CN112950837B - Banknote breakage condition identification method and device based on deep learning - Google Patents
Banknote breakage condition identification method and device based on deep learning Download PDFInfo
- Publication number
- CN112950837B CN112950837B CN202110232998.8A CN202110232998A CN112950837B CN 112950837 B CN112950837 B CN 112950837B CN 202110232998 A CN202110232998 A CN 202110232998A CN 112950837 B CN112950837 B CN 112950837B
- Authority
- CN
- China
- Prior art keywords
- defect
- data
- banknote
- image
- paper money
- 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.)
- Active
Links
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
- G07D7/187—Detecting defacement or contamination, e.g. dirt
-
- 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
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- 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
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/048—Activation functions
-
- 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
- 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
- G07D7/20—Testing patterns thereon
- G07D7/202—Testing patterns thereon using pattern matching
- G07D7/206—Matching template patterns
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Abstract
The invention provides a banknote breakage condition identification method and device based on deep learning, which belong to the field of artificial intelligence and can be used in the financial field and other fields, and the method comprises the following steps: acquiring image information of paper money, and respectively intercepting a defect image block and a standard image block in the image information to generate defect data and defect-free data; filtering and/or amplifying the defect data and the defect-free data to generate a training image, calibrating the damaged position of paper money in the defect data to generate defect type data, and generating training set data according to the training image and the defect type data; training a preset YOLOv3 network through the training set data to obtain a paper money detection model, and inputting paper money images to be detected into the paper money detection model to obtain characteristic parameters; and calculating according to the characteristic parameters to obtain a paper currency defect ratio, and comparing the paper currency defect ratio with a preset threshold value to obtain the paper currency breakage condition.
Description
Technical Field
The invention relates to the field of artificial intelligence, which is applicable to the financial field and other fields, in particular to a banknote breakage condition identification method and device based on deep learning.
Background
During the printing or transferring process of the paper currency, the defects of spots, pits, scratches, chromatic aberration, defects and the like are inevitably generated, and the paper currency with similar defects should be found and recovered in time. How to solve the problems of high detection difficulty and the like caused by small paper currency damage defects, which are important points and difficulties of defect detection. The traditional defect detection generally selects a corresponding light source first, and a proper illumination method is selected through a lighting test, so that a good image can be obtained. Then designing an extraction algorithm according to the defect characteristics of the actual imaging picture, wherein the characteristics commonly used by the extraction algorithm comprise: haar, SIFT, HOG, etc.; and the defect classification algorithm is commonly used in a neural network (MLP), a Support Vector Machine (SVM), adaboost and the like. The similar method has the defects of single detectable defect type, weak generalization capability and poor recognition effect on the damage condition of a small area.
Disclosure of Invention
The invention aims to provide a banknote damage condition identification method and device based on deep learning, which are used for solving the problems of single detectable defect type and weak generalization capability in the prior art, monitoring the banknote damage state in real time and effectively monitoring the banknote damage defect in a small area.
In order to achieve the above object, the banknote breakage condition identification method based on deep learning provided by the invention specifically comprises the following steps: acquiring image information of paper money, and respectively intercepting a defect image block and a standard image block in the image information to generate defect data and defect-free data; filtering and/or amplifying the defect data and the defect-free data to generate a training image, calibrating the damaged position of paper money in the defect data to generate defect type data, and generating training set data according to the training image and the defect type data; training a preset YOLOv3 network through the training set data to obtain a paper money detection model, and inputting paper money images to be detected into the paper money detection model to obtain characteristic parameters; and calculating according to the characteristic parameters to obtain a paper currency defect ratio, and comparing the paper currency defect ratio with a preset threshold value to obtain the paper currency breakage condition.
In the banknote breakage recognition method based on deep learning, it is preferable that the acquiring of the image information of the banknote includes: and acquiring a banknote image through a CDD visual detection device, and converting the banknote image into a gray image to obtain image information.
