CN102142168A - High-speed and high-resolution number collecting device of banknote sorting machine and identification method - Google Patents
High-speed and high-resolution number collecting device of banknote sorting machine and identification method Download PDFInfo
- Publication number
- CN102142168A CN102142168A CN2011100075019A CN201110007501A CN102142168A CN 102142168 A CN102142168 A CN 102142168A CN 2011100075019 A CN2011100075019 A CN 2011100075019A CN 201110007501 A CN201110007501 A CN 201110007501A CN 102142168 A CN102142168 A CN 102142168A
- Authority
- CN
- China
- Prior art keywords
- chip
- paper money
- programmable logic
- image sensor
- type image
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Landscapes
- Inspection Of Paper Currency And Valuable Securities (AREA)
- Image Analysis (AREA)
Abstract
The invention provides a high-speed and high-resolution number collecting device of a banknote sorting machine and an identification method. The high-speed and high-resolution number collecting device of the banknote sorting machine comprises image sensors, a multichannel A/D (analog to digital) converter chip, a programmable logic chip, a digital signal processor chip, a dynamic memory chip and a communication structure chip, wherein the image sensors are respectively connected with the multichannel A/D converter chip, the multichannel A/D converter chip is connected with the programmable logic chip, and the programmable logic chip is respectively connected with the digital signal processor chip and the dynamic memory chip. The invention realizes the high-resolution collection to banknote images under the condition of high-speed operation of the banknotes. The contact type image sensors have the advantages of low cost, small volume and low requirements for light source performance. Positioning and cutting thresholds are not needed to be set in the identification method of banknote numbers, so that an accurate positioning and cutting position and ideal identification results can be obtained when the banknotes are depreciated and polluted.
Description
(1) technical field
The present invention relates to image processing techniques, is exactly a kind of paper currency sorter high speed, high resolution number harvester and recognition methods thereof specifically.
(2) background technology
Existing paper currency sorter number harvester is divided into two classes, one class is to use the CCD array image sensor to gather the number of paper money area image, device requires high to the CCD number of shots, as 201001044234.2 patent disclosures are devices of eight CCD camera lenses of a kind of needs, on the bank note both direction, gather the image in four zones respectively, these four zones can not cover all images of bank note, and the number position is determined in these four zones of algorithm search.When the number area part in two adjacent areas the time, need be with number zone splicing, the method intractability is big, causes recognition accuracy undesirable.In addition, adopt ccd image sensor, to light source performance requirement height, the object distance distance is big, thereby causes equipment volume bigger, and moulding is not attractive in appearance.Another kind of is to be suitable for contact-type image sensor (CIS) to gather banknote image, and use digital signal processor (DSP) to discern number of paper money, the scheme that provides as ZL200610155872.0 and 20100104848.0 patents, these class methods are because the constraint of contact-type image sensor minimum value integral time is restricted the bank note travelling speed.In addition, the contact-type image sensor image quality is poor, and existing number of paper money location, dividing method can not obtain accurate in locating, split position, thereby cause obtaining desirable number of paper money recognition effect when bank note generation depreciation and pollution.
(3) summary of the invention
The object of the present invention is to provide that a kind of cost is low, volume is little, paper currency sorter high speed, high resolution number harvester and the recognition methods thereof not high to the light source performance requirement.
The object of the present invention is achieved like this:
Described paper currency sorter high speed, high resolution number harvester, it is by first contact-type image sensor, second contact-type image sensor, the multipath A/D converter chip, programmable logic chip, DSP chip, dynamic ram chip and communication structure chip are formed, first contact-type image sensor, second contact-type image sensor is connected with the multipath A/D converter chip respectively, the multipath A/D converter chip connects programmable logic chip, programmable logic chip connects DSP chip and dynamic ram chip respectively, and DSP chip connects the communication structure chip.
The described recognition methods that realizes by paper currency sorter high speed, high resolution number harvester: utilize the priori of the average height of number of paper money as number of paper money horizontal level location; The moving window position of adding up and obtaining minimum value that utilizes number of paper money image level projection sequence in the moving window is as number of paper money horizontal location coordinate, the width of moving window utilizes the priori of the mean breadth of number of paper money as vertical segmentation by the priori decision of the average height of utilizing number of paper money as number of paper money horizontal level location; Number of paper money vertical direction projection sequence is added up and as objective function, it is optimized vertical segmentation position that this objective function is obtained peaked split position in the brightness of cutting apart the vertical segmentation position; In the horizontal location of each number of paper money and vertical segmentation zone, carry out binary conversion treatment, carry out normalized then, use three layers of error anti-pass type artificial neural network that number of paper money is discerned at last.
Paper currency sorter high speed, high resolution number harvester of the present invention can realize that bank note is under the high-speed cruising situation, banknote image is carried out high-resolution acquisition, and the imageing sensor that is adopted is a contact-type image sensor, and its cost is low, volume is little, and is not high to the light source performance requirement.Paper currency number identification method does not need to set location and segmentation threshold, can obtain accurate in locating and split position and desirable recognition result in bank note generation depreciation with when being subjected to polluting yet.
(4) description of drawings
Fig. 1 is a structural representation of the present invention;
Fig. 2 is programmable logic chip internal storage tissue of the present invention and control synoptic diagram;
Fig. 3 is data of the present invention and control signal sequential chart;
Fig. 4 is a horizontal location position view of the present invention;
Fig. 5 is a horizontal location moving window moving process synoptic diagram of the present invention;
Fig. 6 is a vertical segmentation searching process synoptic diagram of the present invention.
(5) embodiment
The invention will be further described for example below in conjunction with accompanying drawing.
Embodiment 1: in conjunction with Fig. 1, a kind of paper currency sorter high speed, high resolution of the present invention number harvester, it is by first contact-type image sensor (1), second contact-type image sensor (2), multipath A/D converter chip (3), programmable logic chip (4), DSP chip (5), dynamic ram chip (6) and communication structure chip (7) are formed, first contact-type image sensor (1), second contact-type image sensor (2) is connected with multipath A/D converter chip (3) respectively, multipath A/D converter chip (3) connects programmable logic chip (4), programmable logic chip (4) connects DSP chip (5) and dynamic ram chip (6) respectively, and DSP chip (5) connects communication structure chip (7).
The recognition methods that is realized by paper currency sorter high speed, high resolution number harvester is: utilize the priori of the average height of number of paper money as number of paper money horizontal level location; The moving window position of adding up and obtaining minimum value that utilizes number of paper money image level projection sequence in the moving window is as number of paper money horizontal location coordinate, the width of moving window utilizes the priori of the mean breadth of number of paper money as vertical segmentation by the priori decision of the average height of utilizing number of paper money as number of paper money horizontal level location; Number of paper money vertical direction projection sequence is added up and as objective function, it is optimized vertical segmentation position that this objective function is obtained peaked split position in the brightness of cutting apart the vertical segmentation position; In the horizontal location of each number of paper money and vertical segmentation zone, carry out binary conversion treatment, carry out normalized then, use three layers of error anti-pass type artificial neural network that number of paper money is discerned at last.
Embodiment 2: in conjunction with Fig. 1, described paper currency sorter high speed, high resolution number harvester comprises first and second contact-type image sensors, hyperchannel modulus conversion chip, programmable logic chip, dynamic ram chip, DSP chip and communication interface chip.First and second contact-type image sensors are connected with programmable logic chip with the hyperchannel modulus conversion chip respectively, programmable logic chip is connected with hyperchannel modulus conversion chip, DSP chip, dynamic ram chip respectively, and DSP chip is connected with communication interface chip; Described hyperchannel modulus conversion chip is the AD9822 chip, programmable logic chip is an Xilinx FPGA XC3S200 chip, DSP chip TITMS320C6000 family chip, dynamic ram chip are the MT48LC16M16A2 chip, and communication interface chip is the MAX232A chip.Described high speed, high resolution number of paper money image collecting device is finished its process control by programmable logic chip, and programmable logic chip control modulus conversion chip and DSP chip make the complete executed in parallel of number of paper money collection and data transmission.The institutional framework of image line storer is " table tennis " structure in the sheet of programmable logic chip, does not need to set aside some time between two row image acquisition and finishes DSP chip to the data read in the programmable logic chip on-chip memory.Finishing pre-service in numerical processor chip after, high resolving power number of paper money image is saved in the dynamic ram chip.According to the bank note face amount, towards recognition result, the image in number of paper money zone is read the internal storage of DSP chip from dynamic ram chip, by digital signal processor number of paper money is positioned, cuts apart and discerns.
The described recognition methods that realizes by paper currency sorter high speed, high resolution number harvester, comprise optimization number of paper money location and dividing method and number identification method, utilize the priori of the average height of number of paper money as number of paper money horizontal level location.The moving window position of adding up and obtaining minimum value that utilizes number of paper money image level projection sequence in the moving window is as number of paper money horizontal location coordinate, and the width of moving window is by the priori decision of the average height of utilizing number of paper money as number of paper money horizontal level location.Utilize the priori of the mean breadth of number of paper money as vertical segmentation.Number of paper money vertical direction projection sequence is added up and as objective function, it is optimized vertical segmentation position that this objective function is obtained peaked split position in the brightness of cutting apart the vertical segmentation position.In the horizontal location of each number of paper money and vertical segmentation zone, carry out binary conversion treatment, carry out normalized then, use three layers of error anti-pass type artificial neural network that number of paper money is discerned at last.
Embodiment 3: in conjunction with Fig. 1--Fig. 6, paper currency sorter high speed, high resolution number harvester comprises first and second contact-type image sensors (CIS), multipath A/D converter chip, programmable logic chip, DSP chip, dynamic ram chip and communication structure chip.Two contact-type image sensors that are staggeredly placed can be gathered on the bank note simultaneously, the image of following both sides, and wherein at least one side image comprises the number of paper money zone; The analog to digital converter chip is with the output voltage signal conversion position digital signal of two contact-type image sensors, as the input signal of programmable logic chip; Programmable logic chip is finished under the situation of paper currency high-speed operation, makes image acquisition and the view data data transmission executed in parallel between programmable logic chip and DSP chip, obtains high-definition picture; Dynamic ram chip is used to preserve the complete high resolving power banknote image that comprises the number of paper money area image; Communication chip sends to the number of paper money recognition result host computer of cleaning-sorting machine system.The internal storage tissue of programmable logic chip can be realized the high speed, high resolution collection of number of paper money image.This internal storage institutional framework is " table tennis " structure, by two isometric dual-port on-chip memories, and three groups of logic switches, modules such as front end address generator and control-signals generator are formed.Its control procedure is as follows:
1) at 2n contact-type image sensor due in integral time, FPGA (Field Programmable Gate Array) is controlled the output data line that its internal logic switch SW 1 is connected the front end data line of internal storage A analog to digital converter, the front end address generator is that internal storage A produces address signal in proper order according to the sequential of contact-type image sensor data output, the banknote image data of preserving the contact-type image sensor collection are in internal storage A, n=0,1,2, L.
2) produce look-at-me to digital signal processor simultaneously, and control internal logic switch SW 2 is connected with the data bus of DSP chip the data line of internal storage B respectively with address wire respectively with SW3 with address bus; Digital signal processor detects after the look-at-me and reads the banknote image data that 2n-1 gathers constantly among the internal storage B from programmable logic chip.
3) at 2n+1 contact-type image sensor due in integral time, FPGA (Field Programmable Gate Array) is controlled the output data line that its internal logic switch SW 1 is connected the front end data line of internal storage B analog to digital converter, the front end address generator is that internal storage B produces address signal in proper order according to the sequential of contact-type image sensor data output, and the banknote image data of preserving the contact-type image sensor collection are in internal storage B.
4) produce look-at-me to digital signal processor simultaneously, and control internal logic switch SW 2 is connected with the data bus of DSP chip the data line of internal storage A respectively with address wire respectively with SW3 with address bus; Digital signal processor detects after the look-at-me and reads the banknote image data that 2n gathers constantly among the internal storage A from programmable logic chip.
5) circulation carries out 1)-4) step, up to gathering a complete banknote image.
As shown in Figure 3, programmable logic chip " table tennis " institutional framework by internal storage can realize that banknote image data acquisition and data transmit complete executed in parallel between programmable logic chip and digital signal processing chip.Banknote image harvester of the present invention has improved the speed of bank note operation to greatest extent, and realized under the contact-type image sensor constraint of integral time obtaining the banknote image of highest resolution, for the number of paper money location, cut apart and identification provides the good data basis.
Because high resolving power banknote image data volume is bigger, can not preserve in the on-chip memory of DSP chip, so the high resolving power banknote image is stored in the outer chip dynamic memory.When digital signal processor finish bank note face amount, towards identification after, digital signal processor is with this face amount, read from outer chip dynamic memory in the on-chip memory towards the number of paper money of correspondence zone topography, be used for number of paper money the location, cut apart and discern.
In the described paper currency number identification method number of paper money horizontal location method as shown in Figure 4 and Figure 5, its process is:
1) with the projection in the horizontal direction of each pixel of number of paper money area image.Brighter pixel has bigger brightness value, and the pixel on the number of paper money is darker, effectively little brightness value.The height of supposing the number of paper money area image is H, and the prior estimate of the average height of number of paper money is h, and deviation is Δ h, as shown in Figure 4.It is the integer sequence P of H that the horizontal projection value of number of paper money area image forms length
1={ p
1(0), p
1(1), L, p
1(H-1) }.
2) be that the window of h+2 Δ h is at horizontal projection sequence P with width
1={ p
1(0), p
1(1), L, p
1(H-1) } go up slip, move a position, as shown in Figure 5 at every turn.
3) calculate horizontal projection sequence P in the each mobile rear hatch of moving window
1={ p
1(0), p
1(1), L, p
1(H-1) } part and, be designated as s respectively
1(0), s
1(1), L, s
1(k), L, wherein s
1(k), k ∈ 0,1, L} is calculated by following formula:
4) at sequence S
1={ s
1(0), s
1(1), L, s
1(k), search for minimum value among the L}, it is the position, coboundary of horizontal location to deserved sequence number, promptly
The position, coboundary of its horizontal location is l
Down=l
Up+ h+2 Δ h
In the described paper money recognition method number of paper money vertical direction dividing method as shown in Figure 6, its process is:
1) at number of paper money horizontal location up-and-down boundary [l
Up, l
Down] between, the number of paper money image is carried out vertical projection, suppose that number of paper money area image width is W, then can obtain length is the vertical projection value sequence P of W
2={ p
2(0), p
2(1), L, p
2(W-1) }.
2) from left side, number of paper money zone, search sequence P to the right
2={ p
2(0), p
2(1), L, p
2(W-1) } descending first sudden change position is designated as l0, the initial position that this position is cut apart as first number left margin in.
3) prior estimate of establishing the number of paper money mean breadth is w, and the prior estimate of mean distance is 2 Δ w between two adjacent numbers, as shown in Figure 6, and search vertical projection subsequence { p
2(l
0+ w), p
2(l
0+ w+1), L, p
2(l
0+ w+2 Δ w) } the maximal value corresponding sequence number in is designated as l as first number right margin split position
1, l
1Calculate by following formula:
4) with l
1As the split position of second number left margin, search vertical projection subsequence { p
2(l
1+ w), p
2(l
1+ w+1), L, p
2(l
1+ w+2 Δ w) } the maximal value corresponding sequence number in is designated as l as first number right margin split position
2l
2It also is the left margin split position of the 3rd number.
5) use and 4) identical method can obtain the split position on the border, the left and right sides of all numbers, and the numerical value of these positions is calculated by following formula:
6) establish total M the number of bank note, calculate the brightness of above-mentioned split position vertical projection with, be designated as
7) precision of above-mentioned dividing method depends on initial segmentation position l
0, for improving segmentation precision, with initial segmentation position l
0At interval [l
0-Δ w, l
0+ Δ w] interior moving.Whenever move once, with above-mentioned 3), 4), 5) and method calculates a component and cuts the position
The number of times that moves for the initial segmentation position of i wherein, and with 6) described method calculate corresponding segmentation result vertical projection brightness and, be designated as
8) get sequence
The split position of middle maximal value correspondence
As final segmentation result, wherein k satisfies following formula:
Split position brightness and maximum in the number of paper money zone that described number of paper money location, dividing method are determined, even the number of paper money zone depreciation takes place or polluted, the inventive method also can obtain optimized location, split position.
Described paper currency number identification method is:
1) each number zone of bank note is by up-and-down boundary l
Up, l
DownWith left and right sides split position
Decision, top left corner apex that this is regional and lower right corner apex coordinate are respectively
With
2) image of checking numbers in this zone carries out binary conversion treatment.
3) in the binaryzation result images, tighten up up and down and border, the left and right sides, promptly from top to bottom, first stain is position, coboundary l '
Up, from top to bottom, first stain is lower boundary position l '
Down, from left to right, first stain is left margin position l '
i, from right to left, first stain is right margin position l '
I+1
4) be respectively at top left corner apex and lower right corner apex coordinate (l '
i, l '
Up) and (l '
I+1, l '
Down) the zone in, carry out normalized with two-wire shape interpolation method.
5) with three layers of error anti-pass type artificial neural network each number is discerned.
Claims (2)
1. paper currency sorter high speed, high resolution number harvester, it is by first contact-type image sensor (1), second contact-type image sensor (2), multipath A/D converter chip (3), programmable logic chip (4), DSP chip (5), dynamic ram chip (6) and communication structure chip (7) are formed, it is characterized in that: first contact-type image sensor (1), second contact-type image sensor (2) is connected with multipath A/D converter chip (3) respectively, multipath A/D converter chip (3) connects programmable logic chip (4), programmable logic chip (4) connects DSP chip (5) and dynamic ram chip (6) respectively, and DSP chip (5) connects communication structure chip (7).
2. recognition methods that is realized by the described paper currency sorter high speed, high resolution of claim 1 number harvester is characterized in that: utilize the priori of the average height of number of paper money as number of paper money horizontal level location; The moving window position of adding up and obtaining minimum value that utilizes number of paper money image level projection sequence in the moving window is as number of paper money horizontal location coordinate, the width of moving window utilizes the priori of the mean breadth of number of paper money as vertical segmentation by the priori decision of the average height of utilizing number of paper money as number of paper money horizontal level location; Number of paper money vertical direction projection sequence is added up and as objective function, it is optimized vertical segmentation position that this objective function is obtained peaked split position in the brightness of cutting apart the vertical segmentation position; In the horizontal location of each number of paper money and vertical segmentation zone, carry out binary conversion treatment, carry out normalized then, use three layers of error anti-pass type artificial neural network that number of paper money is discerned at last.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2011100075019A CN102142168A (en) | 2011-01-14 | 2011-01-14 | High-speed and high-resolution number collecting device of banknote sorting machine and identification method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2011100075019A CN102142168A (en) | 2011-01-14 | 2011-01-14 | High-speed and high-resolution number collecting device of banknote sorting machine and identification method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN102142168A true CN102142168A (en) | 2011-08-03 |
Family
ID=44409646
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2011100075019A Pending CN102142168A (en) | 2011-01-14 | 2011-01-14 | High-speed and high-resolution number collecting device of banknote sorting machine and identification method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102142168A (en) |
Cited By (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102324133A (en) * | 2011-08-10 | 2012-01-18 | 深圳市怡化电脑有限公司 | Contact image sensor module for banknote recognition |
| CN102842168A (en) * | 2012-09-06 | 2012-12-26 | 上海古鳌电子科技股份有限公司 | Image processing device |
| CN103310528A (en) * | 2013-07-08 | 2013-09-18 | 广州广电运通金融电子股份有限公司 | Image compensation and correction method and banknote detection and identification device |
| WO2014023109A1 (en) * | 2012-08-09 | 2014-02-13 | 广州广电运通金融电子股份有限公司 | Image identification system and image storage control method |
| CN103971451A (en) * | 2014-04-24 | 2014-08-06 | 中国人民银行印制科学技术研究所 | Securities checking and packaging method |
| CN105184290A (en) * | 2015-08-25 | 2015-12-23 | 深圳怡化电脑股份有限公司 | Target region extraction method and system |
| CN105447826A (en) * | 2015-11-06 | 2016-03-30 | 东方通信股份有限公司 | Banknote image acquisition processing method |
| CN105957238A (en) * | 2016-05-20 | 2016-09-21 | 聚龙股份有限公司 | Banknote management method and system |
| CN106056751A (en) * | 2016-05-20 | 2016-10-26 | 聚龙股份有限公司 | Prefix number identification method and system |
| CN106447907A (en) * | 2016-09-18 | 2017-02-22 | 深圳怡化电脑股份有限公司 | Method and device for detecting banknote image abnormity |
| CN106447910A (en) * | 2016-09-08 | 2017-02-22 | 深圳怡化电脑股份有限公司 | Paper money identifying method and apparatus |
| CN106658860A (en) * | 2017-01-11 | 2017-05-10 | 深圳怡化电脑股份有限公司 | Light source drive control circuit and method of image sensor |
| CN106874909A (en) * | 2017-01-18 | 2017-06-20 | 深圳怡化电脑股份有限公司 | A kind of recognition methods of image character and its device |
| CN107085885A (en) * | 2017-03-22 | 2017-08-22 | 深圳怡化电脑股份有限公司 | A kind of acquisition method, storage method and its device of currency examination data |
| CN107622562A (en) * | 2017-09-11 | 2018-01-23 | 深圳怡化电脑股份有限公司 | Extracting method, device, equipment and the storage medium of banknote image |
| CN108665606A (en) * | 2017-03-30 | 2018-10-16 | 深圳怡化电脑股份有限公司 | A kind of recognition methods of bank note Information and device |
| CN111768565A (en) * | 2020-05-21 | 2020-10-13 | 程功勋 | Method for identifying and post-processing invoice codes in value-added tax invoices |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1517940A (en) * | 2003-01-08 | 2004-08-04 | ���ٹ�ҵ��ʽ���� | Paper monery recording number reading device and paper money recording number reading method |
| CN201465141U (en) * | 2009-07-21 | 2010-05-12 | 刘冬梅 | Device for distinguishing and recording serial member of RMB (Renminbi) |
| CN101833660A (en) * | 2010-01-20 | 2010-09-15 | 上海古鳌电子机械有限公司 | Number identification system of paper money sorter and control method thereof |
-
2011
- 2011-01-14 CN CN2011100075019A patent/CN102142168A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1517940A (en) * | 2003-01-08 | 2004-08-04 | ���ٹ�ҵ��ʽ���� | Paper monery recording number reading device and paper money recording number reading method |
| CN201465141U (en) * | 2009-07-21 | 2010-05-12 | 刘冬梅 | Device for distinguishing and recording serial member of RMB (Renminbi) |
| CN101833660A (en) * | 2010-01-20 | 2010-09-15 | 上海古鳌电子机械有限公司 | Number identification system of paper money sorter and control method thereof |
Non-Patent Citations (1)
| Title |
|---|
| 金野: "纸币图像分析理解技术及其应用", 《中国博士学位论文全文数据库（电子期刊）》 * |
Cited By (29)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102324133A (en) * | 2011-08-10 | 2012-01-18 | 深圳市怡化电脑有限公司 | Contact image sensor module for banknote recognition |
| WO2014023109A1 (en) * | 2012-08-09 | 2014-02-13 | 广州广电运通金融电子股份有限公司 | Image identification system and image storage control method |
| US9838598B2 (en) | 2012-08-09 | 2017-12-05 | Grg Banking Equipment Co., Ltd. | Image identification system and image storage control method |
| CN102842168A (en) * | 2012-09-06 | 2012-12-26 | 上海古鳌电子科技股份有限公司 | Image processing device |
| US9685022B2 (en) | 2013-07-08 | 2017-06-20 | Grg Banking Equipment Co., Ltd. | Image compensation correction method and banknote recognition and detection device |
| CN103310528A (en) * | 2013-07-08 | 2013-09-18 | 广州广电运通金融电子股份有限公司 | Image compensation and correction method and banknote detection and identification device |
| CN103310528B (en) * | 2013-07-08 | 2016-08-17 | 广州广电运通金融电子股份有限公司 | Image compensation modification method and identification banknote tester |
| CN103971451A (en) * | 2014-04-24 | 2014-08-06 | 中国人民银行印制科学技术研究所 | Securities checking and packaging method |
| CN105184290A (en) * | 2015-08-25 | 2015-12-23 | 深圳怡化电脑股份有限公司 | Target region extraction method and system |
| CN105184290B (en) * | 2015-08-25 | 2021-04-16 | 深圳怡化电脑股份有限公司 | Target area extraction method and system |
| CN105447826A (en) * | 2015-11-06 | 2016-03-30 | 东方通信股份有限公司 | Banknote image acquisition processing method |
| CN105447826B (en) * | 2015-11-06 | 2018-09-07 | 东方通信股份有限公司 | A kind of processing method of banknote image acquisition |
| CN105957238B (en) * | 2016-05-20 | 2019-02-19 | 聚龙股份有限公司 | A kind of paper currency management method and its system |
| CN105957238A (en) * | 2016-05-20 | 2016-09-21 | 聚龙股份有限公司 | Banknote management method and system |
| US10930105B2 (en) | 2016-05-20 | 2021-02-23 | Julong Co., Ltd. | Banknote management method and system |
| CN106056751A (en) * | 2016-05-20 | 2016-10-26 | 聚龙股份有限公司 | Prefix number identification method and system |
| CN106056751B (en) * | 2016-05-20 | 2019-04-12 | 聚龙股份有限公司 | The recognition methods and system of serial number |
| CN106447910A (en) * | 2016-09-08 | 2017-02-22 | 深圳怡化电脑股份有限公司 | Paper money identifying method and apparatus |
| CN106447910B (en) * | 2016-09-08 | 2019-07-05 | 深圳怡化电脑股份有限公司 | A kind of method and device of paper money recognition |
| CN106447907B (en) * | 2016-09-18 | 2019-04-26 | 深圳怡化电脑股份有限公司 | A kind of detection method and device of banknote image abnormity |
| CN106447907A (en) * | 2016-09-18 | 2017-02-22 | 深圳怡化电脑股份有限公司 | Method and device for detecting banknote image abnormity |
| CN106658860A (en) * | 2017-01-11 | 2017-05-10 | 深圳怡化电脑股份有限公司 | Light source drive control circuit and method of image sensor |
| CN106658860B (en) * | 2017-01-11 | 2018-09-11 | 深圳怡化电脑股份有限公司 | A kind of the light source drive control circuit and method of imaging sensor |
| CN106874909B (en) * | 2017-01-18 | 2019-10-11 | 深圳怡化电脑股份有限公司 | A kind of recognition methods of image character and its device |
| CN106874909A (en) * | 2017-01-18 | 2017-06-20 | 深圳怡化电脑股份有限公司 | A kind of recognition methods of image character and its device |
| CN107085885A (en) * | 2017-03-22 | 2017-08-22 | 深圳怡化电脑股份有限公司 | A kind of acquisition method, storage method and its device of currency examination data |
| CN108665606A (en) * | 2017-03-30 | 2018-10-16 | 深圳怡化电脑股份有限公司 | A kind of recognition methods of bank note Information and device |
| CN107622562A (en) * | 2017-09-11 | 2018-01-23 | 深圳怡化电脑股份有限公司 | Extracting method, device, equipment and the storage medium of banknote image |
| CN111768565A (en) * | 2020-05-21 | 2020-10-13 | 程功勋 | Method for identifying and post-processing invoice codes in value-added tax invoices |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102142168A (en) | High-speed and high-resolution number collecting device of banknote sorting machine and identification method | |
| CN113643289B (en) | Fabric surface defect detection method and system based on image processing | |
| CN103345631B (en) | Image characteristics extraction, training, detection method and module, device, system | |
| CN110322453A (en) | 3D point cloud semantic segmentation method based on position attention and auxiliary network | |
| CN104598915A (en) | Gesture recognition method and gesture recognition device | |
| US9928677B2 (en) | Banknote recognition method based on sorter dust accumulation and sorter | |
| CN108205667A (en) | Method for detecting lane lines and device, lane detection terminal, storage medium | |
| CN104899853A (en) | Image region dividing method and device | |
| CN101676930A (en) | Method and device for recognizing table cells in scanned image | |
| CN113160062B (en) | Infrared image target detection method, device, equipment and storage medium | |
| CN105046197A (en) | Multi-template pedestrian detection method based on cluster | |
| CN104715490A (en) | Navel orange image segmenting method based on adaptive step size harmony search algorithm | |
| CN103337072A (en) | Texture and geometric attribute combined model based indoor target analytic method | |
| CN110472634A (en) | Change detecting method based on multiple dimensioned depth characteristic difference converged network | |
| CN102043959A (en) | License plate character segmentation method | |
| CN106022346A (en) | Banknote number cutting method and device | |
| CN106157323A (en) | The insulator division and extracting method that a kind of dynamic division threshold value and block search combine | |
| CN206058228U (en) | Machine Vision Inspecting System | |
| CN113223027A (en) | Immature persimmon segmentation method and system based on PolarMask | |
| CN105513066A (en) | General object detection method based on seed point selection and super pixel fusion | |
| CN106558053A (en) | Object segmentation methods and Object Segmentation device | |
| CN103279752A (en) | Eye locating method based on improved Adaboost algorithm and human face geometrical characteristics | |
| CN104537342A (en) | Quick lane line detection method combined with ridge boundary detection and Hough transformation | |
| CN105427287A (en) | Projection transformation-based connected region marking method | |
| CN105303200A (en) | Human face identification method for handheld device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C02 | Deemed withdrawal of patent application after publication (patent law 2001) | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20110803 |