CN105788064B - Bill identification method and device - Google Patents

Bill identification method and device Download PDF

Info

Publication number
CN105788064B
CN105788064B CN201410834833.8A CN201410834833A CN105788064B CN 105788064 B CN105788064 B CN 105788064B CN 201410834833 A CN201410834833 A CN 201410834833A CN 105788064 B CN105788064 B CN 105788064B
Authority
CN
China
Prior art keywords
image
bill
pasting
area
key features
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
Application number
CN201410834833.8A
Other languages
Chinese (zh)
Other versions
CN105788064A (en
Inventor
朱先刚
杜玉振
徐志刚
姜晓军
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Weihai Xinbeiyang Rongxin Science & Technology Co ltd
Shandong New Beiyang Information Technology Co Ltd
Original Assignee
Weihai Xinbeiyang Rongxin Science & Technology Co ltd
Shandong New Beiyang Information Technology Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Weihai Xinbeiyang Rongxin Science & Technology Co ltd, Shandong New Beiyang Information Technology Co Ltd filed Critical Weihai Xinbeiyang Rongxin Science & Technology Co ltd
Priority to CN201410834833.8A priority Critical patent/CN105788064B/en
Publication of CN105788064A publication Critical patent/CN105788064A/en
Application granted granted Critical
Publication of CN105788064B publication Critical patent/CN105788064B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Abstract

The invention discloses a bill identification method and a bill identification device. The bill identification method comprises the following steps: acquiring an image of a bill to be identified; determining a non-pasting area of the bill in the image, wherein the non-pasting area is an area except for the pasting area in the image, and the pasting area is an area pasted with the sticky note in the image of the bill; extracting key features of the non-pasting area; and comparing the key features of the non-pasting area with preset key features. By the method and the device, the effect of improving the counterfeit distinguishing accuracy of the bills is achieved.

