the method can be adopted for identification by adopting an image processing and neural network training method.
However, most of the current methods based on image processing and neural network training require a large number of sample images to perform feature extraction operations, and banknote contamination has a large number of types in actual production, and meanwhile, rare and infrequent contamination occurs frequently, and common image features of banknote contamination cannot be obtained through a large number of samples, which also causes the defects of low detection efficiency and high detection error rate in the prior art.
Disclosure of Invention
The embodiment of the invention provides a method for identifying stained paper money, which aims to solve the problems of low detection efficiency and high detection error rate of the stained paper money.
According to an aspect of an embodiment of the present invention, there is provided a method of identifying a stained paper money, including: clustering sample paper currencies to obtain a plurality of paper currency groups, wherein each paper currency group comprises the sample paper currencies with the same characteristics;
adding a label to each paper money group to obtain labeled paper money data;
cutting the labeled paper money data to obtain cutting sample data, and training through the cutting sample data to obtain a stained paper money identification model;
and identifying the paper money to be detected through the stained paper money identification model to obtain a stained result of the paper money to be detected.
According to another aspect of the embodiments of the present invention, there is provided an apparatus for recognizing a stained paper money, including: the system comprises a clustering module, a judging module and a judging module, wherein the clustering module is used for clustering original sample paper money to obtain a plurality of paper money groups, and each paper money group comprises the original sample paper money with the same characteristics;
the label adding module is used for adding labels to each paper currency group to obtain labeled paper currency data;
the identification model acquisition module is used for cutting the labeled paper money data to acquire cutting sample data and training the cutting sample data to acquire a stained paper money identification model;
and the paper currency contamination result acquisition module is used for identifying the paper currency to be detected through the contamination paper currency identification model and acquiring the contamination result of the paper currency to be detected.
According to another aspect of the embodiments of the present invention, there is provided an electronic apparatus, including:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein,
the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform a method of identifying a soiled banknote according to any of the embodiments of the present invention.
According to another aspect of embodiments of the present invention, there is provided a computer readable storage medium having stored thereon computer instructions for causing a processor to perform a method of identifying a soiled banknote according to any of the embodiments of the present invention.
According to the technical scheme of the embodiment of the invention, various types of data samples can be obtained by clustering and adding labels to the sample paper money, the number of the samples of the rarely-stained paper money can be further increased by cutting, so that the accuracy of stained paper money recognition model training is ensured, the stained result of the paper money can be accurately obtained by performing paper money recognition through the stained paper money recognition model, the problems of low detection efficiency and high detection error rate of stained paper money are solved, and the recognition efficiency of stained paper money is improved.
It should be understood that the statements in this section do not necessarily identify key or critical features of the embodiments of the present invention, nor do they necessarily limit the scope of the invention. Other features of the present invention will become apparent from the following description.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
FIG. 1 is a flow chart of a method for identifying a stained banknote according to one embodiment of the present invention;
FIG. 2 is a flow chart of a method for identifying a stained banknote according to a second embodiment of the present invention;
FIG. 3 is a schematic structural diagram of a device for identifying a stained paper currency according to a third embodiment of the invention;
fig. 4 is a schematic configuration diagram of an electronic apparatus that implements the method of identifying a stained paper money according to the fourth embodiment of the present invention.
Detailed Description
In order to make the technical solutions of the present invention better understood, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It should be noted that the terms "comprises" and "comprising," and any variations thereof, in the description and claims of the present invention and the above-described drawings, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
Example one
Fig. 1 is a flowchart of a method for identifying a stained paper currency according to an embodiment of the present invention, which is applicable to the identification of a stained paper currency, and the method can be implemented by a device for identifying a stained paper currency, which can be implemented in hardware and/or software, and the device for identifying a stained paper currency can be configured in an electronic device. As shown in fig. 1, the method includes:
s110, clustering the sample paper currency to obtain a plurality of paper currency groups, wherein each paper currency group comprises sample paper currency with the same characteristics.
Note that the banknotes are currency symbols which are issued by countries and forcibly used in place of the metallic currencies. The sample banknotes may be obtained from banknotes circulating in the market, and images of the faces of the sample banknotes are captured by using a camera or other equipment with a capturing function, and the banknote group may include one or more sample banknotes having the same characteristics, which is not limited in this embodiment.
Optionally, clustering the sample banknotes to obtain a plurality of banknote groups includes: extracting specified characteristics of each sample banknote, wherein the specified characteristics comprise gray level characteristics or texture characteristics; and dividing the paper currency with the distance between the specified characteristics within a preset range into the same paper currency group.
The grayscale feature may refer to banknote face image data with only one sampling color per pixel, and the texture feature may be used to describe surface properties of an object corresponding to an image or an image area, such as thickness and density of an image texture. Because the color and brightness of each point on the banknote are different, each point of the photographed image will present different degrees of gray, and clustering the sample banknotes in this embodiment may be to aggregate images with the same gray texture feature, so as to obtain a plurality of banknote groups with the same gray or texture feature. Of course, the sample banknotes may be clustered by the variational self-encoder, and the specific way of clustering the sample banknotes is not limited in this embodiment.
And S120, adding a label to each banknote group to obtain labeled banknote data.
Optionally, the adding a label to each banknote group to obtain labeled banknote data specifically may include: selecting a specified number of sample banknotes from each banknote group; identifying and determining matched label types aiming at the selected sample paper currency in each paper currency group, wherein the label types comprise conventional dirty paper currency, unconventional dirty paper currency and normal paper currency; and adding the label type to each sample paper currency in the corresponding paper currency group to obtain labeled paper currency data.
Alternatively, conventional insults include stroke insults, smear insults, and missing insults, and non-conventional insults include burn-out insults.
The label is used for identifying the classification or content of the product, and is convenient for searching and positioning the identification carried on the label. The labeled banknote may be for identifying the type of banknote. Specifically, for each kind of banknote, the image characteristic distribution is regular, so that the contamination type corresponding to the image contamination can be obtained by finding the distribution form. The insult types for a banknote can include, but are not limited to, conventional insult banknotes, non-conventional insult banknotes, and normal banknotes. Specifically, the conventionally stained paper money in the embodiment may include, but is not limited to, stroke stains, smear stains and missing stains, wherein the stroke stains may be stains formed on the surface of the paper money by using a pen, the smear stains may be stains formed on the paper money by using a pigment or a pen, and the missing stains may be the paper money which is missing and becomes incomplete. Unconventional soiled notes may include, but are not limited to, notes that have been soiled by burn, and normal notes may be clean notes that have not been soiled. The labeled banknote data may be labeled banknote image data having similar gray scale features in the banknote group, and the labeled banknote image data is labeled banknote data.
It should be noted that, since the sample banknotes in each banknote group have the same characteristics, in the present embodiment, only a specified number of sample banknotes need to be selected from each banknote group, where the specified number is a small amount of data relative to the number of sample banknotes of the entire banknote group, and for example, three banknote groups are obtained by clustering: the banknote group A, the banknote group B and the banknote group C are characterized in that the banknote group A comprises 100 sample banknotes, 3 sample banknotes are randomly selected from the banknote group A, a specified number of sample banknotes are identified through expert experience, the matched label type is determined to be burnt-out dirt in unconventional dirt, and the determined burnt-out dirt is added to each sample banknote remaining in the banknote group A. Of course, in the present embodiment, only the banknote group a is described as an example, and the manner of adding labels to the banknote group B and the banknote group B is substantially the same, and the description thereof is omitted in the present embodiment, and all the banknote groups to which labels are added are regarded as labeled banknote data.
S130, cutting the labeled paper money data to obtain cutting sample data, and training through the cutting sample data to obtain a stained paper money identification model.
Optionally, S130 may include: determining a sliding window, wherein the sliding window is smaller than the size of the sample paper currency; performing sliding cutting on the tagged paper money data according to the sliding window to obtain cutting sample data, wherein the cutting sample data is larger than the tagged paper money data; inputting the cutting sample data into a deep learning network for training to obtain a stained paper currency recognition model, wherein the deep learning network comprises a dark net-53 network.
In one specific implementation, each labeled sample banknote may be subjected to sliding cutting according to a preset sliding window, where the sliding window is smaller than the size of the sample banknote, for example, the size of the sample banknote is 30 × 30, and the size of the sliding window may be 3 × 3, so that after one labeled sample banknote is cut, a plurality of cut samples may be obtained, thereby increasing the number of sample banknotes. Because the labeled banknote data also contains unconventional stained banknote data, the number of unconventional stained samples can be increased by cutting the labeled banknote data, namely, the number of the unconventional stained samples contained in the cutting sample data obtained by the cutting process is more than that contained in the original sample data which is not cut, so that the problem of inaccurate model training caused by the small sample amount of the unconventional stained banknotes is solved, and therefore, the stained banknote identification model obtained by training the cutting sample data can be used for accurately detecting various types of stained banknotes, and the identification precision of the stained banknotes is improved.
In one specific implementation, the darknet-53 convolutional neural network may be pre-trained using cut sample data to obtain a trained darknet-53 convolutional neural network. Of course, the present embodiment is described by taking the darknet-53 convolutional neural network as an example, and the specific type of the deep learning network is not limited.
And S140, identifying the paper money to be detected through the stained paper money identification model to obtain a stained result of the paper money to be detected.
The banknote under test may be unknown image data of the banknote including regular insult, irregular insult, and normal type, among others.
Optionally, S140 may include: inputting the paper money to be detected into a stained paper money identification model to obtain the label type of the paper money to be detected; and taking the label type of the paper money to be detected as an defiling result.
The image data of the paper money to be detected is input into the stained paper money identification model for identification training, so that a stained result of the paper money to be detected can be obtained, optionally, the stained result can be a stained result corresponding to the type of the label, for example, the stained result of the paper money can be stroke stained, smearing stained, missing stained and burnt stained.
According to the technical scheme of the embodiment of the invention, various types of data samples can be obtained by clustering and adding labels to sample paper money, the number of samples of rare stained paper money can be further increased by cutting, so that the accuracy of stained paper money recognition model training is ensured, the stained result of the paper money can be accurately obtained by performing paper money recognition through the stained paper money recognition model, the problems of low detection efficiency and high detection error rate of stained paper money are solved, and the recognition efficiency of stained paper money is improved.
Example two
Fig. 2 is a flowchart of a method for identifying a stained paper currency according to a second embodiment of the present invention, where after the step of identifying a paper currency to be tested by a stained paper currency identification model and obtaining a stained result of the paper currency to be tested, the method further includes: and determining the contamination level of the paper money to be detected according to the contamination level standard, and giving an alarm prompt when the contamination level is determined to reach a preset level. Wherein explanations of the same or corresponding terms as those of the above embodiments are omitted. As shown in fig. 2, the method specifically includes the following steps:
s210, clustering the sample paper currency to obtain a plurality of paper currency groups, wherein each paper currency group comprises sample paper currency with the same characteristics.
Optionally, clustering the sample banknotes to obtain a plurality of banknote groups includes: extracting specified characteristics of each sample banknote, wherein the specified characteristics comprise gray level characteristics or texture characteristics; and dividing the paper currency with the distance between the specified characteristics within a preset range into the same paper currency group.
And S220, adding a label to each banknote group to obtain labeled banknote data.
Optionally, the adding a label to each banknote group to obtain labeled banknote data specifically may include: selecting a specified number of sample banknotes from each banknote group; identifying and determining matched label types aiming at the selected sample paper currency in each paper currency group, wherein the label types comprise conventional dirty paper currency, unconventional dirty paper currency and normal paper currency; and adding the label type to each sample paper currency in the corresponding paper currency group to obtain labeled paper currency data.
Alternatively, conventional insults include stroke insults, smear insults, and missing insults, and non-conventional insults include burn-out insults.
And S230, cutting the labeled paper currency data to obtain cutting sample data, and training through the cutting sample data to obtain a stained paper currency recognition model.
Optionally, S230 may include: determining a sliding window, wherein the sliding window is smaller than the size of the sample paper currency; performing sliding cutting on the tagged paper money data according to the sliding window to obtain cutting sample data, wherein the cutting sample data is larger than the tagged paper money data; inputting the cutting sample data into a deep learning network for training to obtain a stained paper currency recognition model, wherein the deep learning network comprises a dark net-53 network.
And S240, identifying the paper money to be detected through the stained paper money identification model to obtain a stained result of the paper money to be detected.
Optionally, S240 may include: inputting the paper money to be detected into a stained paper money identification model to obtain the label type of the paper money to be detected; and taking the label type of the paper money to be detected as an defiling result.
And S250, determining the contamination level of the paper money to be tested according to the contamination level standard, wherein the contamination level standard comprises the corresponding relation between the label type and the contamination level.
The soiling grade can be grade division of the degree of soiling of the paper money, and the degree can be divided according to the degree of face shielding. The insult rating criteria can be classified as severely compromised, moderately compromised, and non-compromised. The serious damage can indicate that most images on the paper money to be detected are shielded, the moderate damage can indicate that the paper money to be detected is partially shielded, and the contamination can indicate that the paper money to be detected is not shielded. Accordingly, taking the example of pen-stroke contamination in conventional contamination, the contamination result can be divided into: stroke-severely impaired, stroke-moderately impaired.
And S260, giving an alarm when the fouling level is determined to reach the preset level.
The preset grade is the stain grade of the medium or above paper currency, and when the stain grade of the paper currency is seriously damaged, namely most of the paper currency is shielded or lost by stains, the paper currency cannot be circulated on the world, so that a corresponding alarm prompt is sent.
Note that, in the present embodiment, the alarm may be given by a sound, a graphic, or the like, and the present embodiment is not limited to a specific form of the alarm.
According to the technical scheme of the embodiment of the invention, various types of data samples can be obtained by clustering and adding labels to the sample paper money, the number of the samples of the rarely-stained paper money can be further increased by cutting, so that the accuracy of stained paper money recognition model training is ensured, the stained result of the paper money can be accurately obtained by performing paper money recognition through the stained paper money recognition model, the problems of low detection efficiency and high detection error rate of stained paper money are solved, and the recognition efficiency of stained paper money is improved. Meanwhile, the contamination grade of the paper money to be detected is determined according to the contamination grade standard, and the alarm prompt is carried out when the contamination grade is determined to reach the preset grade, so that a user can conveniently screen out the paper money which is seriously contaminated and cannot be circulated in time according to the alarm prompt, and the circulation rate of the paper money is improved.
EXAMPLE III
Fig. 3 is a schematic structural diagram of a device for identifying a stained paper currency according to a third embodiment of the present invention. As shown in fig. 3, the apparatus includes: the banknote counting and counting system comprises a clustering module 310, a label adding module 320, a recognition model obtaining module 330 and a banknote soiling result obtaining module 340.
The clustering module 310 is configured to cluster original sample banknotes to obtain a plurality of banknote groups, where each banknote group includes original sample banknotes with the same characteristics;
the label adding module 320 is used for adding labels to each paper currency group to obtain labeled paper currency data;
the identification model acquisition module 330 is configured to perform cutting processing on the labeled banknote data to acquire cutting sample data, and perform training on the cutting sample data to acquire a stained banknote identification model;
the banknote contamination result obtaining module 340 is configured to identify the banknote to be detected through the contaminated banknote identification model, and obtain a contamination result of the banknote to be detected.
Optionally, the clustering module 310 includes:
the specified feature extraction unit is used for extracting specified features of each sample banknote, wherein the specified features comprise gray features or texture features;
and the paper currency group determining unit is used for dividing paper currencies of which the distances among the specified characteristics are within a preset range into the same paper currency group.
Optionally, the tag adding module 320 includes:
a number selection unit for selecting a specified number of sample banknotes from each banknote group;
the label type determining unit is used for identifying and determining the matched label type for the selected sample paper currency in each paper currency group, wherein the label type comprises normal stained paper currency, unconventional stained paper currency and normal paper currency;
and the labeling data acquisition unit is used for adding the label type to each sample banknote in the corresponding banknote group to acquire labeling banknote data.
Alternatively, conventional insults include stroke insults, smear insults, and missing insults, and non-conventional insults include burn-out insults.
Optionally, the recognition model obtaining module 330 includes:
a sliding window determination unit for determining a sliding window, wherein the sliding window is smaller than the size of the sample banknote;
the sample data cutting unit is used for performing sliding cutting on the labeled paper money data according to the sliding window to obtain cutting sample data, wherein the cutting sample data is larger than the labeled paper money data;
and the sample data input unit is used for inputting the cutting sample data into a deep learning network for training to obtain a stained paper currency recognition model, wherein the deep learning network comprises a dark net-53 network.
Optionally, the banknote insult result acquisition module 340 comprises:
the label type obtaining unit is used for inputting the paper money to be detected into the stained paper money identification model and obtaining the label type of the paper money to be detected;
and the contamination result acquisition unit is used for taking the label type of the paper money to be detected as the contamination result.
Optionally, the apparatus further comprises:
the contamination level determining device is used for determining the contamination level of the paper money to be detected according to a contamination level standard, wherein the contamination level standard comprises the corresponding relation between the label type and the contamination level;
and the alarm prompting device is used for giving an alarm prompt when the fouling grade is determined to reach the preset grade.
The stained paper money recognition device provided by the embodiment of the invention can execute the stained paper money recognition method provided by any embodiment of the invention, and has corresponding functional modules and beneficial effects of the execution method.
Example four
FIG. 4 shows a schematic block diagram of an electronic device 10 that may be used to implement an embodiment of the invention. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the inventions described and/or claimed herein.
As shown in fig. 4, the electronic device 10 includes at least one processor 11, and a memory communicatively connected to the at least one processor 11, such as a Read Only Memory (ROM)12, a Random Access Memory (RAM)13, and the like, wherein the memory stores a computer program executable by the at least one processor, and the processor 11 can perform various suitable actions and processes according to the computer program stored in the Read Only Memory (ROM)12 or the computer program loaded from a storage unit 18 into the Random Access Memory (RAM) 13. In the RAM 13, various programs and data necessary for the operation of the electronic apparatus 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other via a bus 14. An input/output (I/O) interface 15 is also connected to bus 14.
A number of components in the electronic device 10 are connected to the I/O interface 15, including: an input unit 16 such as a keyboard, a mouse, or the like; an output unit 17 such as various types of displays, speakers, and the like; a storage unit 18 such as a magnetic disk, an optical disk, or the like; and a communication unit 19 such as a network card, modem, wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information/data with other devices via a computer network such as the internet and/or various telecommunication networks.
The processor 11 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various processors running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, or the like. The processor 11 performs the various methods and processes described above, such as the method of contaminant banknote identification.
In some embodiments, the method of soiled banknote identification may be implemented as a computer program tangibly embodied on a computer readable storage medium, such as the storage unit 18. In some embodiments, part or all of the computer program may be loaded and/or installed onto the electronic device 10 via the ROM 12 and/or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the stained banknote identification method described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to perform the method of soiled banknote identification by any other suitable means (e.g., by means of firmware).
Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuitry, Field Programmable Gate Arrays (FPGAs), Application Specific Integrated Circuits (ASICs), Application Specific Standard Products (ASSPs), system on a chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be special or general purpose, receiving data and instructions from, and transmitting data and instructions to, a storage system, at least one input device, and at least one output device.
A computer program for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the computer programs, when executed by the processor, cause the functions/acts specified in the flowchart and/or block diagram block or blocks to be performed. A computer program can execute entirely on a machine, partly on a machine, as a stand-alone software package partly on a machine and partly on a remote machine or entirely on a remote machine or server.
In the context of the present invention, a computer-readable storage medium may be a tangible medium that can contain, or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. A computer readable storage medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. Alternatively, the computer readable storage medium may be a machine readable signal medium. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
To provide for interaction with a user, the systems and techniques described here can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which a user can provide input to the electronic device. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic, speech, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a back-end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back-end, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), Wide Area Networks (WANs), blockchain networks, and the internet.
The computing system may include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also called a cloud computing server or a cloud host, and is a host product in a cloud computing service system, so that the defects of high management difficulty and weak service expansibility in the traditional physical host and VPS service are overcome.
It should be understood that various forms of the flows shown above may be used, with steps reordered, added, or deleted. For example, the steps described in the present invention may be executed in parallel, sequentially, or in different orders, and are not limited herein as long as the desired results of the technical solution of the present invention can be achieved.
The above-described embodiments should not be construed as limiting the scope of the invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may be made in accordance with design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. A method of identifying a stained banknote, comprising:
clustering sample paper currencies to obtain a plurality of paper currency groups, wherein each paper currency group comprises the sample paper currencies with the same characteristics;
adding a label to each paper money group to obtain labeled paper money data;
cutting the labeled paper money data to obtain cutting sample data, and training through the cutting sample data to obtain a stained paper money identification model;
and identifying the paper money to be detected through the stained paper money identification model to obtain a stained result of the paper money to be detected.
2. The method according to claim 1, wherein clustering the sample banknotes to obtain a plurality of banknote clusters comprises:
extracting specified features of each sample banknote, wherein the specified features comprise gray scale features or texture features;
and dividing the paper currency with the distance between the specified characteristics within a preset range into the same paper currency group.
3. The method according to claim 1, wherein said tagging each of said banknote bundles to obtain tagged banknote data comprises:
selecting a specified number of sample banknotes from each of the banknote groups;
identifying and determining matched label types for the selected sample paper currency in each paper currency group, wherein the label types comprise normal dirty paper currency, abnormal dirty paper currency and normal paper currency;
and adding the label type to each sample paper currency in the corresponding paper currency group to obtain the labeled paper currency data.
4. The method of claim 3, wherein the conventional insults include stroke, smear, and missing insults and the irregular insults include burn-out insults.
5. The method according to claim 1, wherein the cutting the labeled banknote data to obtain cutting sample data, and training the cutting sample data to obtain an stained banknote identification model comprises:
determining a sliding window, wherein the sliding window is smaller than the size of the sample banknote;
performing sliding cutting on the labeled paper money data according to the sliding window to obtain cutting sample data, wherein the cutting sample data is larger than the labeled paper money data;
inputting the cutting sample data into a deep learning network for training to obtain the stained paper currency recognition model, wherein the deep learning network comprises a dark net-53 network.
6. The method according to claim 1, wherein the identifying the banknote to be tested through the damaged banknote identification model to obtain the damage result of the banknote to be tested comprises the following steps:
inputting the paper money to be detected into the stained paper money identification model to obtain the label type of the paper money to be detected;
and taking the label type of the paper money to be detected as the contamination result.
7. The method according to any one of claims 1 to 6, wherein after the step of identifying the banknote to be tested through the damaged banknote identification model and obtaining the damage result of the banknote to be tested, the method further comprises the following steps:
determining the contamination level of the paper money to be tested according to the contamination level standard, wherein the contamination level standard comprises the corresponding relation between the label type and the contamination level;
and when the fouling grade is determined to reach the preset grade, giving an alarm.
8. An apparatus for identifying a stained paper money, comprising:
the system comprises a clustering module, a judging module and a judging module, wherein the clustering module is used for clustering original sample paper money to obtain a plurality of paper money groups, and each paper money group comprises the original sample paper money with the same characteristics;
the label adding module is used for adding labels to each paper currency group to obtain labeled paper currency data;
the identification model acquisition module is used for cutting the labeled paper money data to acquire cutting sample data and training the cutting sample data to acquire a stained paper money identification model;
and the paper currency contamination result acquisition module is used for identifying the paper currency to be detected through the contamination paper currency identification model and acquiring the contamination result of the paper currency to be detected.
9. An electronic device, characterized in that the electronic device comprises:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein,
the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the method of identifying a soiled banknote according to any of claims 1 to 7.
10. A computer readable storage medium storing computer instructions for causing a processor to perform the method of identifying a soiled banknote according to any of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210086424.9A CN114255540A (en) | 2022-01-25 | 2022-01-25 | Method, device, equipment and storage medium for identifying stained paper money |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210086424.9A CN114255540A (en) | 2022-01-25 | 2022-01-25 | Method, device, equipment and storage medium for identifying stained paper money |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114255540A true CN114255540A (en) | 2022-03-29 |
Family
ID=80796814
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210086424.9A Pending CN114255540A (en) | 2022-01-25 | 2022-01-25 | Method, device, equipment and storage medium for identifying stained paper money |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114255540A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117314897A (en) * | 2023-11-28 | 2023-12-29 | 恒银金融科技股份有限公司 | Method and device for discriminating distortion of banknote image |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102122353A (en) * | 2011-03-11 | 2011-07-13 | 西安电子科技大学 | Method for segmenting images by using increment dictionary learning and sparse representation |
| CN106898082A (en) * | 2017-03-15 | 2017-06-27 | 深圳怡化电脑股份有限公司 | A kind of image is stained the method and device of judgement |
| CN106898078A (en) * | 2017-02-21 | 2017-06-27 | 深圳怡化电脑股份有限公司 | A kind of recognition methods of Hongkong dollar version and device |
| CN107622562A (en) * | 2017-09-11 | 2018-01-23 | 深圳怡化电脑股份有限公司 | Extracting method, device, equipment and the storage medium of banknote image |
| CN110569899A (en) * | 2019-09-03 | 2019-12-13 | 嘉陵江亭子口水利水电开发有限公司 | Dam face defect classification model training method and device |
| CN111340748A (en) * | 2018-12-17 | 2020-06-26 | 汉能移动能源控股集团有限公司 | Battery defect identification method and device, computer equipment and storage medium |
| CN111435559A (en) * | 2019-01-10 | 2020-07-21 | 深圳怡化电脑股份有限公司 | Financial terminal, detection method of paper money watermark image and memory |
| CN112950837A (en) * | 2021-03-03 | 2021-06-11 | 中国工商银行股份有限公司 | Banknote damage condition identification method and device based on deep learning |
| CN113781483A (en) * | 2021-11-12 | 2021-12-10 | 常州微亿智造科技有限公司 | Industrial product appearance defect detection method and device |
-
2022
- 2022-01-25 CN CN202210086424.9A patent/CN114255540A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102122353A (en) * | 2011-03-11 | 2011-07-13 | 西安电子科技大学 | Method for segmenting images by using increment dictionary learning and sparse representation |
| CN106898078A (en) * | 2017-02-21 | 2017-06-27 | 深圳怡化电脑股份有限公司 | A kind of recognition methods of Hongkong dollar version and device |
| CN106898082A (en) * | 2017-03-15 | 2017-06-27 | 深圳怡化电脑股份有限公司 | A kind of image is stained the method and device of judgement |
| CN107622562A (en) * | 2017-09-11 | 2018-01-23 | 深圳怡化电脑股份有限公司 | Extracting method, device, equipment and the storage medium of banknote image |
| CN111340748A (en) * | 2018-12-17 | 2020-06-26 | 汉能移动能源控股集团有限公司 | Battery defect identification method and device, computer equipment and storage medium |
| CN111435559A (en) * | 2019-01-10 | 2020-07-21 | 深圳怡化电脑股份有限公司 | Financial terminal, detection method of paper money watermark image and memory |
| CN110569899A (en) * | 2019-09-03 | 2019-12-13 | 嘉陵江亭子口水利水电开发有限公司 | Dam face defect classification model training method and device |
| CN112950837A (en) * | 2021-03-03 | 2021-06-11 | 中国工商银行股份有限公司 | Banknote damage condition identification method and device based on deep learning |
| CN113781483A (en) * | 2021-11-12 | 2021-12-10 | 常州微亿智造科技有限公司 | Industrial product appearance defect detection method and device |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117314897A (en) * | 2023-11-28 | 2023-12-29 | 恒银金融科技股份有限公司 | Method and device for discriminating distortion of banknote image |
| CN117314897B (en) * | 2023-11-28 | 2024-03-19 | 恒银金融科技股份有限公司 | Method and device for discriminating distortion of banknote image |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110991657A (en) | Abnormal sample detection method based on machine learning | |
| CN111693534A (en) | Surface defect detection method, model training method, device, equipment and medium | |
| US9679354B2 (en) | Duplicate check image resolution | |
| CN112699824B (en) | Method and device for detecting constant of electric energy meter and storage medium | |
| CN108269349B (en) | Paper money processing method, device, equipment and storage medium | |
| WO2024040856A1 (en) | Defect detection method and apparatus, and electronic device and storage medium | |
| CN116952958A (en) | Defect detection method, device, electronic equipment and storage medium | |
| CN118279304B (en) | Abnormal recognition method, device and medium for special-shaped metal piece based on image processing | |
| CN115471476A (en) | Method, device, equipment and medium for detecting component defects | |
| CN115205291A (en) | Circuit board detection method, device, equipment and medium | |
| CN114255540A (en) | Method, device, equipment and storage medium for identifying stained paper money | |
| Cai et al. | An efficient method for electric meter readings automatic location and recognition | |
| CN115456996A (en) | Discrete defect detection method for nuclear fuel pellet and related assembly | |
| CN114120305B (en) | Training method of text classification model, and text content recognition method and device | |
| CN116110066A (en) | Information extraction method, device and equipment of bill text and storage medium | |
| Wu et al. | Multimeter digital recognition based on feature coding detection | |
| CN115542100B (en) | Insulator fault detection method, device, equipment and medium | |
| CN117197051A (en) | Defect grading method and device, electronic equipment and storage medium | |
| CN117611529A (en) | Mobile computer shell detection method, device, equipment and storage medium | |
| CN109376739B (en) | Marshalling mode determining method and device | |
| CN115761445A (en) | Method, device, equipment and medium for training chromosome analysis model | |
| CN115187585A (en) | Defect detection method and device, electronic equipment and storage medium | |
| CN116797579A (en) | Defect level determining method and device, electronic equipment and storage medium | |
| CN117009497A (en) | Message detection method, device, equipment and readable storage medium | |
| CN118052877A (en) | Positioning method, device, equipment and medium for strand breakage defect of power cable |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |