CN114445340A - Money bundle detection method, money bundle warehousing method and related device - Google Patents
Money bundle detection method, money bundle warehousing method and related device Download PDFInfo
- Publication number
- CN114445340A CN114445340A CN202111604033.3A CN202111604033A CN114445340A CN 114445340 A CN114445340 A CN 114445340A CN 202111604033 A CN202111604033 A CN 202111604033A CN 114445340 A CN114445340 A CN 114445340A
- Authority
- CN
- China
- Prior art keywords
- money
- money bundle
- bundle
- picture
- network model
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 86
- 238000000034 method Methods 0.000 title claims abstract description 49
- 230000007306 turnover Effects 0.000 claims abstract description 24
- 230000008569 process Effects 0.000 claims abstract description 10
- 238000012549 training Methods 0.000 claims description 73
- 238000004891 communication Methods 0.000 claims description 10
- 238000002372 labelling Methods 0.000 claims description 10
- 238000010586 diagram Methods 0.000 claims description 8
- 230000006870 function Effects 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000001052 transient effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07D—HANDLING OF COINS OR VALUABLE PAPERS, e.g. TESTING, SORTING BY DENOMINATIONS, COUNTING, DISPENSING, CHANGING OR DEPOSITING
- G07D11/00—Devices accepting coins; Devices accepting, dispensing, sorting or counting valuable papers
- G07D11/009—Depositing devices
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07D—HANDLING OF COINS OR VALUABLE PAPERS, e.g. TESTING, SORTING BY DENOMINATIONS, COUNTING, DISPENSING, CHANGING OR DEPOSITING
- G07D11/00—Devices accepting coins; Devices accepting, dispensing, sorting or counting valuable papers
- G07D11/50—Sorting or counting valuable papers
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Evolutionary Biology (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Quality & Reliability (AREA)
- Image Analysis (AREA)
Abstract
The application discloses a money bundle detection method, a storage method and a related device, wherein the method comprises the steps of obtaining money bundle pictures and inputting the money bundle pictures into a trained detection network model; detecting the money bundle placing position and the money type corresponding to the money bundle picture through the detection network model; and determining money storage data corresponding to the money bundle picture based on the detected money bundle placing position and money category. According to the method and the device, the money bundle pictures are identified through the trained detection network model, the money bundle placing positions and the money categories in the money bundle pictures can be automatically obtained, so that the grid turnover box can be automatically checked, the money bundle checking speed in the money bundle warehousing and ex-warehouse checking process can be increased, and the phenomenon of missing points or wrong points caused by manual checking of the panel can be realized on the other side.
Description
Technical Field
The application relates to the technical field of artificial intelligence, in particular to a money bundle detection method, a money bundle warehousing method and a related device.
Background
For the current vault scenario, most of the scenario is operated manually, although machines like sorters are also available to assist in the sorting of bundles within the vault. However, for the most critical procedure of checking the money bundles in and out of the warehouse, the money bundle information in the grid turnover box is usually determined by completely checking the grid turnover box manually, which is time-consuming and labor-consuming on one hand, and also may cause a checking error due to manual operation error on the other hand.
Thus, the prior art has yet to be improved and enhanced.
Disclosure of Invention
The present application provides a money bundle detecting method, a money bundle warehousing method, and a related device, aiming at the deficiencies of the prior art.
In order to solve the above technical problem, a first aspect of the embodiments of the present application provides a money bundle detecting method, where the method further includes:
acquiring a money bundle picture, and inputting the money bundle picture into a trained detection network model;
detecting the money bundle placing position and the money type corresponding to the money bundle picture through the detection network model;
and determining money storage data corresponding to the money bundle picture based on the detected money bundle placing position and money category.
The money bundle detection method, wherein the acquiring a money bundle picture and inputting the money bundle picture into a trained detection network model specifically includes:
acquiring a money bundle picture, and modifying the money bundle picture so that the height of a money bundle in the modified money bundle picture is vertical to the boundary of the money bundle picture;
and inputting the corrected money bundle picture into the trained detection network model.
The money bundle detection method comprises the following specific steps of:
acquiring a training sample set, wherein the training sample set comprises a plurality of training money bundle pictures;
and training a preset network model based on the training sample set to obtain the detection network model.
The money bundle detection method includes the following steps:
acquiring a training money bundle picture set, and selecting part of training money bundle pictures in the training money bundle picture set for marking to obtain target money bundle pictures with marking information;
training the preset network model based on the obtained target money bundle pictures to obtain a candidate network model;
and labeling the money categories of all the money bundle pictures except the target money bundle picture in the training money bundle picture set through the candidate network model to obtain a training sample set.
The money bundle detection method, wherein training a preset network model based on the training sample set to obtain the detection network model specifically includes:
and taking the candidate network model as a preset network model, and training the candidate network model based on the training sample set to obtain the detection network model.
The money bundle detection method, wherein the determining of the money storage data corresponding to the money bundle picture based on the detected money bundle placement position and money category specifically includes:
fitting the money bundle placing positions to generate a grid diagram;
and adding the coin types corresponding to the placing positions of the money bundles corresponding to the grids into the grids to obtain the coin storage data corresponding to the money bundle pictures.
A second aspect of the embodiments of the present application provides a method for warehousing, where the method includes:
acquiring a money bundle picture corresponding to a to-be-warehoused grid turnover box, and determining money storage data corresponding to the money bundle picture based on the money bundle detection method;
comparing the money storage data with target data corresponding to the money bundle picture;
and when the coin storage data is the same as the target data, storing the coin storage data in the target data and warehousing the grid turnover box.
The warehousing method, wherein the method further comprises:
and when the coin storage data are different from the target data, selecting a distinguishing grid with the coin storage data different from the target data, and prompting that the coins are placed wrongly on the distinguishing grid.
A third aspect of embodiments of the present application provides a computer readable storage medium storing one or more programs, which are executable by one or more processors to implement the steps in the money bundle detection method described above and/or to implement the steps in the warehousing method described above.
A fourth aspect of the embodiments of the present application provides a terminal device, including: a processor, a memory, and a communication bus; the memory has stored thereon a computer readable program executable by the processor;
the communication bus realizes the connection communication between the processor and the memory;
the processor, when executing the computer readable program, implements the steps in the money bundle detection method as described above, and/or implements the steps in the warehousing method as described above.
Has the advantages that: compared with the prior art, the money bundle detection method, the money bundle warehousing method and the related device are provided, and the method comprises the steps of obtaining money bundle pictures and inputting the money bundle pictures into a trained detection network model; detecting the money bundle placing position and the money type corresponding to the money bundle picture through the detection network model; and determining money storage data corresponding to the money bundle picture based on the detected money bundle placing position and money category. According to the method and the device, the money bundle pictures are identified through the trained detection network model, the money bundle placing positions and the money categories in the money bundle pictures can be automatically obtained, so that the grid turnover box can be automatically checked, the money bundle checking speed in the money bundle warehousing and ex-warehouse checking process can be increased, and the phenomenon of missing points or wrong points caused by manual checking of the panel can be realized on the other side.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without any inventive work.
Fig. 1 is a flow chart of a money bundle detection method provided by the present application.
Fig. 2 is a schematic diagram of the structure of the money bundle detecting device provided by the present application.
Fig. 3 is a schematic structural diagram of a terminal device provided in the present application.
Detailed Description
The present application provides a money bundle detecting method, a money bundle warehousing method and a related device, and in order to make the purpose, technical scheme and effect of the present application clearer and clearer, the present application is further described in detail below with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
As used herein, the singular forms "a", "an", "the" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms "comprises" and/or "comprising," when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof. It will be understood that when an element is referred to as being "connected" or "coupled" to another element, it can be directly connected or coupled to the other element or intervening elements may also be present. Further, "connected" or "coupled" as used herein may include wirelessly connected or wirelessly coupled. As used herein, the term "and/or" includes all or any element and all combinations of one or more of the associated listed items.
It will be understood by those within the art that, unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. It will be further understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the prior art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.
It should be understood that, the sequence numbers and sizes of the steps in this embodiment do not mean the execution sequence, and the execution sequence of each process is determined by its function and inherent logic, and should not constitute any limitation on the implementation process of this embodiment.
The inventor has found that most of the current cashbox scenes are operated manually, although machines such as a sorter help to sort the bundles in the cashbox. However, for the most critical procedure of checking the money bundles in and out of the warehouse, the money bundle information in the grid turnover box is usually determined by completely checking the grid turnover box manually, which is time-consuming and labor-consuming on one hand, and also may cause a checking error due to manual operation error on the other hand.
In order to solve the above problem, in the embodiment of the present application, a money bundle picture is obtained, and the money bundle picture is input into a trained detection network model; detecting the money bundle placing position and the money type corresponding to the money bundle picture through the detection network model; and determining money storage data corresponding to the money bundle picture based on the detected money bundle placing position and money category. According to the method and the device, the money bundle pictures are identified through the trained detection network model, the money bundle placing positions and the money categories in the money bundle pictures can be automatically obtained, so that the grid turnover box can be automatically checked, the money bundle checking speed in the money bundle warehousing and ex-warehouse checking process can be increased, and the phenomenon of missing points or wrong points caused by manual checking of the panel can be realized on the other side.
The following description of the embodiments is provided to further explain the present disclosure by way of example in connection with the appended drawings.
The present embodiment provides a money bundle detection method, as shown in fig. 1, the method including:
s10, acquiring the money bundle picture, and inputting the money bundle picture into the trained detection network model.
Specifically, the money bundle picture carries a plurality of money bundle regions, each of the money bundle regions corresponds to a money bundle, and the money types of the money bundles corresponding to the money bundle regions may be all the same, may be partially the same, and may be partially different, and may also be all different. For example, the money bundle picture includes a money bundle region a and a money bundle region B, the money type of the money bundle corresponding to the money bundle region a is 10 yuan, and the money type of the money bundle corresponding to the money bundle region B is 20 yuan. In one implementation, the money bundle picture may be obtained by shooting the grid circulation box by a shooting device, that is, when the grid circulation box needs to be checked, the grid circulation box may be shot by the shooting device to obtain the money bundle picture, and then the money storage data of the money bundle carried by the grid circulation box is determined based on the money bundle detection method provided in this embodiment.
In an implementation manner of this embodiment, since the problem of slant of the picture content may occur during the process of capturing the wallet picture, the wallet picture may be preprocessed to correct the picture content in the wallet picture before being input into the trained detection network model, so that the difficulty in recognizing the wallet picture may be reduced, and the recognition speed and accuracy of the detection network may be improved. Based on this, the acquiring the wallet image and inputting the wallet image into the trained detection network model specifically includes:
acquiring a money bundle picture, and modifying the money bundle picture so that the height of a money bundle in the modified money bundle picture is vertical to the boundary of the money bundle picture;
and inputting the corrected money bundle picture into the trained detection network model.
In particular, the angles and positions of the picture contents in the wallet picture can be modified when the wallet picture is modified, so that the height of the wallet in the modified wallet picture is perpendicular to the boundary of the wallet picture. In one implementation, the bundle of pictures may be modified by a horizontal rectification algorithm (e.g., hough transform, etc.) to modify the angle and position of the picture content in the bundle of pictures at a preset fixed angle and fixed position, wherein the height of the bundle of pictures in the bundle of pictures is perpendicular to the boundary of the bundle of pictures when the picture content in the bundle of pictures is at the fixed angle and fixed position. In addition, in order to provide the detection speed of the money bundle pictures, after the money bundle pictures are acquired, the money bundle pictures can be compressed to reduce the number of the money bundle pictures, so that the operation speed of the detection network model can be improved. Of course, in practical application, the money bundle pictures are obtained by shooting the whole grid turnover box, or by shooting part of the grid turnover box according to practical conditions, that is, the grid turnover box can be divided into a plurality of box areas according to practical conditions, then each box area is shot respectively to obtain money bundle pictures corresponding to each box area, and money storage data corresponding to the whole grid turnover box detected by the money bundle pictures respectively is stored, so that the problem that the detection accuracy is influenced due to the fact that the whole pictures are not clear due to the fact that the grid turnover box is too large can be solved by the division mode for the region detection.
The detection network model is a trained deep learning network model, for example, the detection network model adopts an SSD network model. In one implementation, the training process of obtaining the detection network model based on the training of the preset training sample set by the detection network model specifically includes:
acquiring a training sample set;
and training a preset network model based on the training sample set to obtain the detection network model.
Specifically, the training sample set includes a plurality of training wallet pictures, each of the plurality of training wallet pictures carries a wallet region, and each wallet region corresponds to one wallet. The training wallet pictures respectively carry a wallet region to form a wallet region set, the wallet region set can be divided into a plurality of wallet region types according to types of coins, each wallet region type in the wallet region types corresponds to one type of coin, and the wallet types corresponding to the wallet region types are different. In one implementation, the money bundle region classes at least comprise 100 yuan, 50 yuan, 20 yuan, 10 yuan, 5 yuan and 1 yuan of circulation tickets circulating on the market and 100 yuan, 50 yuan, 20 yuan, 10 yuan, 5 yuan and 1 yuan of original seal tickets allocated by people. In addition, in practical application, in order to improve the training speed of the detection network model, each training money bundle picture in the training sample set carries a money bundle region, that is, each training money bundle picture carries a money bundle, so that the recognition difficulty of the training money bundle pictures can be reduced, the learning speed of the preset network model can be improved, and the training speed of the detection network model can be further improved.
In an implementation manner of this embodiment, the acquiring a training sample set specifically includes:
acquiring a training money bundle picture set, and selecting part of training money bundle pictures in the training money bundle picture set for marking to obtain target money bundle pictures with marking information;
training the preset network model based on the obtained target money bundle pictures to obtain a candidate network model;
and labeling the money categories of all the money bundle pictures except the target money bundle picture in the training money bundle picture set through the candidate network model to obtain a training sample set.
Specifically, the labeling information of the target money bundle picture can be formed by manual labeling, wherein the labeling information can include money types corresponding to the money bundle region and position information of the money bundle region in the money bundle picture, so that the preset network model can learn money type characteristics and money bundle region characteristics carried by the target money bundle picture, and further can predict the money bundle placing position and money category. In addition, a money bundle region set formed by the target money bundle pictures carrying the money bundle regions is also divided into a plurality of candidate money bundle region types according to the money types, the candidate money bundle region types are in one-to-one correspondence with the money bundle region types, and the money types corresponding to the candidate money bundle region types are the same as the money types corresponding to the money bundle region types. For example, the plurality of money bundle region classes include circulation tickets 100, 50, 20, 10, 5, 1 and original seal tickets 100, 50, 20, 10, 5, 1 that are circulated in the market, and the plurality of candidate money bundle region classes include circulation tickets 100, 50, 20, 10, 5, 1 and original seal tickets 100, 50, 20, 10, 5, 1 that are circulated in the market, and original seal tickets 100, 50, 20, 10, 5, 1 that are circulated in the market.
After the target money bundle picture with the label is obtained, the preset network model is pre-trained on the basis of the target money bundle picture with the label to obtain a candidate network model, wherein the candidate network model can learn picture characteristics in the money bundle picture to predict the money bundle placing position and the money type in the money bundle picture. And then, predicting the predicted placing position and the coin type of each training money bundle picture except the target money bundle picture in the training picture set by adopting the candidate network model, and taking the predicted placing position and the coin type as the marking information of the training money bundle picture to obtain a training sample set. According to the embodiment, the automatic labeling of all the rest original picture data is performed through the candidate network model, so that the manual labeling time is greatly reduced.
In this embodiment, when the training sample set is determined, the candidate network model for pre-training is determined, and the labeling information of part of the training wallet pictures in the training sample set is determined through the candidate network model, that is, the labeling information of part of the training wallet pictures in the training sample set may have a problem of low accuracy. Therefore, in order to ensure the model accuracy of the detection network model, when the detection network model is trained based on the training sample set, the candidate network model can be used as a preset network model, so that the feature recognition capability of the money bundle picture learned in the pre-training of the candidate network model can be utilized, and the model accuracy of the detection network model can be ensured.
Based on the above, the candidate network model is used as a preset network model, and the candidate network model is trained based on the training sample set to obtain the detection network model.
Specifically, the model parameters of the candidate network model are model parameters trained based on the target money bundle picture, and the candidate network model can learn picture characteristics of the trained money bundle picture, so that the candidate network model is used as a preset network model, and the training precision of the trained detection network model can be improved. When the candidate network model is trained based on the training sample set, the training money bundle picture is input into the candidate network model, the predicted money bundle placing position and the predicted money category corresponding to the training money bundle picture are determined through the candidate network model, then the loss item is determined based on the marking information carried by the training money bundle picture, and then the candidate network model is trained based on the loss item to obtain the detection network model.
S20, detecting the placement position and the coin type of the money bundle corresponding to the money bundle picture through the detection network model.
Specifically, the money bundle picture may carry one money bundle region, or may carry a plurality of money bundle regions, and when carrying one money bundle region, the money bundle placing position and the money type may be the placing position of the money bundle region and the money type of the money bundle in the money bundle region; when the portable money bundle is carried with a plurality of money bundle areas, the money bundle placing positions and the money categories are also multiple, the money bundle placing positions and the money categories are in one-to-one correspondence with the money bundle areas, and the money bundle placing positions and the money categories are the positions of the corresponding money bundle areas in the money bundle picture and the money categories of the money bundles in the money bundle areas.
And S30, determining money storage data corresponding to the money bundle picture based on the detected money bundle placing position and money type.
Specifically, the money storage data is used for reflecting money storage information in the money bundle storage device corresponding to the money bundle picture, wherein the money storage information includes a money bundle storage position and a money category corresponding to the money bundle. In one implementation, the money storage data stores information for the bundles in the grid tote, as the bundles are generally stored by the grid tote, that is, the money storage data includes the money category of each bundle stored by each grid in the grid tote and the storage location of each bundle in the grid tote.
In one implementation manner, the determining, based on the detected money bundle placement position and the detected money category, money storage data corresponding to the money bundle picture specifically includes:
fitting the money bundle placing positions to generate a grid diagram;
and adding the coin types corresponding to the placing positions of the money bundles corresponding to the grids into the grids to obtain the coin storage data corresponding to the money bundle pictures.
Specifically, after the money bundle placing positions of the money bundles are obtained, straight line fitting can be performed on the money bundle placing positions to obtain a plurality of crosswise fitted straight lines, the crosswise fitted straight lines can be a pixel grid diagram, each grid in the grid diagram corresponds to one money bundle placing position, and namely each grid diagram corresponds to one money bundle area. In one embodiment, before detecting the wallet picture, the wallet picture is modified so that the height of the wallet in the wallet picture is perpendicular to the boundary of the wallet picture. Therefore, the edge of each money bundle area is on the X axis and the Y axis, so that when the money bundles are placed and fitted to generate a grid image, straight line fitting can be adopted to obtain a plurality of fitted straight lines which are crossed along the X axis direction and the Y axis direction, and the grid image of the grid in the simulated grid turnover box is obtained. And after the obtained grid image is obtained, adding the money categories corresponding to the money bundle placing positions corresponding to the grids into the grids so as to obtain money storage data corresponding to the money bundle image.
In summary, the present embodiment provides a money bundle detection method, which includes obtaining a money bundle picture, and inputting the money bundle picture into a trained detection network model; detecting the money bundle placing position and the money type corresponding to the money bundle picture through the detection network model; and determining money storage data corresponding to the money bundle picture based on the detected money bundle placing position and money category. According to the method and the device, the money bundle pictures are identified through the trained detection network model, the money bundle placing positions and the money categories in the money bundle pictures can be automatically obtained, so that the grid turnover box can be automatically checked, the money bundle checking speed in the money bundle warehousing and ex-warehouse checking process can be increased, and the phenomenon of missing points or wrong points caused by manual checking of the panel can be realized on the other side.
Based on the money bundle detection method, the embodiment provides a warehousing method, and the method includes:
acquiring a money bundle picture corresponding to a to-be-warehoused grid turnover box, and determining money storage data corresponding to the money bundle picture based on the money bundle detection method;
comparing the money storage data with target data corresponding to the money bundle picture;
and when the coin storage data is the same as the target data, storing the coin storage data in the target data and warehousing the grid turnover box.
In one implementation, the method further comprises:
and when the coin storage data is different from the target data, selecting a distinguishing grid with the coin storage data different from the target data, and prompting that the coin of the distinguishing grid is placed wrongly.
Specifically, the money bundle picture is obtained by collecting images of the to-be-put grid turnover box. The target data is pre-stored money bundle information used for recording money bundles stored in the grid turnover box, and the acquired money storage data can be used for comparing the money storage data with the target data so as to compare the money bundles stored in the grid turnover box with the money bundles recorded by the target data, so that the money bundles can be checked, and the problems of random placement of the money bundles, missing of the money bundles and replacement of the money bundles can be detected in the grid turnover box, and automatic warehousing and checking are realized.
Based on the money bundle detection method, the present embodiment provides a money bundle detection device, as shown in fig. 2, the device includes:
an obtaining module 100, configured to obtain a wallet image, and input the wallet image into a trained detection network model;
the detection module 200 is configured to detect a money bundle placing position and a money type corresponding to the money bundle picture through the detection network model;
a determining module 300, configured to determine money storage data corresponding to the money bundle picture based on the detected money bundle placement position and money category.
Based on the above-described money bundle detection method, the present embodiment provides a computer-readable storage medium storing one or more programs, which are executable by one or more processors to implement the steps in the money bundle detection method according to the above-described embodiment.
Based on the money bundle detection method, the present application further provides a terminal device, as shown in fig. 3, including at least one processor (processor) 20; a display screen 21; and a memory (memory)22, and may further include a communication Interface (Communications Interface)23 and a bus 24. The processor 20, the display 21, the memory 22 and the communication interface 23 can communicate with each other through the bus 24. The display screen 21 is configured to display a user guidance interface preset in the initial setting mode. The communication interface 23 may transmit information. The processor 20 may call logic instructions in the memory 22 to perform the methods in the embodiments described above.
Furthermore, the logic instructions in the memory 22 may be implemented in software functional units and stored in a computer readable storage medium when sold or used as a stand-alone product.
The memory 22, which is a computer-readable storage medium, may be configured to store a software program, a computer-executable program, such as program instructions or modules corresponding to the methods in the embodiments of the present disclosure. The processor 20 executes the functional application and data processing, i.e. implements the method in the above-described embodiments, by executing the software program, instructions or modules stored in the memory 22.
The memory 22 may include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store data created according to the use of the terminal device, and the like. Further, the memory 22 may include a high speed random access memory and may also include a non-volatile memory. For example, a variety of media that can store program codes, such as a usb disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk, may also be transient storage media.
In addition, the specific processes loaded and executed by the storage medium and the instruction processors in the terminal device are described in detail in the method, and are not stated herein.
Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present application, and not to limit the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions in the embodiments of the present application.
Claims (10)
1. A money bundle detection method, the method further comprising:
acquiring a money bundle picture, and inputting the money bundle picture into a trained detection network model;
detecting the money bundle placing position and the money type corresponding to the money bundle picture through the detection network model;
and determining money storage data corresponding to the money bundle picture based on the detected money bundle placing position and money category.
2. The money bundle detection method according to claim 1, wherein the obtaining of the money bundle picture and the inputting of the money bundle picture into the trained detection network model specifically comprises:
acquiring a money bundle picture, and modifying the money bundle picture so that the height of a money bundle in the modified money bundle picture is vertical to the boundary of the money bundle picture;
and inputting the corrected money bundle picture into the trained detection network model.
3. The money bundle detection method according to claim 1, wherein the training process of the detection network model specifically comprises:
acquiring a training sample set, wherein the training sample set comprises a plurality of training money bundle pictures;
and training a preset network model based on the training sample set to obtain the detection network model.
4. The money bundle detection method according to claim 3, wherein the obtaining of the training sample set specifically comprises:
acquiring a training money bundle picture set, and selecting part of training money bundle pictures in the training money bundle picture set for marking to obtain target money bundle pictures with marking information;
training the preset network model based on the obtained target money bundle pictures to obtain a candidate network model;
and labeling the money categories of all the money bundle pictures except the target money bundle picture in the training money bundle picture set through the candidate network model to obtain a training sample set.
5. The money bundle detection method according to claim 4, wherein the training a preset network model based on the training sample set to obtain the detection network model specifically comprises:
and taking the candidate network model as a preset network model, and training the candidate network model based on the training sample set to obtain the detection network model.
6. The money bundle detection method according to claim 1, wherein the determining of the money storage data corresponding to the money bundle picture based on the detected money bundle placement position and money category specifically comprises:
fitting the money bundle placing positions to generate a grid diagram;
and adding the coin types corresponding to the placing positions of the money bundles corresponding to the grids into the grids to obtain the coin storage data corresponding to the money bundle pictures.
7. A method for warehousing, the method comprising:
acquiring a money bundle picture corresponding to a to-be-warehoused grid turnover box, and determining money storage data corresponding to the money bundle picture based on the money bundle detection method according to any one of claims 1-6;
comparing the money storage data with target data corresponding to the money bundle picture;
and when the coin storage data is the same as the target data, storing the coin storage data in the target data and warehousing the grid turnover box.
8. The warehousing method of claim 7, further comprising:
and when the coin storage data is different from the target data, selecting a distinguishing grid with the coin storage data different from the target data, and prompting that the coin of the distinguishing grid is placed wrongly.
9. A computer readable storage medium, storing one or more programs, which are executable by one or more processors to perform the steps of the money bundle detection method according to any one of claims 1-6, and/or to perform the steps of the warehousing method according to any one of claims 7-8.
10. A terminal device, comprising: a processor, a memory, and a communication bus; the memory has stored thereon a computer readable program executable by the processor;
the communication bus realizes connection communication between the processor and the memory;
the processor, when executing the computer readable program, implements the steps in the money bundle detection method according to any one of claims 1-6, and/or implements the steps in the warehousing method according to any one of claims 7-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111604033.3A CN114445340A (en) | 2021-12-24 | 2021-12-24 | Money bundle detection method, money bundle warehousing method and related device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111604033.3A CN114445340A (en) | 2021-12-24 | 2021-12-24 | Money bundle detection method, money bundle warehousing method and related device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114445340A true CN114445340A (en) | 2022-05-06 |
Family
ID=81363760
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111604033.3A Pending CN114445340A (en) | 2021-12-24 | 2021-12-24 | Money bundle detection method, money bundle warehousing method and related device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114445340A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109325538A (en) * | 2018-09-29 | 2019-02-12 | 北京京东尚科信息技术有限公司 | Object detection method, device and computer readable storage medium |
| CN109697460A (en) * | 2018-12-05 | 2019-04-30 | 华中科技大学 | Object detection model training method, target object detection method |
| CN111339957A (en) * | 2020-02-28 | 2020-06-26 | 广州中智融通金融科技有限公司 | Image recognition-based cashbox bundle state detection method, system and medium |
| CN111369188A (en) * | 2020-02-27 | 2020-07-03 | 广州中智融通金融科技有限公司 | Machine vision-based bundled note warehousing method, system and medium |
| CN112329845A (en) * | 2020-11-03 | 2021-02-05 | 深圳云天励飞技术股份有限公司 | Method and device for replacing paper money, terminal equipment and computer readable storage medium |
-
2021
- 2021-12-24 CN CN202111604033.3A patent/CN114445340A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109325538A (en) * | 2018-09-29 | 2019-02-12 | 北京京东尚科信息技术有限公司 | Object detection method, device and computer readable storage medium |
| CN109697460A (en) * | 2018-12-05 | 2019-04-30 | 华中科技大学 | Object detection model training method, target object detection method |
| CN111369188A (en) * | 2020-02-27 | 2020-07-03 | 广州中智融通金融科技有限公司 | Machine vision-based bundled note warehousing method, system and medium |
| CN111339957A (en) * | 2020-02-28 | 2020-06-26 | 广州中智融通金融科技有限公司 | Image recognition-based cashbox bundle state detection method, system and medium |
| CN112329845A (en) * | 2020-11-03 | 2021-02-05 | 深圳云天励飞技术股份有限公司 | Method and device for replacing paper money, terminal equipment and computer readable storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110060237B (en) | Fault detection method, device, equipment and system | |
| TWI703510B (en) | Vehicle damage identification method, device and computing equipment | |
| CN110032998B (en) | Method, system, device and storage medium for detecting characters of natural scene picture | |
| CN109409398B (en) | Image processing apparatus, image processing method, and storage medium | |
| CN108399386A (en) | Information extracting method in pie chart and device | |
| CN110619333B (en) | Text line segmentation method, text line segmentation device and electronic equipment | |
| CN111310826B (en) | Method and device for detecting labeling abnormality of sample set and electronic equipment | |
| CN114842019B (en) | Battery plate surface defect detection method, system, storage medium and equipment | |
| CN101908136A (en) | Table identifying and processing method and system | |
| CN105701446A (en) | Preforming object detection | |
| CN108734161B (en) | Method, device and equipment for identifying prefix number area and storage medium | |
| CN106650670A (en) | Method and device for detection of living body face video | |
| CN110781882A (en) | License plate positioning and identifying method based on YOLO model | |
| WO2021232670A1 (en) | Pcb component identification method and device | |
| CN112446262A (en) | Text analysis method, text analysis device, text analysis terminal and computer-readable storage medium | |
| CN108268641A (en) | Invoice information recognition methods and invoice information identification device, equipment and storage medium | |
| CN112001219A (en) | Multi-angle multi-face recognition attendance checking method and system | |
| CN112036304A (en) | Medical bill layout identification method and device and computer equipment | |
| CN112613367A (en) | Bill information text box acquisition method, system, equipment and storage medium | |
| CN114445340A (en) | Money bundle detection method, money bundle warehousing method and related device | |
| CN111126286A (en) | Vehicle dynamic detection method and device, computer equipment and storage medium | |
| CN111402185A (en) | Image detection method and device | |
| CN114120057A (en) | Confusion matrix generation method based on Paddledetection | |
| CN111225297A (en) | Broadband passive optical network port resource remediation method and system | |
| CN109934113A (en) | A kind of classroom number counting method and its system, device, storage medium |
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 |