CN115083066B - Method and device for detecting whether paper currency is old or new based on digital image - Google Patents
Method and device for detecting whether paper currency is old or new based on digital image Download PDFInfo
- Publication number
- CN115083066B CN115083066B CN202210849734.1A CN202210849734A CN115083066B CN 115083066 B CN115083066 B CN 115083066B CN 202210849734 A CN202210849734 A CN 202210849734A CN 115083066 B CN115083066 B CN 115083066B
- Authority
- CN
- China
- Prior art keywords
- paper money
- area
- detected
- characteristic
- matrix
- 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
- 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
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/10—Image acquisition
- G06V10/12—Details of acquisition arrangements; Constructional details thereof
- G06V10/14—Optical characteristics of the device performing the acquisition or on the illumination arrangements
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/22—Image preprocessing by selection of a specific region containing or referencing a pattern; Locating or processing of specific regions to guide the detection or recognition
- G06V10/225—Image preprocessing by selection of a specific region containing or referencing a pattern; Locating or processing of specific regions to guide the detection or recognition based on a marking or identifier characterising the area
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/761—Proximity, similarity or dissimilarity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
-
- 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
- G07D11/10—Mechanical details
- G07D11/16—Handling of valuable papers
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- General Health & Medical Sciences (AREA)
- Software Systems (AREA)
- Medical Informatics (AREA)
- Databases & Information Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Molecular Biology (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Inspection Of Paper Currency And Valuable Securities (AREA)
Abstract
The invention provides a method and a device for detecting whether paper money is old or new based on a digital image, wherein the method comprises the following steps: collecting a blue light gray image of the paper money to be detected under blue light and a red light gray image of the paper money to be detected under red light by using an image sensor; selecting a blank area of the blue-ray gray-scale image as a characteristic area, and marking the characteristic area as a matrix A = [ aij ]; selecting a blank area of the red light gray image as a contrast area, and marking the contrast area as a matrix B = [ bij ]; making a difference between the characteristic area and the comparison area to obtain a brand new characteristic area matrix C = [ cij ]; calculating the proportion P of all pixel points of the characteristic region occupied by the pixel points of which the pixels exceed a preset pixel threshold in the brand new characteristic region matrix; if the specific gravity is less than or equal to the preset specific gravity threshold value, the paper money to be detected is new; otherwise, the paper money to be detected is the old paper money. The technology can determine the old and new of the paper money more quickly and accurately.
Description
Technical Field
The invention relates to the technical field of paper money detection, in particular to a method and a device for detecting whether paper money is old or new by a digital image.
Background
Along with the rapid development of social economy and the acceleration of currency circulation speed, the phenomenon of worn and stained paper money is more and more prominent, and great inconvenience is brought to the life of people. So that new and old detections in banknote sorting are also becoming more and more important. The new and old paper money detection is one of the key technologies of paper money sorting detection. At present, the work of classifying the new bank paper money and the old bank paper money is mainly completed by manual processing of workers. This manual detection is time consuming, labor intensive and inefficient. Meanwhile, the manual detection has no clear judgment standard, and different personnel have different standards for judging whether the paper money is new or old. The paper money sorting machine in the market mainly cleans, sorts and classifies the RMB of different versions, and realizes the functions of counting money, counting, identifying true and false and the like of the RMB paper money. Therefore, a method for accurately and rapidly judging whether the paper money is old or new is urgently needed.
Disclosure of Invention
A method and apparatus for detecting whether a banknote is new or old based on a digital image is provided. Firstly, collecting a gray image under blue light and a gray image under red light of a paper money to be detected, then extracting an image outline, and solving similarity measurement between a new RMB and the RMB to be detected. And finally, judging the freshness of the RMB to be detected according to the similarity metric value. The technology can accurately and quickly judge the freshness of the paper money.
In a first aspect, the present invention provides a method for detecting whether a banknote is new or old based on a digital image, the method comprising: collecting a blue light gray image of the paper money to be detected under blue light and a red light gray image of the paper money to be detected under red light by using an image sensor; selecting a blank area of the blue-light gray image as a characteristic area, and marking the characteristic area as a matrix A = [ aij ]; selecting a blank area of the red light gray image as a contrast area, and marking the contrast area as a matrix B = [ bij ]; making a difference between the characteristic area and the comparison area to obtain a brand new characteristic area matrix C = [ cij ]; calculating the proportion P of all pixel points of the characteristic region occupied by the pixel points of which the pixels exceed a preset pixel threshold in the brand new characteristic region matrix; if the specific gravity is less than or equal to the preset specific gravity threshold value, the paper money to be detected is new; otherwise, the paper money to be detected is the old paper money.
Further, the preset pixel threshold is 200; the preset specific gravity threshold is 0.08.
Further, for the same paper currency to be detected, the positions of the characteristic region and the comparison region in the paper currency to be detected are the same, and the coordinates of the contained pixel points are the same.
Further, the feature region and the contrast region are both rectangular in shape.
Further, for the paper money to be detected with the same version and the same face value, the positions and the sizes of the characteristic region and the comparison region and the coordinates of the contained pixel points are the same.
Further, if the banknote to be detected is a 2005 edition of 100 yuan banknote, the number of pixels at the position of the characteristic region and the position of the comparison region, which are away from the upper boundary of the banknote to be detected, are 125, and the number of pixels at the left boundary, which are away from the banknote to be detected, are 10; the width of the characteristic region and the contrast region are both 115 pixel points, and the height is 65 pixel points.
Further, the method further comprises: determining a characteristic area and a comparison area according to the face value of the paper money to be detected based on a preset database; the preset database comprises position coordinates of the characteristic areas and the comparison areas corresponding to different face values.
Further, the method further comprises: and automatically rotating the paper money to be detected to acquire an accurate gray image.
In a second aspect, an embodiment of the present invention provides an apparatus for detecting whether a banknote is new or old based on a digital image, where the apparatus includes: the image acquisition module is used for acquiring a blue light gray image of the paper money to be detected under blue light and a red light gray image of the paper money to be detected under red light by using the image sensor; the characteristic region determining module is used for selecting a blank region of the blue-ray gray-scale image as a characteristic region and marking the characteristic region as a matrix A = [ aij ]; the comparison area determining module is used for selecting a blank area of the red light gray image as a comparison area and marking the comparison area as a matrix B = [ bij ]; the brand new characteristic area matrix calculation module is used for subtracting the characteristic area from the comparison area to obtain a brand new characteristic area matrix C; the proportion calculation module is used for calculating the proportion P of all pixel points of the characteristic region occupied by pixel points of which the pixels exceed a preset pixel threshold in the brand-new characteristic region matrix; the new and old confirmation module is used for determining the paper money to be detected as new paper money if the specific gravity is less than or equal to a preset specific gravity threshold; otherwise, the paper money to be detected is the old paper money.
The embodiment of the invention has the following beneficial effects:
the invention provides a method and a device for detecting whether paper money is old or new based on digital images, wherein the method comprises the steps of collecting a blue light gray image of the paper money to be detected under blue light and a red light gray image of the paper money to be detected under red light by using an image sensor; selecting a blank area of the blue-ray gray-scale image as a characteristic area, and marking the characteristic area as a matrix A = [ aij ]; selecting a blank area of the red light gray image as a contrast area, and marking the contrast area as a matrix B = [ bij ]; making a difference between the characteristic area and the comparison area to obtain a brand new characteristic area matrix C = [ cij ]; calculating the proportion P of all pixel points of the characteristic region occupied by the pixel points of which the pixels exceed a preset pixel threshold in the brand new characteristic region matrix; if the specific gravity is less than or equal to the preset specific gravity threshold value, the paper money to be detected is new; otherwise, the paper money to be detected is the old paper money. The technology can accurately and quickly judge the old and new of the paper money.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by the practice of the invention as set forth hereinafter.
In order to make the aforementioned and other objects, features and advantages of the present invention comprehensible, preferred embodiments accompanied with figures are described in detail below.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
FIG. 1 is a flowchart of a method for detecting whether a banknote is new or old according to an embodiment of the present invention;
fig. 2 is a flowchart of another method for detecting whether a banknote is new or old according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. The components of embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations.
Thus, the following detailed description of the embodiments of the present invention, presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Along with the rapid development of social economy and the acceleration of currency circulation speed, the phenomenon of worn and stained paper money is more and more prominent, and great inconvenience is brought to the life of people. So the new and old detection in the sorting of banknotes is also becoming more and more important. The new and old paper money detection is one of the key technologies of paper money sorting detection. At present, the work of classifying the new bank paper money and the old bank paper money is mainly completed by manual processing of workers. This kind of manual detection is time-consuming, hard, inefficient. Meanwhile, the manual detection has no clear judgment standard, and different personnel have different standards for judging whether the paper money is new or old. The paper money sorting machine in the market mainly cleans, sorts and classifies the RMB of different versions, and realizes the functions of counting money, counting, identifying true and false and the like of the RMB paper money. Therefore, a method for accurately and rapidly judging whether the paper money is old or new is urgently needed.
Based on the method, the invention provides a method and a device for detecting whether the paper money is old or new based on a digital image. Firstly, collecting a gray image under blue light and a gray image under a red light image of a paper money to be detected, then extracting an image outline, and solving the similarity measurement between a new RMB and the RMB to be detected; and finally, judging the freshness of the RMB to be detected according to the similarity metric value. The technology can accurately and quickly judge the old and new of the paper money. The technology is applied to the technical scene of detecting the old and new of the paper money.
Example one
The invention provides a method for detecting whether paper currency is old or new based on digital images, which comprises the following steps of:
and S102, collecting a blue light gray image of the paper money to be detected under blue light and a red light gray image of the paper money to be detected under red light by using an image sensor.
Specifically, prior to image acquisition, the banknote to be tested needs to be automatically rotated to acquire an accurate grayscale image. That is, since the banknotes are moved after entering the machine, the banknotes are randomly rotated, and the banknotes are usually tilted to some extent, and although the dimensions are not large, they affect the selected detection area. In order to solve the problem, the invention firstly rotates the image when the detection area is intercepted.
Step S104, selecting a blank area of the blue-light gray image as a feature area, and marking the feature area as a matrix a = [ aij ].
Step S106, selecting a blank area of the red gray image as a contrast area, and marking the contrast area as a matrix B = [ bij ].
Specifically, for the same banknote to be detected, the positions of the characteristic region and the comparison region in the banknote to be detected are the same, and the coordinates of the included pixel points are the same. The characteristic region and the contrast region are both rectangular in shape.
Step S108, subtracting the feature area from the contrast area to obtain a brand new feature area matrix C = [ cij ].
Specifically, the above process is to make a difference between pixel values of corresponding pixels of the feature region and the contrast region, that is, C = a-B. A. And B is a matrix formed by pixel values of pixel points in the region.
Step S110, calculating the proportion P of all pixel points of the characteristic region occupied by pixel points of which the pixels exceed a preset pixel threshold in the brand-new characteristic region matrix.
Specifically, the preset pixel threshold is generally 200. The value of 200 is a critical value determined by testing a large number of brand new and old coins.
Step S112, if the specific gravity is less than or equal to a preset specific gravity threshold, the paper money to be detected is a new paper money; otherwise, the paper money to be detected is the old paper money.
Specifically, in general, the preset specific gravity threshold is 0.08. The value 0.08 is a critical value determined by testing a large number of new and old coins.
And more specifically, for the paper money to be detected with the same version and the same face value, the positions and the sizes of the characteristic region and the comparison region and the coordinates of the contained pixel points are the same. For example, if the paper money to be detected is 2005 edition of 100 yuan paper money, the distance between the characteristic region and the contrast region is 37mm from the upper boundary of the paper money to be detected, and the distance between the characteristic region and the contrast region is 3mm from the left boundary of the paper money to be detected; the feature and contrast areas are 34mm wide and 20mm high, and are generally rectangular. Therefore, the positions of the characteristic areas and the comparison areas of the paper money with different versions and different denominations can be determined in advance and stored in a preset database, and therefore detection can be carried out more quickly.
More specifically, the direction of the bill put by the user (i.e., the orientation of the bill) includes 4 types: 1 obverse direction, 2 obverse direction, 3 reverse direction, 4 reverse direction. After the user puts the paper currency that awaits measuring into the device, the sensor will be discerned the orientation of paper currency that awaits measuring, and the identification process is:
1) The sensor acquires an image of the paper money to be detected, and then performs preprocessing on the acquired image of the paper money (wherein the preprocessing comprises: rotating the image, solving a circumscribed rectangle, and the like) respectively taking and splicing the parts with the width of 400mm and the height of 36mm in the middle of the front and the back of the banknote image to be detected, and if the user puts the banknote image in the front, extracting a front-direction spliced graph with the size of 400 × 72mm; if the user puts the user in the reverse side, a reverse side forward splicing map is extracted, and the size of the map is also 400 × 72mm;
2) And (3) putting the obtained matrix of the spliced image into a BP neural network for identification, outputting a classification result by the neural network, and finally judging the orientation of the paper money according to the output result of the neural network.
More specifically, for 2015 edition 100 yuan banknotes, regardless of the orientation of the banknotes, the positions of the feature region and the comparison region are 37mm away from the upper boundary of the banknotes to be detected and 3mm away from the left boundary of the banknotes to be detected under the condition that the front faces are positive; the feature and contrast areas were 34mm wide and 20mm high.
More specifically, all the involved image resolutions in the patent of the invention are 100dpi; the technology of the invention can identify the authenticity of 3 kinds of paper money, namely 99 edition 100 yuan, 05 edition 100 yuan and 15 edition 100 yuan.
Fig. 2 is a flowchart of a simplified method for detecting whether a banknote is old or new according to an embodiment of the present invention, where fig. 2 includes the following steps:
step S202, based on a preset database, determining a characteristic area and a comparison area according to the face value of the paper money to be detected; the preset database comprises position coordinates of the characteristic areas and the comparison areas corresponding to different face values.
Specifically, the coordinates of the four feature areas (i.e., the coordinates of the 4 edge points of the rectangular feature area) of each denomination and each version of the banknote are recorded in advance and stored in a preset database. In actual use, the face value and the version of the real-time paper money to be detected are determined, and then the coordinates of the characteristic region and the comparison region are directly extracted according to the information of the face value and the version.
And step S204, subtracting the characteristic area from the comparison area to obtain a brand new characteristic area matrix C.
Step S206, calculating the proportion P of the pixel points of the brand new characteristic region matrix, of which the pixels exceed the preset pixel threshold value, to all the pixel points of the characteristic region.
Step S208, if the specific gravity is less than or equal to a preset specific gravity threshold, the paper money to be detected is a new paper money; otherwise, the paper money to be detected is the old paper money.
The beneficial effects of this embodiment are as follows:
1. the new and old banknotes can be accurately, automatically and stably judged by a preset algorithm (namely calculating a difference value for a target area, calculating a similarity measurement (namely specific gravity P) between the new RMB and the RMB to be detected, and judging the new and old degrees of the RMB to be detected according to the similarity measurement value).
2. In consideration of the complexity of the paper money pattern, the technology selects an area with more uniform pixel values on the paper money image as a target area (namely, a blank area of the paper money is used as a characteristic area and a contrast area of the paper money), thereby eliminating the noise influence and ensuring that the detection is quicker and more accurate.
3. The technology combines the red light detection and the blue light detection, so that the detection result is more accurate.
4. Due to the movement of the banknotes after entering the machine, the banknotes are rotated randomly and they are usually tilted to a certain extent, although of small dimensions, which affect the selected detection zone. In order to solve the problem, when the detection area is intercepted, the image is firstly rotated so as to acquire a more accurate initial image.
5. The position of the characteristic region and the position of the comparison region of the paper money with different face values and different versions are predetermined and correspondingly stored in the preset database, the characteristic region and the comparison region are directly called in the later stage according to the face values of the paper money to be detected, and new and old detection results can be obtained more quickly.
Example two
The embodiment of the invention provides a device for detecting whether paper money is old or new based on a digital image, which comprises:
the image acquisition module is used for acquiring a blue light gray image of the paper money to be detected under blue light and a red light gray image of the paper money to be detected under red light by using the image sensor;
the characteristic region determining module is used for selecting a blank region of the blue-light gray-scale image as a characteristic region and marking the characteristic region as a matrix A = [ aij ];
the comparison area determining module is used for selecting a blank area of the red light gray image as a comparison area and marking the comparison area as a matrix B = [ bij ];
the brand new characteristic area matrix calculation module is used for subtracting the characteristic area from the comparison area to obtain a brand new characteristic area matrix C;
the proportion calculation module is used for calculating the proportion P of all pixel points of the characteristic region occupied by pixel points of which the pixels exceed a preset pixel threshold in the brand-new characteristic region matrix;
the old and new confirmation module is used for determining the paper money to be detected as new money if the specific gravity is less than or equal to a preset specific gravity threshold; otherwise, the paper money to be detected is the old paper money.
The realization principle and the generated technical effect of the device for detecting the new and old paper money based on the digital image provided by the embodiment of the invention are the same as those of the method embodiment for detecting the new and old paper money based on the digital image.
Finally, it should be noted that: the above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; while the invention has been described in detail and with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the present invention.
Claims (8)
1. A method for detecting whether a banknote is new or old based on a digital image, the method comprising:
collecting a blue light gray image of the paper money to be detected under blue light and a red light gray image of the paper money to be detected under red light by using an image sensor;
selecting a blank area of the blue light gray image as a characteristic area, and marking the characteristic area as a matrix A = [ aij ];
selecting a blank area of the red light gray image as a contrast area, and marking the contrast area as a matrix B = [ bij ]; for the same paper money to be detected, the positions of the characteristic region and the comparison region in the paper money to be detected are the same, and the coordinates of the contained pixel points are the same; the matrix A and the matrix B are both matrixes formed by pixel values of pixel points;
the characteristic area and the comparison area are subjected to subtraction to obtain a brand new characteristic area matrix C;
calculating the proportion P of all pixel points of the characteristic region occupied by pixel points of which the pixels in the brand new characteristic region matrix exceed a preset pixel threshold;
if the specific gravity is smaller than or equal to a preset specific gravity threshold value, the paper money to be detected is a new paper money; otherwise, the paper money to be detected is the old paper money.
2. The method for detecting the freshness of a banknote based on a digital image according to claim 1, wherein the preset pixel threshold is 200; the preset specific gravity threshold is 0.08.
3. The method for detecting the freshness of a banknote based on a digital image as claimed in claim 2, wherein the feature area and the contrast area are both rectangular in shape.
4. The method for detecting whether a banknote is new or old based on a digital image as claimed in claim 3, wherein the position, the size and the coordinates of the included pixel points of the characteristic region and the comparison region are the same for the banknotes to be detected with the same version and the same face value.
5. The method for detecting whether a banknote is new or old based on digital images as claimed in claim 4, wherein if the banknote to be detected is a 2005-edition 100-dollar banknote, the positions of the feature region and the comparison region are 125 pixels away from the upper boundary of the banknote to be detected and 10 pixels away from the left boundary of the banknote to be detected;
the width of the characteristic region and the width of the comparison region are both 115 pixel points, and the height of the characteristic region and the height of the comparison region are both 65 pixel points.
6. The method for detecting the freshness of a banknote based on a digital image according to claim 5, further comprising: determining the characteristic area and the comparison area according to the face value of the paper money to be detected based on a preset database; and the preset database comprises position coordinates of the characteristic areas and the comparison areas corresponding to different face values.
7. The method for detecting the freshness of paper money based on digital images as claimed in claim 6, wherein before the step of collecting the blue light gray image under blue light and the red light gray image under red light of the paper money to be detected by using the image sensor, the method further comprises:
and automatically rotating the paper money to be detected so as to acquire an accurate gray image.
8. An apparatus for detecting whether a banknote is new or old based on a digital image, the apparatus comprising:
the image acquisition module is used for acquiring a blue light gray image of the paper money to be detected under blue light and a red light gray image of the paper money to be detected under red light by using the image sensor;
a characteristic region determining module, configured to select a blank region of the blue-light grayscale image as a characteristic region, and mark the characteristic region as a matrix a = [ aij ];
a comparison area determining module, configured to select a blank area of the red light grayscale image as a comparison area, and mark the comparison area as a matrix B = [ bij ]; for the same paper money to be detected, the positions of the characteristic region and the comparison region in the paper money to be detected are the same, and the coordinates of the contained pixel points are the same; the matrix A and the matrix B are both matrixes formed by pixel values of pixel points;
a brand new characteristic area matrix calculation module, configured to make a difference between the characteristic area and the comparison area, to obtain a brand new characteristic area matrix C = [ cij ];
the proportion calculation module is used for calculating the proportion P of all pixel points of the characteristic region occupied by the pixel points of which the pixels in the brand-new characteristic region matrix exceed a preset pixel threshold;
the old and new confirmation module is used for determining the paper money to be detected as new paper money if the specific gravity is less than or equal to a preset specific gravity threshold; otherwise, the paper money to be detected is the old paper money.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210849734.1A CN115083066B (en) | 2022-07-20 | 2022-07-20 | Method and device for detecting whether paper currency is old or new based on digital image |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210849734.1A CN115083066B (en) | 2022-07-20 | 2022-07-20 | Method and device for detecting whether paper currency is old or new based on digital image |
Publications (2)
Publication Number | Publication Date |
---|---|
CN115083066A CN115083066A (en) | 2022-09-20 |
CN115083066B true CN115083066B (en) | 2022-12-06 |
Family
ID=83259187
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210849734.1A Active CN115083066B (en) | 2022-07-20 | 2022-07-20 | Method and device for detecting whether paper currency is old or new based on digital image |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115083066B (en) |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPS6451595A (en) * | 1987-08-24 | 1989-02-27 | Oki Electric Ind Co Ltd | Paper money discriminator |
JPH1069558A (en) * | 1996-08-29 | 1998-03-10 | Sanyo Electric Co Ltd | Paper money identifying method |
CN202995871U (en) * | 2012-11-16 | 2013-06-12 | 北京兆维电子(集团)有限责任公司 | Bank note authentic identification device |
CN104966349A (en) * | 2015-06-30 | 2015-10-07 | 新达通科技股份有限公司 | ATM platform-based method of detecting new bank note and old bank note |
WO2016183831A1 (en) * | 2015-05-20 | 2016-11-24 | 深圳怡化电脑股份有限公司 | Method and device for identifying defects of paper currency |
JP2017182672A (en) * | 2016-03-31 | 2017-10-05 | キヤノン株式会社 | Method, device, and program for information processing |
KR20180020596A (en) * | 2016-08-19 | 2018-02-28 | 노틸러스효성 주식회사 | Simulation method for creating soiled banknote images |
Family Cites Families (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
FR2877609B1 (en) * | 2004-11-08 | 2007-03-09 | Arjowiggins Security Soc Par A | SAFETY STRUCTURE AND ARTICLE INCORPORATING SUCH A STRUCTURE |
JP2010277252A (en) * | 2009-05-27 | 2010-12-09 | Toshiba Corp | Paper sheet handling apparatus |
CN101986352B (en) * | 2010-12-01 | 2015-04-29 | 威海华菱光电股份有限公司 | Contact image sensor |
CN104063939A (en) * | 2014-06-20 | 2014-09-24 | 威海华菱光电股份有限公司 | Target object authenticity verifying method and device |
JP2016092712A (en) * | 2014-11-10 | 2016-05-23 | セイコーエプソン株式会社 | Image processing apparatus, image processing method and program |
KR101792690B1 (en) * | 2015-12-30 | 2017-11-03 | 기산전자(주) | Banknote processing device |
CN106355739B (en) * | 2016-08-18 | 2019-03-12 | 深圳怡化电脑股份有限公司 | A kind of method and device that detection bank note is new and old |
CN106447906A (en) * | 2016-09-14 | 2017-02-22 | 深圳怡化电脑股份有限公司 | Method and device for identifying money facing direction |
CN106910276B (en) * | 2017-02-24 | 2019-04-26 | 深圳怡化电脑股份有限公司 | Detect the new and old method and device of bank note |
JP2020042485A (en) * | 2018-09-10 | 2020-03-19 | グローリー株式会社 | Currency information providing system, currency information providing database server, currency information providing method and currency information providing program |
TWI703509B (en) * | 2018-12-13 | 2020-09-01 | 致茂電子股份有限公司 | Optical detecting device and calibrating method |
CN113269708B (en) * | 2020-04-17 | 2024-07-12 | 深圳市怡化时代科技有限公司 | Method and device for determining new and old media, computer equipment and storage medium |
-
2022
- 2022-07-20 CN CN202210849734.1A patent/CN115083066B/en active Active
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPS6451595A (en) * | 1987-08-24 | 1989-02-27 | Oki Electric Ind Co Ltd | Paper money discriminator |
JPH1069558A (en) * | 1996-08-29 | 1998-03-10 | Sanyo Electric Co Ltd | Paper money identifying method |
CN202995871U (en) * | 2012-11-16 | 2013-06-12 | 北京兆维电子(集团)有限责任公司 | Bank note authentic identification device |
WO2016183831A1 (en) * | 2015-05-20 | 2016-11-24 | 深圳怡化电脑股份有限公司 | Method and device for identifying defects of paper currency |
CN104966349A (en) * | 2015-06-30 | 2015-10-07 | 新达通科技股份有限公司 | ATM platform-based method of detecting new bank note and old bank note |
JP2017182672A (en) * | 2016-03-31 | 2017-10-05 | キヤノン株式会社 | Method, device, and program for information processing |
KR20180020596A (en) * | 2016-08-19 | 2018-02-28 | 노틸러스효성 주식회사 | Simulation method for creating soiled banknote images |
Also Published As
Publication number | Publication date |
---|---|
CN115083066A (en) | 2022-09-20 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US9064187B2 (en) | Method and system for item identification | |
US20060029257A1 (en) | Apparatus for determining a surface condition of an object | |
TW201305969A (en) | Method and apparatus for authentication of a coin or other manufactured item | |
CN106952393B (en) | Paper money identification method and device, electronic equipment and storage medium | |
CN107103683B (en) | Paper money identification method and device, electronic equipment and storage medium | |
CN109462999B (en) | Visual inspection method based on learning through data balance and visual inspection device using same | |
CN107134047B (en) | White watermark detection method and device | |
CN106204616B (en) | Method and device for identifying currency value of Iran paper money | |
US7010154B2 (en) | Money identifying method and device | |
CN108806058A (en) | A kind of paper currency detecting method and device | |
JPH08189904A (en) | Surface defect detector | |
CN106447904B (en) | Method and device for identifying paper money | |
WO2018130119A1 (en) | Double prefix number-based paper money authenticity identification method and system | |
CN115083066B (en) | Method and device for detecting whether paper currency is old or new based on digital image | |
CN106296975B (en) | method and device for identifying face value of dollar paper money | |
CN111462392A (en) | Method and device for identifying paper money based on multispectral image similarity algorithm | |
CN113033635B (en) | Method and device for detecting invisible graphics context of coin | |
CN111915792B (en) | Method and device for identifying zebra crossing image-text | |
CN117237966B (en) | Banknote recognition method and device based on internal contour of denomination digital character | |
Sooruth et al. | Automatic South African Coin Recognition Through Visual Template Matching | |
CN108961530B (en) | Paper currency defect identification method and system | |
CN108320371B (en) | Method and device for identifying counterfeit paper money | |
US10438436B2 (en) | Method and system for detecting staining | |
CN117798087B (en) | Visual sorting system and terminal for lithium battery based on appearance defect detection | |
US20230394872A1 (en) | Detection of face manipulation by quantified disorder measurements |
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 |