Description

Bill identification method and device
Technical Field
The invention relates to the field of bill identification, in particular to a bill identification method and a bill identification device.
Background
Money orders are a common credit payment instrument in the financial field, and are widely used, especially in international trade settlement. In general, the payee of the draft can transfer the draft right by means of name endorsement, the endorsement can be recorded on the back of the draft during the endorsement transfer of the draft, and when the number of transfers is large and the back of the draft cannot meet the requirement of the endorser on the recorded matters, the endorsement is recorded on a sticky note with a uniform format, and the sticky note is adhered to a specified adhesion part of the draft, so the bill held by the ticket holder during the circulation of the draft and the payment of the draft usually comprises the draft and the sticky note which is adhered and connected with the draft.
The prior method for identifying the draft is that when the draft is issued, an original image of the draft is obtained through an image obtaining device, the obtained original image of the draft is uploaded to a database of a bill management system of an issuing organization for storage, when a user settles the draft at the issuing organization, a worker of the issuing organization firstly obtains the image of the draft to be settled through a scanning device, then obtains the original image of the draft from the database of the bill management system, and compares the two images, thereby judging the authenticity of the draft. The original image of the draft acquired by the image acquisition device comprises one or more of a visible light image, an infrared light image and an ultraviolet light image, wherein the image acquired corresponding to each light source at least comprises a key feature for identifying the authenticity of the draft, for example, the visible light image comprises a ticket number, a money amount and other features for identifying the authenticity of the bill, the infrared light image comprises a watermark feature for identifying the authenticity of the bill, and the ultraviolet light image comprises a fluorescence feature for identifying the authenticity of the bill and the like.
The inventor finds that after the draft is pasted with the sticky note on the back surface, the thickness of the draft is changed, and the adhesive part of the sticky note is pasted with glue, so that the optical characteristics of the pasting area of the draft are obviously changed, the problem that the characteristics for identifying the authenticity of the draft in the infrared light image and the ultraviolet light image are difficult to obtain is caused, and the problem that the identification rate is reduced when the draft with the sticky note is identified is easy to occur.
Aiming at the problem that the identification rate is easy to decline when the draft with the sticky note is identified in the prior art, an effective solution is not provided at present.
Disclosure of Invention
The invention mainly aims to provide a bill identification method and a bill identification device, which aim to solve the problem that the identification rate is easy to reduce when the money order with the sticky note is identified.
In order to achieve the above object, according to one aspect of the present invention, there is provided a bill discriminating method. The bill identification method comprises the following steps: acquiring an image of a bill to be identified; determining a non-pasting area of the bill in the image, wherein the non-pasting area is an area except for the pasting area in the image, and the pasting area is an area pasted with the sticky note in the image of the bill; extracting key features of the non-pasting area; and comparing the key features of the non-pasting area with preset key features.
Further, acquiring the image of the ticket includes: and illuminating the bill by using infrared light to obtain an infrared transmission image and/or an infrared reflection image of the bill. Determining a non-adhesive area of a document in an image includes: the non-pasted area is extracted from the infrared light transmission image and/or the infrared reflection image.
Alternatively, the first and second electrodes may be,
acquiring an image of a document includes: and (3) irradiating the bill by using ultraviolet light to obtain an ultraviolet transmission image and/or an ultraviolet reflection image of the bill. Determining a non-adhesive area of a document in an image includes: the non-pasted area is extracted from the ultraviolet light transmission image and/or the ultraviolet reflection image.
Further, determining a non-pasted area of the document in the image includes: sequentially acquiring the number of black pixels of each column of pixels of the image from one side of the image in a preset area of the image; respectively judging whether the number of the black pixels of each row is greater than a preset number threshold; determining columns with the number of black pixels larger than a preset number threshold value as pasting columns, wherein the pasting columns are pixel columns where pasting areas are located; determining the position and the size of a pasting area by a pasting column; and determining an area other than the pasting area in the image as a non-pasting area.
Further, comparing the key features of the non-pasting region with the preset key features comprises: searching a standard image for identifying the authenticity of the bill; and matching and calculating the key features of the non-pasting area and the corresponding key features in the standard image to obtain the matching degree of the key features.
Further, after obtaining the matching degree of the key features, the bill identifying method further includes: the authenticity of the bill is identified according to the matching degree of the key features, wherein the authenticity of the bill is identified according to the matching degree of the key features comprises the following steps: judging whether a plurality of key features of the non-pasting area are matched with corresponding key features in the standard image or not; if the plurality of key features of the non-pasting area are matched with the corresponding key features in the standard image, determining that the bill meets the requirements; and determining that the bill is not qualified if a key feature which does not match the corresponding key feature in the standard image exists in the plurality of key features of the non-pasting area.
In order to achieve the above object, according to another aspect of the present invention, there is provided a bill discriminating apparatus. The bill discriminating apparatus includes: the image acquisition unit is used for acquiring an image of a bill to be identified; the non-pasting area extraction unit is used for determining a non-pasting area of the bill in the image, wherein the non-pasting area is an area except for the pasting area in the image, and the pasting area is an area pasted with the sticky note in the image of the bill; the key feature extraction unit is used for extracting key features of the non-pasting area; and the key feature matching calculation unit is used for comparing the key features of the non-pasting area with preset key features.
Further, the image acquisition unit is used for illuminating the bill by using infrared light to obtain an infrared transmission image and/or an infrared reflection image of the bill, and the non-pasting area extraction unit is used for extracting the non-pasting area from the infrared transmission image and/or the infrared reflection image. Or the image acquisition unit is used for irradiating the bill by using ultraviolet light to obtain an ultraviolet transmission image and/or an ultraviolet reflection image of the bill, and the non-pasting area extraction unit is used for extracting the non-pasting area from the ultraviolet transmission image and/or the ultraviolet reflection image.
Further, the non-pasted region extraction unit is configured to determine the non-pasted region of the bill in the image by: sequentially acquiring the number of black pixels of each column of pixels of the image from one side of the image in a preset area of the image; respectively judging whether the number of the black pixels of each row is greater than a preset number threshold; determining columns with the number of black pixels larger than a preset number threshold value as pasting columns, wherein the pasting columns are pixel columns where pasting areas are located; determining the position and the size of a pasting area by a pasting column; an area other than the pasting area in the image is determined as a non-pasting area.
Further, the key feature matching calculation unit is configured to compare the key feature of the non-pasting region with a preset key feature by: searching a standard image for identifying the authenticity of the bill; and matching and calculating the key features of the non-pasting area and the corresponding key features in the standard image to obtain the matching degree of the key features.
Further, the key feature matching calculation unit is used for identifying the authenticity of the bill according to the matching degree of the key features in the following modes: judging whether a plurality of key features of the non-pasting area are matched with corresponding key features in the standard image or not; if the plurality of key features of the non-pasting area are matched with the corresponding key features in the standard image, determining that the bill meets the requirements; and determining that the bill is not qualified if a key feature which does not match the corresponding key feature in the standard image exists in the plurality of key features of the non-pasting area.
According to the method and the device, the authenticity of the bill is judged by using the key characteristics of the non-sticking area of the bill image, so that the problem that the identification rate is easy to reduce when the bill with the sticky note is identified is solved, and the effect of improving the accuracy of identifying the bill is achieved.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this application, illustrate embodiments of the invention and, together with the description, serve to explain the invention and not to limit the invention. In the drawings:
FIG. 1 is a schematic block diagram of a bill validator according to an embodiment of the invention;
FIG. 2 is a flow chart of a method of ticket authentication according to one embodiment of the present invention;
FIG. 3a is a schematic illustration of a visible light image of a document according to one embodiment of the present invention;
FIG. 3b is a schematic illustration of an infrared light transmitting image of a document according to one embodiment of the present invention;
FIG. 3c is a schematic illustration of an ultraviolet light reflected image of a document according to one embodiment of the present invention;
FIG. 4 is a schematic block diagram of a bill validator according to another embodiment of the invention; and
fig. 5 is a flowchart of a method of authenticating a ticket according to another embodiment of the present invention.
Detailed Description
It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict. The present invention will be described in detail below with reference to the embodiments with reference to the attached drawings.
In order to make the technical solutions better understood by those skilled in the art, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only partial embodiments of the present application, but not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
It should be noted that the terms "first," "second," and the like in the description and claims of this application and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It should be understood that the data so used may be interchanged under appropriate circumstances such that embodiments of the application described herein may be used. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
Fig. 1 is a schematic block composition diagram of a bill identifying apparatus according to an embodiment of the present invention, and as shown in the figure, the bill identifying apparatus includes an image obtaining unit 11, a non-attached region extracting unit 12, a standard image storing unit 13, a standard image extracting unit 14, a key feature extracting unit 15, and a key feature matching calculating unit 16.
The image acquiring unit 11 is configured to acquire an image of a bill, where the acquired image of the bill includes one or more of a visible light image, an infrared transmission image, an infrared reflection image, an ultraviolet transmission image, and an ultraviolet reflection image, and includes an image acquirer, such as an image sensor or a camera, for example, which illuminates the bill with various light sources to obtain an image of the bill corresponding to the light sources, such as illuminating the bill with visible light to obtain the visible light image, illuminating the bill with infrared light to obtain the infrared transmission image and/or the infrared reflection image, and illuminating the bill with ultraviolet light to obtain the ultraviolet transmission image and/or the ultraviolet reflection image.
As shown in fig. 3a, image 31 is a visible light image of a document with a partially sticky note, as shown in fig. 3b, image 41 is an infrared transmission image of a document with a partially sticky note, and as shown in fig. 3c, image 51 is an ultraviolet transmission image of a document with a partially sticky note.
The non-pasting region extracting unit 12 extracts a pasting region and a non-pasting region from the bill image, such as from an infrared transmission image and/or an infrared reflection image, or from an ultraviolet transmission image and/or an ultraviolet reflection image, according to the change of the optical characteristics after the bill is pasted with the sticky note, wherein the region pasted with the sticky note in the bill image is the pasting region, and the region outside the pasting region in the bill image is the non-pasting region. Preferably, the pasting region and the non-pasting region are extracted from the infrared transmission image and/or the infrared reflection image, as shown in fig. 3b, as seen from the infrared transmission image 41 of the bill, the brightness of the image region 43 and the image region 44 is significantly different, wherein the image region 43 with a relatively low brightness value is the pasting region, and the image region 44 with a relatively high brightness value is the non-pasting region, therefore, the infrared transmission image 41 is composed of the pasting region 43 and the non-pasting region 44; also, as shown in fig. 3a, the visible light image 31 is composed of a pasted area 33 and a non-pasted area 34, corresponding to the infrared transmission image 41; as shown in fig. 3c, the ultraviolet reflection image 51 is composed of a pasting region 53 and a non-pasting region 54, corresponding to the infrared transmission image 41.
And the standard image storage unit 13 is used for storing the standard image of the bill, and the standard image storage unit 13 can be a local storage of the bill identifying device or a storage device of a remote server networked with the bill identifying device.
And a standard image extracting unit 14 for acquiring a standard image of the bill corresponding to the bill to be authenticated from the standard image storing unit 13.
The key feature extraction unit 15 is used for processing the image of the bill acquired by the image acquisition unit 11 to acquire the key feature of the image of the bill to be identified, and processing the standard image acquired by the standard image extraction unit 14 from the standard image storage unit 13 to acquire the key feature of the standard image of the bill corresponding to the bill to be identified, wherein the key feature is a feature for identifying the authenticity of the bill, and the key feature comprises one or more combinations of a bill number, a capital writing amount, a small writing amount, a ticket dispenser seal, a revealer seal, a fiber thread, a watermark, a safety line, a bill number shading, a red water line, a theme pattern and the like.
And the key feature matching calculation unit 16 is used for performing matching calculation on the key features in the non-pasting area in the bill image and the corresponding key features in the standard image and outputting the matching value of the key features in the non-pasting area of the bill image and the corresponding key features in the standard image.
FIG. 2 is a flow diagram of a method of authenticating a document according to one embodiment of the invention, the method including the steps of:
step S20, acquiring image of the bill to be authenticated
The image acquiring unit 11 acquires an image of a bill to be authenticated, and the acquired image of the bill includes one or more of a visible light image, an infrared transmission image, an infrared reflection image, an ultraviolet transmission image, and an ultraviolet reflection image. In this embodiment, the acquired image of the bill includes five types, namely, a visible light image, an infrared transmission image, an infrared reflection image, an ultraviolet transmission image, and an ultraviolet reflection image.
Step S21, determining the non-sticking area of the bill in the image
The method comprises the steps of detecting a pasting area from an infrared transmission image boundary area by utilizing the characteristics that the gray scale of the pasting area and the gray scale of a non-pasting area in the infrared transmission image of the bill are obviously changed, the pasting area is located at the edge of the image and the like, and finally determining the position and the size of the pasting area in the image.
Preferably, the pasting region is determined in the following manner. As shown in fig. 3b, in the predetermined area of the infrared transmission image 41 of the bill, from one side of the image, for example, in the 1/3 area on the left side of the image, each column of pixels is processed from left to right, firstly, whether the pixels in the current column are black pixels is judged, wherein, the brightness threshold value is th, if the value of the pixel is less than th, the pixel is black pixel, otherwise, the pixel is white pixel; then, calculating the number of black pixels col [ x ] in each column of pixels, wherein x is the serial number of the pixel columns from the left side, such as col [0], col [1] … … col [ n ]; then, judging whether the pixel column x is a pixel column where a pasting area is located, namely a pasting column for short, wherein the threshold value of the number of black pixels is N, if col [ x ] is larger than N, the pixel column x is a pasting column, and if not, the pixel column x is a non-pasting column; and finally, determining a pasting area, wherein an area formed by all pasting columns is the pasting area, the first pasting column on the left side is the left boundary of the pasting area, and the last pasting column on the left side is the right boundary of the pasting area, so that the position and the size of the pasting area are determined. As in the infrared transmission image 41 shown in fig. 3b, the numerical value of each pixel in the pasted area 43 is smaller than the luminance threshold value th, and the numerical value of each pixel in the non-pasted area 44 is not smaller than the luminance threshold value th; the position and size of the pasting area in the other images of the bill are determined according to the position and size of the pasting area obtained from the infrared transmission image of the bill. For example, the position and size of the pasting region of the visible light image, the ultraviolet transmission image, and the ultraviolet reflection image are determined from the infrared transmission image. Since the positions and sizes of the pasting regions in the document images corresponding to the various light sources are the same, the visible light image 31 is processed according to the positions and sizes of the pasting regions 43 in the infrared transmission image 41 in fig. 3b, the region corresponding to the positions and sizes of the pasting regions 43 in the visible light image 31 is determined to be the pasting region 33 (shown in fig. 3 a) of the visible light image 31, and similarly, the ultraviolet reflection image 51 is processed according to the positions and sizes of the pasting regions 43 in the infrared transmission image 41 in fig. 3b, and the region corresponding to the positions and sizes of the pasting regions 43 in the ultraviolet reflection image 51 is determined to be the pasting region 53 of the ultraviolet reflection image 51.
Step S22, extracting key features of the non-pasting region
The key features are extracted from the non-pasted area of the document image by the key feature extraction unit 15 based on the optical characteristics of the key features. Such as extracting the ticket number, upper case amount, and lower case amount from a visible light image of the ticket; extracting a ticket number, a capital sum, a lower capital sum and a safety line from an infrared reflection image of the ticket; extracting a ticket number, a safety line and a watermark from an infrared transmission image of the ticket; extracting fiber silk, theme patterns, ticket number shading and red waterlines from the ultraviolet reflection image of the ticket; the filaments are extracted from the uv transmission image of the bill. As shown in fig. 3b, the watermark 45, security thread 46 is extracted from the non-adhesive area 44 of the ir-transmissive image 41 of the document. As shown in fig. 3c, a theme pattern 56, a ticket number shading 55, a fluorescent recognition unit 57 are extracted from the non-pasted area 54 of the ultraviolet reflection image 51 of the ticket.
Step S23, comparing the key feature of the non-pasting area with the preset key feature
In this step, the key features of the non-pasting region of the bill image may be compared with the preset key features by performing matching calculation on the key features of the non-pasting region of the bill image and the corresponding key features in the standard image.
The key feature matching calculation unit 16 performs matching calculation on the key features of the non-pasting region in the acquired bill image and the corresponding key features in the standard image to obtain a matching degree value of the key features. Because the ticket number of the ticket has uniqueness, the authenticity of the ticket can be identified by acquiring the standard image of the ticket with the same ticket number according to the ticket number of the ticket. The obtaining method is that the standard image obtaining unit 14 searches and obtains the standard image which is the same as the ticket number of the ticket from the standard image storage unit 13, wherein, the standard image storage unit 13 can be a local memory of the ticket identifying device or a storage device of a remote server networked with the ticket identifying device.
And comparing each key feature of the non-pasting area in the acquired bill image with the corresponding key feature in the standard image one by one to obtain the matching value of the key feature of the bill and the standard image.
Fig. 4 is a schematic block diagram of a bill identifying apparatus according to another embodiment of the present invention, which is different from the above embodiments in that the present embodiment further includes a bill authenticity judging unit 17 for judging whether a bill to be identified is authentic according to the key feature matching degree value output by the key feature matching calculating unit 16.
Fig. 5 is a flowchart of a bill discriminating method according to another embodiment of the present invention, which is as follows:
step S40, acquiring image of the bill to be authenticated
The same as step S20.
Step S41, determining the non-sticking area of the bill in the image
The same as step S21.
Step S42, extracting key features of the non-pasting region
The same as step S22.
Step S43, the key feature of the non-pasting area of the bill image is matched with the corresponding key feature in the standard image
The same as the matching calculation in step S23.
Step S44, judging whether all key features are matched
Judging the authenticity of the bill to be identified by the bill authenticity judging unit 17 according to the key feature matching degree value output by the key feature matching calculating unit 16, and if all the key features of the non-pasted area of the bill image are matched with the corresponding key features in the bill standard image, going to step S45; if all the key features of the non-pasted area of the bill image do not match at least one of the corresponding key features in the standard image of the bill, go to step S46.
Step S45, the bill meets the requirement
The bill is genuine.
Step S46, the bill is not in accordance with the requirement
The ticket is false, such as the current ticket is a false ticket, or a forged ticket, or a tampered ticket, etc.
The bill identification method provided by the embodiment of the invention judges the authenticity of the bill by utilizing whether all the key features of the non-pasting area of the bill image are matched with the corresponding key features in the standard bill image, eliminates the influence on bill authenticity judgment after pasting the sticky note in the pasting area, and thus improves the recognition rate of bill judgment.
It should be noted that 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 that, although a logical order is illustrated in the flowcharts, in some cases, the steps illustrated or described may be performed in an order different than presented herein.
It will be apparent to those skilled in the art that the modules or steps of the present invention described above may be implemented by a general purpose computing device, they may be centralized on a single computing device or distributed across a network of multiple computing devices, and they may alternatively be implemented by program code executable by a computing device, such that they may be stored in a storage device and executed by a computing device, or fabricated separately as individual integrated circuit modules, or fabricated as a single integrated circuit module from multiple modules or steps. Thus, the present invention is not limited to any specific combination of hardware and software.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims (10)

1. A method of authenticating a document, comprising:
acquiring an image of a bill to be identified, wherein the image of the bill comprises a visible light image and an infrared transmission image;
determining a non-pasting area of the bill in the image, wherein the non-pasting area is an area except for a pasting area in the image, and the pasting area is an area pasted with a sticky note in the image of the bill;
extracting key features of the non-pasting area; and
comparing the key features of the non-pasting area with preset key features;
detecting a pasting area from the infrared transmission image boundary area, and finally determining the position and the size of the pasting area in the image; and determining the position and the size of the pasting area in the visible light image according to the position and the size of the pasting area obtained by the infrared transmission image.
2. The bill discriminating method according to claim 1,
acquiring the image of the ticket includes: illuminating the bill with infrared light to obtain an infrared transmission image and/or an infrared reflection image of the bill,
determining a non-pasted region of the document in the image comprises: extracting the non-pasted region from the infrared light transmission image and/or the infrared reflection image,
alternatively, the first and second electrodes may be,
acquiring the image of the ticket includes: irradiating the bill by ultraviolet light to obtain an ultraviolet transmission image and/or an ultraviolet reflection image of the bill,
determining a non-pasted region of the document in the image comprises: extracting the non-pasted region from the ultraviolet light transmission image and/or the ultraviolet reflection image.
3. The document authentication method of claim 1, wherein determining the non-adhesive area of the document in the image comprises:
sequentially acquiring the number of black pixels of each column of pixels of the image from one side of the image in a preset area of the image;
respectively judging whether the number of the black pixels of each row is greater than a preset number threshold;
determining columns with the number of black pixels larger than the preset number threshold as pasting columns, wherein the pasting columns are pixel columns where the pasting areas are located; and
determining the position and the size of the pasting area by the pasting column; and
determining an area other than the pasting area in the image as the non-pasting area.
4. The method of claim 1, wherein comparing the key feature of the non-adhesive area with a predetermined key feature comprises:
searching a standard image for identifying the authenticity of the bill;
and matching and calculating the key features of the non-pasting area and the corresponding key features in the standard image to obtain the matching degree of the key features.
5. The method of claim 4, wherein after obtaining the degree of match of the key feature, the method further comprises: and identifying the authenticity of the bill according to the matching degree of the key features, wherein the identifying the authenticity of the bill according to the matching degree of the key features comprises the following steps:
judging whether the plurality of key features of the non-pasting area are all matched with the corresponding key features in the standard image;
if the plurality of key features of the non-pasting area are matched with the corresponding key features in the standard image, determining that the bill meets the requirement; and
and if the key features which do not match with the corresponding key features in the standard image exist in the key features of the non-pasting area, determining that the bill is not qualified.
6. A bill discriminating apparatus comprising:
the image acquisition unit is used for acquiring an image of a bill to be identified, wherein the image of the bill comprises a visible light image and an infrared transmission image;
a non-pasting area extracting unit, configured to determine a non-pasting area of the bill in the image, where the non-pasting area is an area other than a pasting area in the image, and the pasting area is an area to which a sticky note is pasted in the image of the bill;
a key feature extraction unit, configured to extract a key feature of the non-pasting region; and
the key feature matching calculation unit is used for comparing the key features of the non-pasting area with preset key features;
detecting a pasting area from the infrared transmission image boundary area, and finally determining the position and the size of the pasting area in the image; and determining the position and the size of the pasting area in the visible light image according to the position and the size of the pasting area obtained by the infrared transmission image.
7. The document authentication device according to claim 6,
the image acquisition unit is used for irradiating the bill by using infrared light to obtain an infrared transmission image and/or an infrared reflection image of the bill,
the non-pasting region extracting unit is configured to extract the non-pasting region from the infrared light transmission image and/or the infrared reflection image,
alternatively, the first and second electrodes may be,
the image acquisition unit is used for irradiating the bill by using ultraviolet light to obtain an ultraviolet transmission image and/or an ultraviolet reflection image of the bill,
the non-pasting region extracting unit is used for extracting the non-pasting region from the ultraviolet light transmission image and/or the ultraviolet reflection image.
8. The document authentication device according to claim 6, wherein the non-pasted region extraction unit is configured to determine the non-pasted region of the document in the image by:
sequentially acquiring the number of black pixels of each column of pixels of the image from one side of the image in a preset area of the image;
respectively judging whether the number of the black pixels of each row is greater than a preset number threshold;
determining columns with the number of black pixels larger than the preset number threshold as pasting columns, wherein the pasting columns are pixel columns where the pasting areas are located; and
determining the position and the size of the pasting area by the pasting column; and
determining an area other than the pasting area in the image as the non-pasting area.
9. The bill identifying device according to claim 6, wherein the key feature matching calculating unit is configured to compare the key feature of the non-pasting region with a preset key feature by:
searching a standard image for identifying the authenticity of the bill; and
and matching and calculating the key features of the non-pasting area and the corresponding key features in the standard image to obtain the matching degree of the key features.
10. The bill identifying device according to claim 9, wherein the key feature matching calculating unit is configured to identify the authenticity of the bill based on the matching degree of the key feature by:
judging whether the plurality of key features of the non-pasting area are all matched with the corresponding key features in the standard image;
if the plurality of key features of the non-pasting area are matched with the corresponding key features in the standard image, determining that the bill meets the requirement; and
and if the key features which do not match with the corresponding key features in the standard image exist in the key features of the non-pasting area, determining that the bill is not qualified.
CN201410834833.8A 2014-12-26 2014-12-26 Bill identification method and device Active CN105788064B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201410834833.8A CN105788064B (en) 2014-12-26 2014-12-26 Bill identification method and device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201410834833.8A CN105788064B (en) 2014-12-26 2014-12-26 Bill identification method and device

Publications (2)

Publication Number Publication Date
CN105788064A CN105788064A (en) 2016-07-20
CN105788064B true CN105788064B (en) 2020-05-12

Family

ID=56389092

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201410834833.8A Active CN105788064B (en) 2014-12-26 2014-12-26 Bill identification method and device

Country Status (1)

Country Link
CN (1) CN105788064B (en)

Families Citing this family (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108022360B (en) * 2016-10-31 2020-07-24 深圳怡化电脑股份有限公司 Method and system for identifying water-washed paper money
CN107991319B (en) * 2017-12-08 2021-03-23 伟创力电子技术(苏州)有限公司 Automatic film detection method
CN111524268B (en) * 2019-01-16 2022-08-30 深圳怡化电脑股份有限公司 Method, device and equipment for detecting paper money adhesive substance
CN111489486A (en) * 2019-01-25 2020-08-04 深圳怡化电脑股份有限公司 Method, device and equipment for detecting pasted bills and storage medium
CN110458787B (en) * 2019-08-09 2022-03-08 武汉高德智感科技有限公司 Image fusion method and device and computer storage medium
CN111546804B (en) * 2020-04-08 2021-03-23 远光软件股份有限公司 Automatic original bill pasting method and device

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101751713A (en) * 2008-12-03 2010-06-23 北京金储自动化技术研究所 Fake identification system of bank bills based on spectral image analysis
CN103208004A (en) * 2013-03-15 2013-07-17 北京英迈杰科技有限公司 Automatic recognition and extraction method and device for bill information area

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP5538202B2 (en) * 2010-12-24 2014-07-02 日立オムロンターミナルソリューションズ株式会社 Paper sheet identification device and paper sheet identification method

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101751713A (en) * 2008-12-03 2010-06-23 北京金储自动化技术研究所 Fake identification system of bank bills based on spectral image analysis
CN103208004A (en) * 2013-03-15 2013-07-17 北京英迈杰科技有限公司 Automatic recognition and extraction method and device for bill information area

Also Published As

Publication number Publication date
CN105788064A (en) 2016-07-20

Similar Documents

Publication Publication Date Title
CN105788064B (en) Bill identification method and device
CN109684987B (en) Identity verification system and method based on certificate
CN102324132B (en) Bank-note detecting method by identifying ultraviolet-light image and system
Mirza et al. Paper currency verification system based on characteristic extraction using image processing
CN107610322B (en) Banknote version identification method and device, electronic equipment and storage medium
CN104992496A (en) Paper money face identification method and apparatus
JPWO2010016144A1 (en) Paper sheet management system, paper sheet identification apparatus, paper sheet management apparatus, paper sheet management method, and paper sheet management program
CN108320373B (en) Method and device for detecting anti-counterfeiting mark of paper money
CN104916029A (en) Paper money verification system and paper money verification method based on system
CN107180479A (en) A kind of bill discrimination method, device, equipment and storage medium
Murthy et al. Design and implementation of paper currency recognition with counterfeit detection
US20210264583A1 (en) Detecting identification tampering using ultra-violet imaging
CN108510639B (en) Paper money counterfeit discriminating method and device, currency detector and storage medium
CN105741404B (en) The discrimination method of bill, device and system
CN107134047A (en) White watermark detection method and device
KR101707218B1 (en) Smartphone linked counterfeit discrimination apparatus and method
WO2017024779A1 (en) Material anti-counterfeiting method and material anti-counterfeiting system
CN107527423B (en) Paper money anti-counterfeiting identification method and paper money identification device
CN106340115B (en) Method and device for identifying serial number of paper money
Amirsab et al. An automated recognition of fake or destroyed Indian currency notes
CN109543554B (en) Bill detection method, device, terminal and computer readable storage medium
CN106447908A (en) Paper money authentic identification method and device
KR101812206B1 (en) Counterfeit discrimnation and tracking system and method performing thereof
US7889885B2 (en) Method for detecting perforations on the edge of an image of a form
CN109800745B (en) Bill detection method, device, terminal and computer readable storage medium

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant