CN106548202A - Note denomination recognition methodss and system - Google Patents
Note denomination recognition methodss and system Download PDFInfo
- Publication number
- CN106548202A CN106548202A CN201610942284.5A CN201610942284A CN106548202A CN 106548202 A CN106548202 A CN 106548202A CN 201610942284 A CN201610942284 A CN 201610942284A CN 106548202 A CN106548202 A CN 106548202A
- Authority
- CN
- China
- Prior art keywords
- money
- bank note
- image
- value
- interest
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- 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
- G06V10/24—Aligning, centring, orientation detection or correction of the image
- G06V10/242—Aligning, centring, orientation detection or correction of the image by image rotation, e.g. by 90 degrees
-
- 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
- G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/50—Extraction of image or video features by performing operations within image blocks; by using histograms, e.g. histogram of oriented gradients [HoG]; by summing image-intensity values; Projection analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/46—Descriptors for shape, contour or point-related descriptors, e.g. scale invariant feature transform [SIFT] or bags of words [BoW]; Salient regional features
- G06V10/467—Encoded features or binary features, e.g. local binary patterns [LBP]
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Multimedia (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Inspection Of Paper Currency And Valuable Securities (AREA)
- Image Analysis (AREA)
Abstract
The invention provides a kind of note denomination recognition methodss and system, are related to value of money technology of identification field.The method includes:Banknote image is obtained, and the topography in banknote image is intercepted according to predeterminated position;Region of interest area image in identification topography;In the grader of the area-of-interest image information for including various value of money bank note that region of interest area image is input into training in advance, and export the value of money of bank note.The present invention by bank note towards image overturn, it is ensured that bank note reduces the model number of classification towards positive for front or reverse side is positive, improves the accuracy that the training stage trains;By extracting histogram feature so that similar value of money paper money recognition pattern difference is little, and the recognition mode difference of inhomogeneity value of money bank note is big, you can quickly and accurately recognize the value of money of bank note.
Description
Technical field
The invention belongs to value of money technology of identification field, more particularly to a kind of note denomination recognition methodss and system.
Background technology
Indonesia's shield is the legal tender of Indonesia, and which is encoded to IDR.By the printed distribution of Yin Chao factories of country of Indonesia
Indonesia Rupiah (Rp), is one of several currency of value of money minimum in circulation worldwide currency.Different bank note include that Indonesia Rupiah (Rp) has four
It is individual towards be respectively:Front is positive, front is swung to, reverse side is positive and reverse side is swung to.
Indonesia Rupiah (Rp) has 5,000,10,000,20,000,50,000,100,000 in the value of money that permanent current on the market leads to now.And on its different value of money
The dimension information of image be more or less the same, it is difficult to the size of value of money is judged by dimension information.
The problems referred to above are urgently to be resolved hurrily.
The content of the invention
Be more or less the same for the dimension information of image on present Indonesia Rupiah (Rp) difference value of money, it is difficult to by dimension information come
Judge the defect of the size of value of money, the present invention provides a kind of note denomination recognition methodss and system.
On the one hand, the present invention provides a kind of note denomination recognition methodss, including:
Banknote image to be identified is obtained, and the topography in the banknote image is intercepted according to predeterminated position;
Recognize the region of interest area image in the topography;
The region of interest area image is input into into the region of interest area image for including various value of money bank note of training in advance
In the grader of information, and export the value of money of the bank note.
Preferably, it is described to obtain banknote image to be identified, and the local in the banknote image is intercepted according to predeterminated position
Also include before image:
The various area-of-interest image informations for including value of money bank note are obtained using convolutional neural networks classifier training,
And the area-of-interest image information of the various value of money bank note is stored to the grader.
Preferably, to obtain the various senses for including various value of money bank note emerging for the employing convolutional neural networks classifier training
Interesting regional image information, and the area-of-interest image information of the value of money bank note is stored to the grader specifically include:
The banknote image to be measured of various values of money is obtained, treating in the banknote image to be measured is extracted according to the predeterminated position
Survey topography;
The region of interest area image to be measured in the topography to be measured corresponding to various values of money is identified respectively;
Every kind of value of money is chosen the sample of preset data and repeats above-mentioned two step, obtains sample data;
Sample data input is rolled in neural network classifier and is trained, obtain the to be measured of various value of money bank note
Area-of-interest image information.
Preferably, the banknote image to be measured for obtaining various values of money, extracts the paper to be measured according to the predeterminated position
Also include before topography to be measured on coin image:
The bank note is overturn, makes the bank note keep positive.
Preferably, the area-of-interest image information is that the topography is straight under local binarization image model
Square figure feature.
On the other hand, the present invention also provides a kind of note denomination identifying system, including:
Acquisition module, for obtaining banknote image to be identified, and intercepts the office in the banknote image according to predeterminated position
Portion's image;
Identification module, for recognizing the region of interest area image in the topography;
Output module, for the region of interest area image to be input into the sense for including various value of money bank note of training in advance
In the grader of interest regional image information, and export the value of money of the bank note.
Preferably, the system also includes:
Training module, for obtaining the various senses for including various value of money bank note using convolutional neural networks classifier training
Interest regional image information, and the area-of-interest image information of the value of money bank note is stored to the grader.
Preferably, the training module is specifically included:
Acquiring unit, for obtaining the banknote image to be measured of value of money, extracts the bank note to be measured according to the predeterminated position
Topography to be measured on image;
Recognition unit, for identifying the area-of-interest to be measured in the topography to be measured corresponding to various values of money respectively
Image;
Unit is repeated, the sample for every kind of value of money to be chosen preset data repeats above-mentioned two step, obtains
To sample data;
Training unit, is trained for sample data input is rolled in neural network classifier, obtains various
The area-of-interest image information to be measured of value of money bank note.
Preferably, the training module also includes:
Roll-over unit, for overturning the bank note, makes the bank note keep positive.
Preferably, the area-of-interest image information is that the topography is straight under local binarization image model
Square figure feature.
Beneficial effect:The present invention by bank note towards image overturn, it is ensured that bank note towards for front forward direction or
Person's reverse side is positive, reduces the model number of classification, improves the accuracy of training stage training;It is special by extracting rectangular histogram
Levy so that similar value of money paper money recognition pattern difference is little, and the recognition mode difference of inhomogeneity value of money bank note is big;What the present invention was provided
Scheme versatility is good, in the training stage of parameter, it is not necessary to excessive to change, you can quickly and accurately recognize the value of money of bank note.
Description of the drawings
Fig. 1 implements flow chart for the note denomination recognition methodss of the offer of the embodiment of the present invention one;
Fig. 2 implements flow chart for the note denomination recognition methodss of the offer of the embodiment of the present invention two;
Fig. 3 is the schematic block diagram of the note denomination identifying system that the embodiment of the present invention four is provided;
Fig. 4 is the schematic block diagram of the note denomination identifying system that the embodiment of the present invention five is provided.
Specific embodiment
In order that the objects, technical solutions and advantages of the present invention become more apparent, it is below in conjunction with drawings and Examples, right
The present invention is further elaborated.It should be appreciated that specific embodiment described herein is only to explain the present invention, and
It is not used in the restriction present invention.
Fig. 1 is that the note denomination recognition methodss that the embodiment of the present invention one is provided implement flow chart.Referring to Fig. 1 institutes
Show, the note denomination recognition methodss that the present embodiment one is provided may comprise steps of:
S100, acquisition banknote image to be identified, and the topography in the banknote image is intercepted according to predeterminated position;
Specifically, the present invention is the image information of the region of interest area image based on banknote image judging note denomination
, so needing to obtain the image information of bank note first.Topography is intercepted into squarely or rectangle, beneficial to accurately to sense
Interest area image is further judged.The position range of the topography is height h:20:260, width w:350:
650, to exclude the white space that there is bank note in the range of topography.
S200, the region of interest area image recognized in the topography;
Specifically, in area-of-interest (region of interest, area-of-interest) machine vision, image procossing,
Being sketched the contours of from processed image in modes such as square frame, circle, ellipse, irregular polygons needs region to be processed, referred to as feels emerging
Interesting region.Various operators (Operator) and function are commonly used on machine vision software to try to achieve area-of-interest region of interest
Domain, and carry out the next step process of image.The present invention is by carrying out area-of-interest image information to region of interest area image
Extract to obtain note denomination.
S300, the area-of-interest for including various value of money bank note that the region of interest area image is input into training in advance
In the grader of image information, and export the value of money of the bank note.
Specifically, can height in order to ensure the corresponding different sorting parameter of different values of money during training in advance
Corresponding grader is accurately corresponded to, is the sorting parameter by preserving the different value of money bank note for training.According to different values of money just
To bank note there are different sorting parameters, can correspondingly obtain different note denominations.
Above example can be seen that the scheme versatility that the present invention is provided is good, in the training stage of parameter, it is not necessary to mistake
It is change, you can quickly and accurately to recognize the value of money of bank note more.
Fig. 2 is that the note denomination recognition methodss that the embodiment of the present invention two is provided implement flow chart.Referring to Fig. 2 institutes
Show, relative to the acquisition banknote image that a upper embodiment, the present embodiment two are provided, and the paper is intercepted according to predeterminated position
Can also include before topography on coin image:
S400, the various area-of-interests for including various value of money bank note are obtained using convolutional neural networks classifier training
Image information, and the area-of-interest image information of the various value of money bank note is stored to the grader.
Specifically, the convolutional neural networks grader includes:Multiple feature figure layers, at least in multiple feature figure layers
At least one of individual feature figure layer characteristic pattern is divided into multiple regions;And multiple convolution masks, multiple convolution masks with
Multiple regions correspond to respectively, and each convolution mask is used for the response value for obtaining the neuron in respective regions.By by various coin
The area-of-interest image information of value bank note is stored in multiple convolution masks respectively, to distinguish different note denominations.
Further, the employing convolutional neural networks classifier training obtains the various senses for including various value of money bank note
Interest regional image information, and the area-of-interest image information of the various value of money bank note is stored to the classification implement body
Can include:
The banknote image to be measured of various values of money is obtained, treating in the banknote image to be measured is extracted according to the predeterminated position
Survey topography;
The region of interest area image to be measured in the topography to be measured corresponding to various values of money is identified respectively;
Every kind of value of money is chosen the sample of preset data and repeats above-mentioned two step, obtains sample data;
Sample data input is rolled in neural network classifier and is trained, obtain the to be measured of various value of money bank note
Area-of-interest image information.
Further, the banknote image for obtaining various values of money, extracts in the banknote image according to predeterminated position
Topography before can also include:
The bank note is overturn, makes the bank note keep positive.
Relative to a upper embodiment, the bank note of the present embodiment input is towards there is four kinds of states:Front is positive, front is swung to,
Reverse side is positive and reverse side is swung to, and the present invention is based on the positive method of region of interest area image, so bank note is overturn
Keep front positive to region of interest area image or reverse side is positive, be conducive to the feature of the forward direction to bank note front or reverse side
Image quickly carries out the judgement of next step.
Embodiment three, the area-of-interest image information that the present invention is provided are the topography in local binarization
Histogram feature under image model.
The bank note front proposed relative to a upper embodiment, the present embodiment or the region of interest area image of the forward direction of reverse side
With different local binarization pattern histogram features, the different local binarization pattern histogram of both states is distinguished
Feature directly can be judged to the value of money to bank note.
Fig. 3 is the schematic block diagram of the note denomination identifying system that the embodiment of the present invention four is provided, for convenience of description only
Illustrate only part related to the present embodiment.It is shown in Figure 3, the note denomination identifying system that the embodiment of the present invention four is provided
Can include:
Acquisition module 100, for obtaining banknote image to be identified, and intercepts in the banknote image according to predeterminated position
Topography;
Identification module 200, for recognizing the region of interest area image in the topography;
Output module 300, includes various value of money bank note for the region of interest area image is input into training in advance
Area-of-interest image information grader in, and export the value of money of the bank note.
Fig. 4 is the schematic block diagram of the note denomination identifying system that the embodiment of the present invention five is provided, for convenience of description only
Illustrate only part related to the present embodiment.Shown in Figure 4, relative to a upper embodiment, the embodiment of the present invention five is provided
Note denomination identifying system can also include:
Training module 400, for obtaining various including various value of money bank note using convolutional neural networks classifier training
Area-of-interest image information, and the area-of-interest image information of the various value of money bank note is stored to the classification
Device.
Preferably, the training module can specifically include:
Acquiring unit, for obtaining the banknote image to be measured of various values of money, extracts the banknote image according to predeterminated position
On topography to be measured;
Recognition unit, for identifying the area-of-interest to be measured in the topography to be measured corresponding to various values of money respectively
Image;
Unit is repeated, the sample for every kind of value of money to be chosen preset data repeats above-mentioned two step, obtains
To sample data;
Training unit, is trained for sample data input is rolled in neural network classifier, obtains various
The area-of-interest image information to be measured of value of money bank note.
Further, the training module can also include:
Roll-over unit, for overturning the bank note, makes the bank note keep positive.
It should be noted that modules in said system provided in an embodiment of the present invention, due to the inventive method reality
Example is applied based on same design, the technique effect which brings is identical with the inventive method embodiment, and particular content can be found in the present invention
Narration in embodiment of the method, here is omitted.
Above as can be seen that the present embodiment provide note denomination identifying system again may be by bank note towards figure
As being overturn, it is ensured that bank note reduces the model number of classification, improves training towards being that front forward direction or reverse side are positive
The accuracy of stage-training;By extracting histogram feature so that similar value of money paper money recognition pattern difference is little, inhomogeneity value of money
The recognition mode difference of bank note is big;The scheme versatility that the present invention is provided is good, in the training stage of parameter, it is not necessary to excessively change
It is dynamic, you can quickly and accurately to recognize the value of money of bank note.
Presently preferred embodiments of the present invention is the foregoing is only, not to limit the present invention, all essences in the present invention
Any modification, equivalent and improvement made within god and principle etc., should be included within the scope of the present invention.
Claims (10)
1. a kind of note denomination recognition methodss, it is characterised in that include:
Banknote image to be identified is obtained, and the topography in the banknote image is intercepted according to predeterminated position;
Recognize the region of interest area image in the topography;
The region of interest area image is input into into the area-of-interest image information for including various value of money bank note of training in advance
Grader in, and export the value of money of the bank note.
2. the method for claim 1, it is characterised in that acquisition banknote image to be identified, and according to predeterminated position
Also include before intercepting the topography in the banknote image:
Obtain including the area-of-interest image information of various value of money bank note using convolutional neural networks classifier training, and will
The area-of-interest image information of the various value of money bank note is stored to the grader.
3. method as claimed in claim 2, it is characterised in that the employing convolutional neural networks classifier training is included
There is the area-of-interest image information of various value of money bank note, and the area-of-interest image information of the various value of money bank note is deposited
Store up to the grader and specifically include:
The banknote image to be measured of various values of money is obtained, the office to be measured in the banknote image to be measured is extracted according to the predeterminated position
Portion's image;
The region of interest area image to be measured in the topography to be measured corresponding to various values of money is identified respectively;
Every kind of value of money is chosen the sample of preset data and repeats above-mentioned two step, obtains sample data;
Sample data input is rolled in neural network classifier and is trained, the sense to be measured for obtaining various value of money bank note is emerging
Interesting regional image information.
4. method as claimed in claim 3, it is characterised in that the banknote image to be measured of the various values of money of the acquisition, according to institute
Also include before stating the topography to be measured that predeterminated position is extracted in the banknote image:
The bank note is overturn, makes the bank note keep positive.
5. method as claimed in claim 2, it is characterised in that the area-of-interest image information exists for the topography
Histogram feature under local binarization image model.
6. a kind of note denomination identifying system, it is characterised in that include:
Acquisition module, for obtaining banknote image to be identified, and intercepts the Local map in the banknote image according to predeterminated position
Picture;
Identification module, for recognizing the region of interest area image in the topography;
Output module, includes the interested of various value of money bank note for the region of interest area image is input into training in advance
In the grader of regional image information, and export the value of money of the bank note.
7. system as claimed in claim 6, it is characterised in that the system also includes:
Training module, for obtaining various including the interested of various value of money bank note using convolutional neural networks classifier training
Regional image information, and the area-of-interest image information of the value of money bank note is stored to the grader.
8. system as claimed in claim 7, it is characterised in that the training module is specifically included:
Acquiring unit, for obtaining the banknote image to be measured of value of money, extracts in the banknote image according to the predeterminated position
Topography to be measured;
Recognition unit, for identifying the area-of-interest figure to be measured in the topography to be measured corresponding to various values of money respectively
Picture;
Unit is repeated, the sample for every kind of value of money to be chosen preset data repeats above-mentioned two step, obtains sample
Notebook data;
Training unit, is trained for sample data input is rolled in neural network classifier, obtains various values of money
The area-of-interest image information to be measured of bank note.
9. system as claimed in claim 8, it is characterised in that the training module also includes:
Roll-over unit, for overturning the bank note, makes the bank note keep positive.
10. system as claimed in claim 7, it is characterised in that the area-of-interest image information is the topography
Histogram feature under local binarization image model.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610942284.5A CN106548202A (en) | 2016-10-25 | 2016-10-25 | Note denomination recognition methodss and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610942284.5A CN106548202A (en) | 2016-10-25 | 2016-10-25 | Note denomination recognition methodss and system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106548202A true CN106548202A (en) | 2017-03-29 |
Family
ID=58392353
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610942284.5A Pending CN106548202A (en) | 2016-10-25 | 2016-10-25 | Note denomination recognition methodss and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106548202A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108734850A (en) * | 2018-04-27 | 2018-11-02 | 深圳怡化电脑股份有限公司 | Paper Currency Identification, paper money identifier and terminal device |
CN111599081A (en) * | 2020-05-15 | 2020-08-28 | 上海应用技术大学 | Method and system for collecting and dividing RMB paper money |
CN112329845A (en) * | 2020-11-03 | 2021-02-05 | 深圳云天励飞技术股份有限公司 | Method and device for replacing paper money, terminal equipment and computer readable storage medium |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US8519845B2 (en) * | 2010-12-16 | 2013-08-27 | King Fahd University Of Petroleum And Minerals | System and method for tracking people |
CN104851183A (en) * | 2015-05-15 | 2015-08-19 | 深圳怡化电脑股份有限公司 | Paper currency face and orientation recognition method and device |
CN105139510A (en) * | 2015-08-25 | 2015-12-09 | 深圳怡化电脑股份有限公司 | Bank note identification method and system |
CN105894656A (en) * | 2016-03-30 | 2016-08-24 | 浙江大学 | Banknote image recognition method |
CN105989659A (en) * | 2016-04-15 | 2016-10-05 | 新达通科技股份有限公司 | Similar character recognition method and paper currency crown code recognition method |
-
2016
- 2016-10-25 CN CN201610942284.5A patent/CN106548202A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US8519845B2 (en) * | 2010-12-16 | 2013-08-27 | King Fahd University Of Petroleum And Minerals | System and method for tracking people |
CN104851183A (en) * | 2015-05-15 | 2015-08-19 | 深圳怡化电脑股份有限公司 | Paper currency face and orientation recognition method and device |
CN105139510A (en) * | 2015-08-25 | 2015-12-09 | 深圳怡化电脑股份有限公司 | Bank note identification method and system |
CN105894656A (en) * | 2016-03-30 | 2016-08-24 | 浙江大学 | Banknote image recognition method |
CN105989659A (en) * | 2016-04-15 | 2016-10-05 | 新达通科技股份有限公司 | Similar character recognition method and paper currency crown code recognition method |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108734850A (en) * | 2018-04-27 | 2018-11-02 | 深圳怡化电脑股份有限公司 | Paper Currency Identification, paper money identifier and terminal device |
CN111599081A (en) * | 2020-05-15 | 2020-08-28 | 上海应用技术大学 | Method and system for collecting and dividing RMB paper money |
CN112329845A (en) * | 2020-11-03 | 2021-02-05 | 深圳云天励飞技术股份有限公司 | Method and device for replacing paper money, terminal equipment and computer readable storage medium |
CN112329845B (en) * | 2020-11-03 | 2024-05-07 | 深圳云天励飞技术股份有限公司 | Method and device for changing paper money, terminal equipment and computer readable storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN104299008B (en) | Vehicle type classification method based on multi-feature fusion | |
CN104851085B (en) | The automatic method and system for obtaining detection zone in image | |
CN106651872A (en) | Prewitt operator-based pavement crack recognition method and system | |
CN107229932A (en) | A kind of recognition methods of image text and device | |
CN107958217A (en) | A kind of fingerprint classification identifying system and method based on deep learning | |
CN106651774A (en) | License plate super-resolution model reconstruction method and device | |
CN106548202A (en) | Note denomination recognition methodss and system | |
EP2557545A1 (en) | Method for processing bank notes (variants) | |
CN106355744B (en) | A kind of recognition methods of Indonesian Rupiah value of money and device | |
Youn et al. | Efficient multi-currency classification of CIS banknotes | |
CN106663201A (en) | A palm detection method and apparatus | |
CN107067000A (en) | A kind of recognition methods of bank note degree and device | |
CN107025716A (en) | The method and device that detection paper money number is stained | |
Zhao et al. | License plate location based on Haar-like cascade classifiers and edges | |
CN106780954A (en) | A kind of method and device of paper money recognition | |
CN106650611B (en) | Method and device for recognizing color of vehicle body | |
Sharan et al. | Detection of counterfeit Indian currency note using image processing | |
CN104464078A (en) | Method and system for identifying damaged bank note through optical variability printing ink | |
CN105718947B (en) | Lung Cancer Images sophisticated category method based on LBP and wavelet moment fusion feature | |
CN106650555A (en) | Real person verifying method and system based on machine learning | |
CN106920318A (en) | The discrimination method and device of a kind of bank note | |
CN112270271A (en) | Iris identification method based on wavelet packet decomposition | |
CN107527423B (en) | Paper money anti-counterfeiting identification method and paper money identification device | |
CN106898078A (en) | A kind of recognition methods of Hongkong dollar version and device | |
Chakraborty et al. | Recent developments in paper currency recognition system |
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 | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170329 |