In the banknote breakage recognition method based on deep learning, it is preferable that the filtering and/or amplifying the defect data and the defect-free data to generate the training image includes: replacing the particle noise points of the defect data and the defect-free data by using a low-pass or high-pass filter through the weighted average value of each pixel in the pixel point field of the particle noise points in the defect data and the defect-free data; and performing amplification on the defect data and the defect-free data according to one or more of preset angle rotation, brightness and contrast adjustment and Gaussian white noise addition.
In the banknote breakage recognition method based on deep learning, the defect type data preferably includes a picture path, a breakage type, and coordinate position information.
In the banknote breakage condition recognition method based on deep learning, preferably, the preset YOLOv3 network includes: the dark-53 in the YOLOv3 network architecture is replaced by a dense connectivity network DenseNet.
In the banknote breakage condition identification method based on deep learning, preferably, calculating the banknote breakage ratio according to the feature parameter includes: acquiring position parameters of the characteristic parameters, and calculating to acquire length and width data of paper money according to the position parameters; and carrying out calculation according to the confidence coefficient in the length and width data and the characteristic parameters and the defect classification probability into a preset sigmoid function to obtain the banknote defect ratio.
The invention also provides a banknote breakage recognition device based on deep learning, which comprises: the device comprises an image acquisition module, a preprocessing module, a training module and an identification module; the image acquisition module is used for acquiring image information of paper money, and respectively intercepting a defect image block and a standard image block in the image information to generate defect data and defect-free data; the preprocessing module is used for carrying out filtering and/or amplifying treatment on the defect data and the defect-free data to generate a training image, calibrating the damaged position of paper money in the defect data to generate defect type data, and generating training set data according to the training image and the defect type data; the training module is used for training a preset YOLOv3 network through the training set data to obtain a paper money detection model, and inputting paper money images to be detected into the paper money detection model to obtain characteristic parameters; the recognition module is used for calculating and obtaining a paper currency defect ratio according to the characteristic parameters, and comparing the paper currency defect ratio with a preset threshold value to obtain the paper currency damage condition.
In the banknote breakage recognition device based on deep learning, preferably, the image acquisition module includes: and acquiring a banknote image through a CDD visual detection device, and converting the banknote image into a gray image to obtain image information.
In the banknote breakage recognition device based on deep learning, preferably, the preprocessing module includes a filtering unit and an amplifying unit; the filtering unit is used for replacing the particle noise points of the defect data and the defect-free data by using a low-pass or high-pass filter through the weighted average value of each pixel in the pixel point field of the particle noise points in the defect data and the defect-free data; the amplification unit is used for amplifying one or more of rotating the defect data and the defect-free data according to a preset angle, adjusting brightness and contrast and adding Gaussian white noise.
In the banknote breakage condition recognition device based on deep learning, preferably, the recognition module includes a calculation unit, wherein the calculation unit is used for obtaining a position parameter of the characteristic parameter, and calculating and obtaining length and width data of the banknote according to the position parameter; and carrying out calculation according to the confidence coefficient in the length and width data and the characteristic parameters and the defect classification probability into a preset sigmoid function to obtain the banknote defect ratio.
The invention also provides a computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the above method when executing the computer program.
The present invention also provides a computer readable storage medium storing a computer program for executing the above method.
The beneficial technical effects of the invention are as follows: aiming at the condition of small-size breakage of paper money, the original three original prediction scales of Yolov3 cannot meet the requirements, so that the 4 th prediction scale is increased. The signature of [52,52,255] is up-sampled and connected with a signature of [104,104,255] size in the convolution process, which is 4 times the down-sampled size of the input image, and the receptive field is suitable for detecting the small-size damaged position in the paper currency defect. The dense connection network DenseNet is used for replacing the original network structure Darknet-53, each layer of the DenseNet can accept all the previous layers as additional input, the characteristic reuse among multiple layers can be realized better, the gradient vanishing problem in the original structure is relieved, and the network computing efficiency is improved.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this application, illustrate and together with the description serve to explain the invention. In the drawings:
FIG. 1 is a schematic flow chart of a banknote breakage recognition method based on deep learning according to an embodiment of the invention;
FIG. 2 is a flow chart illustrating image preprocessing according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of a Yolov3 feature extraction network according to an embodiment of the present invention;
FIG. 4 is a schematic diagram of a DenseNet according to an embodiment of the present invention;
FIG. 5 is a schematic diagram of a flow chart of calculating a banknote defect ratio according to an embodiment of the present invention;
FIG. 6 is a schematic diagram of a banknote breakage recognition device based on deep learning according to an embodiment of the present invention;
fig. 7 is a schematic structural diagram of an electronic device according to an embodiment of the invention.
Detailed Description
The following will describe embodiments of the present invention in detail with reference to the drawings and examples, thereby solving the technical problems by applying technical means to the present invention, and realizing the technical effects can be fully understood and implemented accordingly. It should be noted that, as long as no conflict is formed, each embodiment of the present invention and each feature of each embodiment may be combined with each other, and the formed technical solutions are all within the protection scope of the present invention.
Additionally, the steps illustrated in the flowcharts of the figures may be performed in a computer system such as a set of computer executable instructions, and although a logical order is illustrated in the flowcharts, in some cases the steps illustrated or described may be performed in an order other than that herein.
Referring to fig. 1, the banknote breakage condition recognition method based on deep learning provided by the present invention specifically includes:
s101, acquiring image information of paper money, and respectively intercepting a defect image block and a standard image block in the image information to generate defect data and defect-free data;
s102, filtering and/or amplifying the defect data and the defect-free data to generate a training image, calibrating the damaged position of paper money in the defect data to generate defect type data, and generating training set data according to the training image and the defect type data;
s103, training a preset YOLOv3 network through the training set data to obtain a paper money detection model, and inputting paper money images to be detected into the paper money detection model to obtain characteristic parameters;
s104, calculating and obtaining a paper currency defect ratio according to the characteristic parameters, and comparing the paper currency defect ratio with a preset threshold value to obtain the paper currency breakage condition.
The defect type data comprises a picture path, a damage type and coordinate position information.
In the above embodiment, acquiring image information of the banknote includes: and acquiring a banknote image through a CDD visual detection device, and converting the banknote image into a gray image to obtain image information. Specifically, in actual work, the CCD visual detection device can be used for collecting paper money images and converting the paper money images into gray level images, defect image blocks are respectively cut off on the paper money gray level images to serve as defect data, and normal images are cut off to serve as defect-free data. The captured image requires a size of resize to 416x 416.
Referring to fig. 2, in an embodiment of the present invention, filtering and/or amplifying the defect data and the defect-free data to generate a training image includes:
s201, replacing the particle noise points of the defect data and the defect-free data by using a low-pass or high-pass filter through the weighted average value of each pixel in the pixel point field of the particle noise points in the defect data and the defect-free data;
s202, performing amplification on the defect data and the defect-free data according to one or more of preset angle rotation, brightness and contrast adjustment and Gaussian white noise addition.
Specifically, in actual work, a low-pass or high-pass filter is used to replace the original pixel value with the weighted average value of each pixel in a certain pixel point field aiming at the characteristic that the banknote image field acquisition is easily affected by internal noise such as particle noise on an image acquisition instrument and an optical negative film.
Expanding the image set by rotating the original image by 90 DEG, 180 DEG and 270 DEG and adjusting the contrast and brightness; the number of image samples is further expanded by adding white gaussian noise. The number of the expanded defect data and the number of defect-free data samples are about 2500, the image quantity ratio of the training set to the test set is 8:2, and the defect types are spots, scratches and defects.
In an embodiment of the present invention, in step S102, the calibration of the position of the banknote damage in the defect data to generate the defect type data may use labelImg software to calibrate the position of the banknote damage in the training picture, generate an XML file corresponding to the pascal format, where the generated XML file includes a picture path, a type to which the damage belongs, and coordinate position information. The training set consists of two parts of an image and an XML file corresponding to the image.
In an embodiment of the present invention, the preset YOLOv3 network includes: the dark-53 in the YOLOv3 network architecture is replaced by a dense connectivity network DenseNet. Specifically, in actual work, the YOLOv3 network firstly divides an input picture into a plurality of cells, and if the center of a target to be detected falls in a certain cell, the cell is responsible for predicting the target and outputting various attributes (including the position of a center point, the width and the height, the confidence and the category information) of the target. The YOLOv3 feature extraction network is shown in fig. 3. In order to improve the feature extraction capability, the dense connection network DenseNet is used to replace the original network structure Darknet-53, and the structure of the DenseNet is shown in FIG. 4.
The output of the DenseNet network at layer l is expressed as:
x l ＝H l ([x 0 ,x 1 ,...,x l-1 ])；
wherein x is l Represents the output of the layer I neural network, H l Representing a nonlinear function. Therefore, each layer of DenseNet can accept all the previous layers as additional input, so that the feature reuse among multiple layers can be realized better, the problem of gradient disappearance in the original structure is relieved, and the network computing efficiency is improved.
After the input picture with the size of 416X416 enters a DenseNet network, 3 original branches are obtained, and after a series of convolution, upsampling, merging and other operations, the branches finally obtain three characteristic diagrams with different sizes, namely y1, y2 and y3, which respectively correspond to 32 times downsampling, 16 times downsampling and 8 times downsampling. The shapes are [13,13,255], [26,26,255] and [52,52,255] respectively corresponding to the detection targets with large size, medium size and small size. However, for some small-size breakage conditions of paper money, the original three original prediction scales of Yolov3 cannot meet the requirements, so that the 4 th prediction scale is increased. The signature of [52,52,255] is up-sampled and connected with a signature of [104,104,255] size in the convolution process, which is 4 times the down-sampled size of the input image, and the receptive field is suitable for detecting the small-size damaged position in the paper currency defect.
Referring to fig. 5, in an embodiment of the present invention, calculating the banknote defect ratio according to the feature parameters includes:
s501, acquiring position parameters of the characteristic parameters, and calculating to acquire length and width data of paper money according to the position parameters;
s502, carrying out calculation according to the length and width data and the confidence coefficient and defect classification probability in the characteristic parameters and a preset sigmoid function to obtain the banknote defect ratio.
Specifically, in actual operation, the output bounding box of a neural network is typically represented by a set of 6-element vectors. 4 location parameters center_x, center_y, w, h, and 1 confidence (1 or 0) and 1 defect classification probability P (i) ([ 1,0 … ], [0,1,0 … ]), respectively. Wherein center_x and center_y are the abscissa and ordinate of the center position of the output bounding box; and w and h are length and width information of the output boundary box. The confidence level represents whether the current bounding box has an object. If the confidence of the box is smaller than the given threshold, the box is considered to contain no object, a sigmoid function is mainly used, the function can restrict the result output by the feature layer to be in the interval of [0,1], and the decimal number obtained by the result continuing to pass through the sigmoid function is represented as belonging to the class if the result is larger than the set threshold, otherwise, the boundary box is deleted and the subsequent processing is not considered. Non-maximal suppression (NMS) processing is then performed on the boxes whose confidence is equal to or greater than the confidence threshold. Therefore, whether the paper money is damaged to a certain degree or not is judged, and the paper money needs to be recovered, and the following formula can be adopted:
where n is the number of output bounding boxes, P (Object) is the corresponding confidence, w, h is the length and width of the output bounding boxes, W, H is the length and width of the banknote, and X is the quotient of the detected defect area and the total area of the banknote. And comparing X with a set threshold value, and if the ratio of the sum of the detected defect areas to the total area of the paper currency is greater than or equal to the set threshold value, considering that the paper currency is damaged to a certain degree and needs to be recovered.
Referring to fig. 6, the present invention further provides a banknote breakage recognition device based on deep learning, the device includes: the device comprises an image acquisition module, a preprocessing module, a training module and an identification module; the image acquisition module is used for acquiring image information of paper money, and respectively intercepting a defect image block and a standard image block in the image information to generate defect data and defect-free data; the preprocessing module is used for carrying out filtering and/or amplifying treatment on the defect data and the defect-free data to generate a training image, calibrating the damaged position of paper money in the defect data to generate defect type data, and generating training set data according to the training image and the defect type data; the training module is used for training a preset YOLOv3 network through the training set data to obtain a paper money detection model, and inputting paper money images to be detected into the paper money detection model to obtain characteristic parameters; the recognition module is used for calculating and obtaining a paper currency defect ratio according to the characteristic parameters, and comparing the paper currency defect ratio with a preset threshold value to obtain the paper currency damage condition.
In the above embodiment, the image acquisition module includes: and acquiring a banknote image through a CDD visual detection device, and converting the banknote image into a gray image to obtain image information. In another embodiment, the pretreatment module comprises a filtration unit and an amplification unit; the filtering unit is used for replacing the particle noise points of the defect data and the defect-free data by using a low-pass or high-pass filter through the weighted average value of each pixel in the pixel point field of the particle noise points in the defect data and the defect-free data; the amplification unit is used for amplifying one or more of rotating the defect data and the defect-free data according to a preset angle, adjusting brightness and contrast and adding Gaussian white noise.
In an embodiment of the present invention, the identification module includes a calculation unit, where the calculation unit is configured to obtain a location parameter of the feature parameter, and calculate to obtain length and width data of the banknote according to the location parameter; and carrying out calculation according to the confidence coefficient in the length and width data and the characteristic parameters and the defect classification probability into a preset sigmoid function to obtain the banknote defect ratio.
The beneficial technical effects of the invention are as follows: aiming at the condition of small-size breakage of paper money, the original three original prediction scales of Yolov3 cannot meet the requirements, so that the 4 th prediction scale is increased. The signature of [52,52,255] is up-sampled and connected with a signature of [104,104,255] size in the convolution process, which is 4 times the down-sampled size of the input image, and the receptive field is suitable for detecting the small-size damaged position in the paper currency defect. The dense connection network DenseNet is used for replacing the original network structure Darknet-53, each layer of the DenseNet can accept all the previous layers as additional input, the characteristic reuse among multiple layers can be realized better, the gradient vanishing problem in the original structure is relieved, and the network computing efficiency is improved.
The invention also provides a computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the above method when executing the computer program.
The present invention also provides a computer readable storage medium storing a computer program for executing the above method.
As shown in fig. 7, the electronic device 600 may further include: a communication module 110, an input unit 120, an audio processing unit 130, a display 160, a power supply 170. It is noted that the electronic device 600 need not include all of the components shown in fig. 7; in addition, the electronic device 600 may further include components not shown in fig. 7, to which reference is made to the related art.
As shown in fig. 7, the central processor 100, sometimes also referred to as a controller or operational control, may include a microprocessor or other processor device and/or logic device, which central processor 100 receives inputs and controls the operation of the various components of the electronic device 600.
The memory 140 may be, for example, one or more of a buffer, a flash memory, a hard drive, a removable media, a volatile memory, a non-volatile memory, or other suitable device. The information about failure may be stored, and a program for executing the information may be stored. And the central processor 100 can execute the program stored in the memory 140 to realize information storage or processing, etc.
The input unit 120 provides an input to the central processor 100. The input unit 120 is, for example, a key or a touch input device. The power supply 170 is used to provide power to the electronic device 600. The display 160 is used for displaying display objects such as images and characters. The display may be, for example, but not limited to, an LCD display.
The memory 140 may be a solid state memory such as Read Only Memory (ROM), random Access Memory (RAM), SIM card, or the like. But also a memory which holds information even when powered down, can be selectively erased and provided with further data, an example of which is sometimes referred to as EPROM or the like. Memory 140 may also be some other type of device. Memory 140 includes a buffer memory 141 (sometimes referred to as a buffer). The memory 140 may include an application/function storage 142, the application/function storage 142 for storing application programs and function programs or a flow for executing operations of the electronic device 600 by the central processor 100.
The memory 140 may also include a data store 143, the data store 143 for storing data, such as contacts, digital data, pictures, sounds, and/or any other data used by the electronic device. The driver storage 144 of the memory 140 may include various drivers of the electronic device for communication functions and/or for performing other functions of the electronic device (e.g., messaging applications, address book applications, etc.).
The communication module 110 is a transmitter/receiver 110 that transmits and receives signals via an antenna 111. A communication module (transmitter/receiver) 110 is coupled to the central processor 100 to provide an input signal and receive an output signal, which may be the same as in the case of a conventional mobile communication terminal.
Based on different communication technologies, a plurality of communication modules 110, such as a cellular network module, a bluetooth module, and/or a wireless local area network module, etc., may be provided in the same electronic device. The communication module (transmitter/receiver) 110 is also coupled to a speaker 131 and a microphone 132 via an audio processor 130 to provide audio output via the speaker 131 and to receive audio input from the microphone 132 to implement usual telecommunication functions. The audio processor 130 may include any suitable buffers, decoders, amplifiers and so forth. In addition, the audio processor 130 is also coupled to the central processor 100 so that sound can be recorded locally through the microphone 132 and so that sound stored locally can be played through the speaker 131.
It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The foregoing description of the embodiments has been provided for the purpose of illustrating the general principles of the invention, and is not meant to limit the scope of the invention, but to limit the invention to the particular embodiments, and any modifications, equivalents, improvements, etc. that fall within the spirit and principles of the invention are intended to be included within the scope of the invention.
Claims (9)
1. A banknote breakage condition recognition method based on deep learning, the method comprising:
acquiring image information of paper money, and respectively intercepting a defect image block and a standard image block in the image information to generate defect data and defect-free data;
filtering and/or amplifying the defect data and the defect-free data to generate a training image, calibrating the damaged position of paper money in the defect data to generate defect type data, and generating training set data according to the training image and the defect type data;
training a preset YOLOv3 network through the training set data to obtain a paper money detection model, and inputting paper money images to be detected into the paper money detection model to obtain characteristic parameters;
calculating according to the characteristic parameters to obtain a paper currency defect ratio, and comparing the paper currency defect ratio with a preset threshold value to obtain a paper currency breakage condition;
the banknote defect ratio obtained by calculation according to the characteristic parameters comprises the following steps:
acquiring position parameters of the characteristic parameters, and calculating to acquire length and width data of paper money according to the position parameters;
carrying out calculation according to the confidence coefficient and the defect classification probability in the length and width data and the characteristic parameters and a preset sigmoid function to obtain a banknote defect ratio;
the preset YOLOv3 network comprises: replacing the dark-53 in the YOLOv3 network structure by a dense connectivity network DenseNet;
the sigmoid function includes:
where n is the number of output bounding boxes, P (Object) is the corresponding confidence, w, h is the length and width of the output bounding boxes, W, H is the length and width of the banknote, and X is the quotient of the detected defect area and the total area of the banknote.
2. The method for recognizing a banknote breakage based on deep learning according to claim 1, wherein acquiring image information of the banknote comprises: and acquiring a banknote image through a CDD visual detection device, and converting the banknote image into a gray image to obtain image information.
3. The deep learning based banknote break condition recognition method according to claim 1, wherein filtering and/or amplifying the defect data and the non-defect data to generate a training image comprises:
replacing the particle noise points of the defect data and the defect-free data by using a low-pass or high-pass filter through the weighted average value of each pixel in the pixel point field of the particle noise points in the defect data and the defect-free data;
and performing amplification on the defect data and the defect-free data according to one or more of preset angle rotation, brightness and contrast adjustment and Gaussian white noise addition.
4. The banknote break condition recognition method based on deep learning according to claim 1, wherein the defect type data includes a picture path, a break type, and coordinate position information.
5. A banknote breakage recognition device based on deep learning, the device comprising: the device comprises an image acquisition module, a preprocessing module, a training module and an identification module;
the image acquisition module is used for acquiring image information of paper money, and respectively intercepting a defect image block and a standard image block in the image information to generate defect data and defect-free data;
the preprocessing module is used for carrying out filtering and/or amplifying treatment on the defect data and the defect-free data to generate a training image, calibrating the damaged position of paper money in the defect data to generate defect type data, and generating training set data according to the training image and the defect type data;
the training module is used for training a preset YOLOv3 network through the training set data to obtain a paper money detection model, and inputting paper money images to be detected into the paper money detection model to obtain characteristic parameters;
the recognition module is used for calculating and obtaining a paper currency defect ratio according to the characteristic parameters, and comparing the paper currency defect ratio with a preset threshold value to obtain a paper currency breakage condition;
the identification module comprises a calculation unit, wherein the calculation unit is used for acquiring position parameters of the characteristic parameters and calculating length and width data of paper money according to the position parameters; carrying out calculation according to the confidence coefficient and the defect classification probability in the length and width data and the characteristic parameters and a preset sigmoid function to obtain a banknote defect ratio;
the preset YOLOv3 network comprises: replacing the dark-53 in the YOLOv3 network structure by a dense connectivity network DenseNet;
the sigmoid function includes:
where n is the number of output bounding boxes, P (Object) is the corresponding confidence, w, h is the length and width of the output bounding boxes, W, H is the length and width of the banknote, and X is the quotient of the detected defect area and the total area of the banknote.
6. The deep learning based banknote break condition recognition device according to claim 5, wherein the image acquisition module comprises: and acquiring a banknote image through a CDD visual detection device, and converting the banknote image into a gray image to obtain image information.
7. The deep learning based banknote break condition recognition device according to claim 5, wherein the preprocessing module comprises a filtering unit and an amplifying unit;
the filtering unit is used for replacing the particle noise points of the defect data and the defect-free data by using a low-pass or high-pass filter through the weighted average value of each pixel in the pixel point field of the particle noise points in the defect data and the defect-free data;
the amplification unit is used for amplifying one or more of rotating the defect data and the defect-free data according to a preset angle, adjusting brightness and contrast and adding Gaussian white noise.
8. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the method of any of claims 1 to 4 when executing the computer program.
9. A computer readable storage medium, characterized in that the computer readable storage medium stores a computer program for executing the method of any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110232998.8A CN112950837B (en) | 2021-03-03 | 2021-03-03 | Banknote breakage condition identification method and device based on deep learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110232998.8A CN112950837B (en) | 2021-03-03 | 2021-03-03 | Banknote breakage condition identification method and device based on deep learning |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112950837A CN112950837A (en) | 2021-06-11 |
| CN112950837B true CN112950837B (en) | 2023-06-16 |
Family
ID=76247300
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110232998.8A Active CN112950837B (en) | 2021-03-03 | 2021-03-03 | Banknote breakage condition identification method and device based on deep learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112950837B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114255540A (en) * | 2022-01-25 | 2022-03-29 | 中国农业银行股份有限公司 | Method, device, equipment and storage medium for identifying stained paper money |
| EP4231257A1 (en) * | 2022-02-22 | 2023-08-23 | European Central Bank | Test deck of artificially soiled banknotes, manufacturing process and uses thereof |
| CN114643209B (en) * | 2022-03-04 | 2024-04-12 | 南京业恒达智能系统有限公司 | Clothing sorting method, device, computer readable medium and electronic equipment |
| CN116912721B (en) * | 2023-09-14 | 2023-12-05 | 众芯汉创(江苏)科技有限公司 | Power distribution network equipment body identification method and system based on monocular stereoscopic vision |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109636772A (en) * | 2018-10-25 | 2019-04-16 | 同济大学 | The defect inspection method on the irregular shape intermetallic composite coating surface based on deep learning |
| CN109685968A (en) * | 2018-12-15 | 2019-04-26 | 西安建筑科技大学 | A kind of the identification model building and recognition methods of the banknote image defect based on convolutional neural networks |
| CN110689531A (en) * | 2019-09-23 | 2020-01-14 | 云南电网有限责任公司电力科学研究院 | Automatic power transmission line machine inspection image defect identification method based on yolo |
| CN110766098A (en) * | 2019-11-07 | 2020-02-07 | 中国石油大学(华东) | Traffic scene small target detection method based on improved YOLOv3 |
| CN111402211A (en) * | 2020-03-04 | 2020-07-10 | 广西大学 | High-speed train bottom foreign matter identification method based on deep learning |
| CN112364721A (en) * | 2020-10-23 | 2021-02-12 | 西安科锐盛创新科技有限公司 | Road surface foreign matter detection method |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP3739513A1 (en) * | 2019-05-13 | 2020-11-18 | Fujitsu Limited | Surface defect identification method and apparatus |
-
2021
- 2021-03-03 CN CN202110232998.8A patent/CN112950837B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109636772A (en) * | 2018-10-25 | 2019-04-16 | 同济大学 | The defect inspection method on the irregular shape intermetallic composite coating surface based on deep learning |
| CN109685968A (en) * | 2018-12-15 | 2019-04-26 | 西安建筑科技大学 | A kind of the identification model building and recognition methods of the banknote image defect based on convolutional neural networks |
| CN110689531A (en) * | 2019-09-23 | 2020-01-14 | 云南电网有限责任公司电力科学研究院 | Automatic power transmission line machine inspection image defect identification method based on yolo |
| CN110766098A (en) * | 2019-11-07 | 2020-02-07 | 中国石油大学(华东) | Traffic scene small target detection method based on improved YOLOv3 |
| CN111402211A (en) * | 2020-03-04 | 2020-07-10 | 广西大学 | High-speed train bottom foreign matter identification method based on deep learning |
| CN112364721A (en) * | 2020-10-23 | 2021-02-12 | 西安科锐盛创新科技有限公司 | Road surface foreign matter detection method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112950837A (en) | 2021-06-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112950837B (en) | Banknote breakage condition identification method and device based on deep learning | |
| CN108229490B (en) | Key point detection method, neural network training method, device and electronic equipment | |
| Rahmouni et al. | Distinguishing computer graphics from natural images using convolution neural networks | |
| CN110705583B (en) | Cell detection model training method, device, computer equipment and storage medium | |
| CN112308095A (en) | Picture preprocessing and model training method and device, server and storage medium | |
| US20200202503A1 (en) | Reduction of glare in imaging documents | |
| CN111460931A (en) | Face spoofing detection method and system based on color channel difference image characteristics | |
| CN112329702B (en) | Method and device for rapid face density prediction and face detection, electronic equipment and storage medium | |
| CN110070115B (en) | Single-pixel attack sample generation method, device, equipment and storage medium | |
| JP2010525486A (en) | Image segmentation and image enhancement | |
| CN109523527A (en) | The detection method in dirty region, device and electronic equipment in image | |
| CN111046746A (en) | License plate detection method and device | |
| WO2020048359A1 (en) | Method, system, and computer-readable medium for improving quality of low-light images | |
| CN111127358A (en) | Image processing method, device and storage medium | |
| US20220036141A1 (en) | Target object identification method and apparatus | |
| CN113920434A (en) | Image reproduction detection method, device and medium based on target | |
| WO2022029482A1 (en) | Target object identification method and apparatus | |
| CN116664833A (en) | Method for improving target re-identification model capacity and target re-identification method | |
| WO2023280081A1 (en) | Apparatus and method for identifying empty tray | |
| CN113947613B (en) | Target area detection method, device, equipment and storage medium | |
| Kocdemir et al. | TMO-Det: Deep tone-mapping optimized with and for object detection | |
| CN116310875A (en) | Target detection method and device for satellite remote sensing image | |
| CN113807407B (en) | Target detection model training method, model performance detection method and device | |
| CN113573137A (en) | Video canvas boundary detection method, system, terminal equipment and storage medium | |
| CN115527023A (en) | Image detection method, image detection device, electronic equipment and 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |