CN107590900A - A kind of crown word number image acquiring method, device, equipment and storage medium - Google Patents
A kind of crown word number image acquiring method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN107590900A CN107590900A CN201710835259.1A CN201710835259A CN107590900A CN 107590900 A CN107590900 A CN 107590900A CN 201710835259 A CN201710835259 A CN 201710835259A CN 107590900 A CN107590900 A CN 107590900A
- Authority
- CN
- China
- Prior art keywords
- word number
- crown word
- image
- pending
- subgraph
- 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
Landscapes
- Image Analysis (AREA)
Abstract
The embodiment of the invention discloses a kind of crown word number image acquiring method, device, equipment and storage medium.Wherein, crown word number image acquiring method includes obtaining the first binary image to pending image progress binary conversion treatment, and pending image includes crown word number；Obtain the positional information of crown word number in first binary image；Binary conversion treatment is carried out to pending image with reference to maximum variance between clusters and particle cluster algorithm and obtains the second binary image；The crown word number image of correspondence position in second binary image is intercepted according to the positional information of crown word number.The embodiment of the present invention carries out binary conversion treatment by combining maximum variance between clusters and particle cluster algorithm to pending image, traditional thresholding method is solved when entering row threshold division to image, the problem of speed of service is slow, optimal segmenting threshold can be converged in the short period of time, and then the true information reflected in crown word number image, so as to improve the accuracy of image segmentation.
Description
Technical field
The present embodiments relate to image recognition technology, more particularly to a kind of crown word number image acquiring method, device, set
Standby and storage medium.
Background technology
Image segmentation is exactly to divide the image into several regions specific, with unique properties and propose mesh interested
Target technology and process, mainly image object is extracted, measured, it is by image procossing to image recognition, analysis
Basis and committed step.
For the method for image segmentation, at present existing very more processing method, such as rim detection split plot design, region
Split plot design, thresholding method, wherein thresholding method are applied and carried out than wide but traditional thresholding method to image
During multi-threshold segmentation, the speed of service is slow.
The content of the invention
The embodiment of the present invention provides a kind of crown word number image acquiring method, device, equipment and storage medium, to pass through knot
Close maximum variance between clusters and particle cluster algorithm and binary conversion treatment is carried out to the pending image, can be in the short period of time
Optimal segmenting threshold is converged to, and then the accuracy of image segmentation can be improved.
In a first aspect, the embodiments of the invention provide a kind of crown word number image acquiring method, including：
Binary conversion treatment is carried out to pending image and obtains the first binary image, the pending image includes hat
Font size；
Obtain the positional information of crown word number in first binary image；
Binary conversion treatment is carried out to the pending image with reference to maximum variance between clusters and particle cluster algorithm and obtains second
Binary image；
The crown word number image of correspondence position in second binary image is intercepted according to the positional information of crown word number.
Second aspect, the embodiment of the present invention additionally provide a kind of crown word number image acquiring device, and the crown word number image obtains
Device includes：
The third aspect, the embodiment of the present invention additionally provide a kind of equipment, and the equipment includes：
One or more processors；
Storage device, for storing one or more programs, when one or more of programs are one or more of
Computing device so that one or more of processors realize the crown word number image acquiring method described in the present embodiment.
Fourth aspect, the embodiment of the present invention additionally provide a kind of computer-readable recording medium, are stored thereon with computer
Program, the program realize the crown word number image acquiring method described in the present embodiment when being executed by processor.
The embodiment of the present invention to the pending image with reference to maximum variance between clusters and particle cluster algorithm by carrying out two
Value is handled, and solves traditional thresholding method when entering row threshold division to image, the problem of speed of service is slow, can compared with
Optimal segmenting threshold, and then the true information reflected in crown word number image are converged in the short time, so as to improve image segmentation
Accuracy.
Brief description of the drawings
Fig. 1 is a kind of crown word number image acquiring method flow chart in the embodiment of the present invention one；
Fig. 2 is a kind of crown word number image acquiring method flow chart in the embodiment of the present invention two；
Fig. 3 is a kind of crown word number image acquiring device structural representation in the embodiment of the present invention three；
Fig. 4 is a kind of device structure schematic diagram in the embodiment of the present invention four.
Embodiment
The present invention is described in further detail with reference to the accompanying drawings and examples.It is understood that this place is retouched
The specific embodiment stated is used only for explaining the present invention, rather than limitation of the invention.It also should be noted that in order to
It is easy to describe, part related to the present invention rather than entire infrastructure is illustrate only in accompanying drawing.
Embodiment one
Fig. 1 is a kind of crown word number image acquiring method flow chart in the embodiment of the present invention one, and the present embodiment is applicable to
Split the image of the crown word number position in pending image (i.e. banknote image) and then get the feelings of crown word number image
Condition, this method can be performed by crown word number image acquiring device, and can typically be integrated in it is various need carry out forge or true or paper money
In the finance device of identification, for example, ATM or cash inspecting machine etc., specifically comprise the following steps：
S110, the first binary image is obtained to pending image progress binary conversion treatment, wrapped in the pending image
Include crown word number.
Bank note distribution method described in the present embodiment is performed by financial self-service equipment, such as ATM (ATM,
Automatic Teller Machine) and automatic teller machine (CRS, Cash Recycling System).
Pending image in the present embodiment is the corresponding banknote image information of complete bank note, specifically, pending figure
The banknote image information as corresponding to can be the bank note of different denominations, country variant, it can be obtained by being arranged at crown word number image
The image capture module in device is taken to obtain.
The binary conversion treatment is used for the Zone Full of the pending image of binaryzation, and binary conversion treatment is exactly by image
The gray value of pixel be arranged to 0 or 255, that is, whole image is showed into obvious black and white effect, not only makes image
Become simple, highlight the profile of target, and image data amount can be reduced.
Specifically, the pending image information includes crown word number image, the crown word number image is the prefix of bank note
Number region image, crown word number are used to record emission of banknotes sequence, can be made up of Arabic numerals and letter.Prefix
Number region image can be located at the lower left corner part of bank note.Exemplary, its size of the RMB of 100 yuan of face amounts is
165*77mm, using 1mm as coordinate system unit, crown word number region is the square of (5,15) (45,15) (45,20) (5,20) composition
Shape region.
First binary image is the result images that this step obtains, and is the gray level image of the pending image.
S120, the positional information for obtaining crown word number in first binary image.
Wherein, the positional information of crown word number is used for the pending specific coordinate of image information where recording crown word number.This implementation
Example can be determined during the positional information of crown word number is obtained by traveling through the pixel value of each pixel in pending image
The positional information of crown word number.
S130, binary conversion treatment is carried out to the pending image with reference to maximum variance between clusters and particle cluster algorithm obtained
To the second binary image；
Wherein, the maximum variance between clusters (OTSU) are also known as Da-Jin algorithm, and its operation principle is, by the gray scale of image
Characteristic, divide the image into background and target two parts.Inter-class variance between background and target is bigger, illustrate pie graph as
Two-part difference is bigger, when partial target mistake is divided into background or part background mistake is divided into target and can all cause two parts difference
Diminish.Therefore, the segmentation for making inter-class variance maximum means misclassification probability minimum.
Particle cluster algorithm (Particle Swarm Optimization, PSO), also known as flock of birds foraging algorithm, its work
Principle is：From RANDOM SOLUTION, optimal solution is found by iteration；Or the quality of solution is evaluated by fitness, by following
Current search to optimal value find global optimum.This algorithm is with the advantages that its realization is easy, precision is high, convergence is fast.
Maximum variance between clusters and particle cluster algorithm are combined binary conversion treatment is carried out to pending image procossing, obtained
To result images be the second binary image, there is the information in true reflection crown word number image, so as to can further improve
The advantages of accuracy of image segmentation.
Optionally, can be according to the positional information of crown word number, only to where crown word number in pending image in the present embodiment
Region carry out binary conversion treatment, and then reduce binary conversion treatment area, the further accuracy for improving image segmentation.
S140, the crown word number figure according to correspondence position in the positional information of crown word number interception second binary image
Picture.
Wherein, the positional information of the crown word number also includes the more specific location information of each crown word number, therefore can root
Each character in crown word number image is intercepted out according to the more specific location information of each crown word number, for identifying.
The technical scheme of the present embodiment, by with reference to maximum variance between clusters and particle cluster algorithm to the pending figure
As carrying out binary conversion treatment, solves traditional thresholding method when entering row threshold division to image, the speed of service is slow to ask
Topic, optimal segmenting threshold, and then the true information reflected in crown word number image can be converged in the short period of time, so as to carry
The accuracy of hi-vision segmentation result.
Embodiment two
Fig. 2 is a kind of crown word number image acquiring method flow chart that the embodiment of the present invention two provides, and the present embodiment is above-mentioned
Respectively the crown word number subgraph for intercepting out from crown word number image is identified to obtain crown word number on the basis of embodiment,
Specifically comprise the following steps：
S210, the first binary image is obtained to pending image progress binary conversion treatment, wrapped in the pending image
Include crown word number.
Wherein, the pending image includes vertical column type crown word number image and horizontal-type crown word number image in bank note.Can be with
Understand, the arrangement mode for crown word number of crown word number is vertical array in the vertical column type crown word number image, the horizontal-type
The arrangement mode of crown word number is transversely arranged in crown word number image.
S220, the positional information for obtaining crown word number in first binary image.
S230, binary conversion treatment is carried out to the pending image with reference to maximum variance between clusters and particle cluster algorithm obtained
To the second binary image.
S240, the crown word number figure according to correspondence position in the positional information of crown word number interception second binary image
Picture.
S250, the positional information for determining using row sciagraphy crown word number element in the crown word number image.
Wherein, row sciagraphy by calculate single column of pixels point pixel and, to judge whether include prefix in the pixel column
The pixel of sign character profile.Exemplary, should when not including the pixel of pixel crown word number character outline in pixel column
The pixel value identical (0 or 255) of all pixels point in row is the pixel of the row pixel and is a determination value, if detecting
The pixel of the row pixel and identical with the determination value, then illustrate not include pixel crown word number character outline in the pixel column
Any one pixel, now using the positional information of the crown word number element as shown in of the sequence number where the row.
S260, the crown word number image is intercepted according to the positional information of the crown word number element respectively, obtained and crown word number
The crown word number subgraph of the identical quantity of element number；Wherein, each crown word number subgraph includes a crown word number member
Element.
Wherein, each crown word number subgraph includes a crown word number element, and the present embodiment can be by identifying hat respectively
Font size subgraph obtains crown word number sequence, further improves the accuracy of image segmentation result.
The technical scheme of the present embodiment, by entering respectively to the crown word number subgraph for intercepting out from crown word number image
Row identification obtains crown word number, further improves the accuracy of image segmentation result.
It is described that the prefix is intercepted according to the positional information of the crown word number element on the basis of above-mentioned technical proposal
Number image, obtains the crown word number subgraph of quantity identical with crown word number element number, including：
Pending crown word number subgraph is intercepted from the pending image according to the positional information of the crown word number element
Picture, obtain the pending crown word number subgraph of quantity identical with crown word number element number；
Binary conversion treatment is carried out to pending crown word number subgraph respectively with reference to maximum variance between clusters and particle cluster algorithm
Obtain the crown word number subgraph.Feature 1, which is so set, to be advantageous in that by combining maximum variance between clusters and population calculation
Method carries out binary conversion treatment to crown word number image, can converge to optimal segmenting threshold, and then true reflection in the short period of time
Information in crown word number image, so as to improve the accuracy of image segmentation result.
Embodiment three
Fig. 3 is a kind of crown word number image acquiring device structural representation that the embodiment of the present invention three provides, as shown in figure 3,
Described device includes：First binary image acquisition module 310, position information acquisition module 320, the second binary image obtain
Modulus block 330 and crown word number image collection module 340.
Wherein, the first binary image acquisition module 310, the is obtained for carrying out binary conversion treatment to pending image
One binary image, the pending image include crown word number；
Position information acquisition module 320, for obtaining the positional information of crown word number in first binary image；
Second binary image acquisition module 330, for being treated with reference to maximum variance between clusters and particle cluster algorithm to described
Processing image carries out binary conversion treatment and obtains the second binary image；
Crown word number image collection module 340, for intercepting second binary image according to the positional information of crown word number
The crown word number image of middle correspondence position.
The technical scheme of the present embodiment, by with reference to maximum variance between clusters and particle cluster algorithm to the pending figure
As carrying out binary conversion treatment, solves traditional thresholding method when entering row threshold division to image, the speed of service is slow to ask
Topic, optimal segmenting threshold, and then the true information reflected in crown word number image can be converged in the short period of time, so as to carry
The accuracy of hi-vision segmentation result.
On the basis of above-described embodiment, the crown word number is made up of multiple crown word number elements；
Corresponding, the second binary image acquisition module includes：
Positional information determining unit, for determining the position of crown word number element in the crown word number image using row sciagraphy
Confidence ceases；
Crown word number subgraph interception unit, for intercepting the hat according to the positional information of the crown word number element respectively
Font size image, obtain the crown word number subgraph of quantity identical with crown word number element number；Wherein, each crown word number subgraph
As including a crown word number element.
On the basis of above-described embodiment, the crown word number image collection module 340 includes：
Pending crown word number subgraph acquiring unit, for being treated according to the positional information of the crown word number element from described
Pending crown word number subgraph is intercepted in processing image, obtains the pending crown word number of quantity identical with crown word number element number
Subgraph；
Crown word number subgraph acquiring unit, for combining maximum variance between clusters and particle cluster algorithm respectively to pending
Crown word number subgraph carries out binary conversion treatment and obtains the crown word number subgraph.
On the basis of above-described embodiment, the pending image includes vertical column type crown word number image and horizontally-arranged in bank note
Formula crown word number image.
The crown word number image acquiring device that the embodiment of the present invention is provided can perform what any embodiment of the present invention was provided
Crown word number image acquiring method, possess the corresponding functional module of execution method and beneficial effect.
Example IV
Fig. 4 is a kind of structural representation for equipment that the embodiment of the present invention four provides, as shown in figure 4, the equipment includes place
Manage device 40, memory 41, input unit 42 and output device 43；The quantity of processor 70 can be one or more in equipment,
In Fig. 4 by taking a processor 40 as an example；Processor 40, memory 41, input unit 42 and output device 43 in equipment can be with
Connected by bus or other modes, in Fig. 4 exemplified by being connected by bus.
Memory 41 is used as a kind of computer-readable recording medium, and journey is can perform available for storage software program, computer
Sequence and module, module is (for example, crown word number image obtains as corresponding to the crown word number image acquiring method in the embodiment of the present invention
The first binary image acquisition module 310 in device, position information acquisition module 320, the second binary image is taken to obtain mould
Block 330 and crown word number image collection module 340).Processor 40 is by running the software program being stored in memory 41, referring to
Order and module, so as to perform the various function application of equipment and data processing, that is, realize that above-mentioned crown word number image obtains
Method.
Memory 41 can mainly include storing program area and storage data field, wherein, storing program area can store operation system
Application program needed for system, at least one function；Storage data field can store uses created data etc. according to terminal.
In addition, memory 41 can include high-speed random access memory, nonvolatile memory, for example, at least one can also be included
Individual disk memory, flush memory device or other non-volatile solid state memory parts.In some instances, memory 41 can enter
One step includes that relative to the remotely located memory of processor 40, these remote memories network connection to equipment can be passed through.
The example of above-mentioned network includes but is not limited to internet, intranet, LAN, mobile radio communication and combinations thereof.
Embodiment five
The embodiment of the present invention five also provides a kind of storage medium for including computer executable instructions, and the computer can
Execute instruction is used to perform a kind of crown word number image acquiring method when being performed by computer processor, and this method includes：
Binary conversion treatment is carried out to pending image and obtains the first binary image, the pending image includes hat
Font size；
Obtain the positional information of crown word number in first binary image；
Binary conversion treatment is carried out to the pending image with reference to maximum variance between clusters and particle cluster algorithm and obtains second
Binary image；
The crown word number image of correspondence position in second binary image is intercepted according to the positional information of crown word number.
Certainly, a kind of storage medium for including computer executable instructions that the embodiment of the present invention is provided, its computer
The method operation that executable instruction is not limited to the described above, it can also carry out a kind of hat that any embodiment of the present invention is provided
Associative operation in font size image acquiring method
By the description above with respect to embodiment, it is apparent to those skilled in the art that, the present invention
It can be realized by software and required common hardware, naturally it is also possible to realized by hardware, but the former is more in many cases
Good embodiment.Based on such understanding, what technical scheme substantially contributed to prior art in other words
Part can be embodied in the form of software product, and the computer software product can be stored in computer-readable storage medium
In matter, floppy disk, read-only storage (Read-Only Memory, ROM), random access memory (Random such as computer
Access Memory, RAM), flash memory (FLASH), hard disk or CD etc., including some instructions are causing a computer to set
Standby (can be personal computer, server, or network equipment etc.) performs the method described in each embodiment of the present invention.
It is worth noting that, in the embodiment of above-mentioned searcher, included unit and module are simply according to work(
Energy logic is divided, but is not limited to above-mentioned division, as long as corresponding function can be realized；In addition, each work(
The specific name of energy unit is also only to facilitate mutually distinguish, the protection domain being not intended to limit the invention.
Pay attention to, above are only presently preferred embodiments of the present invention and institute's application technology principle.Those skilled in the art can manage
Solution, the invention is not restricted to specific embodiment described here, can carry out various obvious changes for a person skilled in the art
Change, readjust and substitute without departing from protection scope of the present invention.Therefore, although by above example to the present invention
It is described in further detail, but the present invention is not limited only to above example, is not departing from the situation of present inventive concept
Under, other more equivalent embodiments can also be included, and the scope of the present invention is determined by scope of the appended claims.
Claims (10)
- A kind of 1. crown word number image acquiring method, it is characterised in that including：Binary conversion treatment is carried out to pending image and obtains the first binary image, the pending image includes crown word number；Obtain the positional information of crown word number in first binary image；Binary conversion treatment is carried out to the pending image with reference to maximum variance between clusters and particle cluster algorithm and obtains the second two-value Change image；The crown word number image of correspondence position in second binary image is intercepted according to the positional information of crown word number.
- 2. crown word number image acquiring method according to claim 1, it is characterised in that：The crown word number is made up of multiple crown word number elements；It is corresponding, intercepted according to the positional information in second binary image after the crown word number image of correspondence position, Also include：Utilize the positional information of crown word number element in row sciagraphy and the determination crown word number image；The crown word number image is intercepted according to the positional information of the crown word number element respectively, obtained and crown word number element number phase With the crown word number subgraph of quantity；Wherein, each crown word number subgraph includes a crown word number element.
- 3. crown word number image acquiring method according to claim 2, it is characterised in that described according to the crown word number element Positional information intercept the crown word number image, obtain the crown word number subgraph of quantity identical with crown word number element number, including：Pending crown word number subgraph is intercepted from the pending image according to the positional information of the crown word number element, obtained The pending crown word number subgraph of quantity identical with crown word number element number；Binary conversion treatment is carried out with reference to maximum variance between clusters and particle cluster algorithm to pending crown word number subgraph respectively to obtain The crown word number subgraph.
- 4. crown word number image acquiring method according to claim 2, it is characterised in that：The pending image includes vertical column type crown word number image and horizontal-type crown word number image in bank note.
- A kind of 5. crown word number image acquiring device, it is characterised in that including：First binary image acquisition module, the first binary image is obtained for carrying out binary conversion treatment to pending image, The pending image includes crown word number；Position information acquisition module, for obtaining the positional information of crown word number in first binary image；Second binary image acquisition module, for reference to maximum variance between clusters and particle cluster algorithm to the pending image Carry out binary conversion treatment and obtain the second binary image；Crown word number image collection module, position is corresponded to for being intercepted according to the positional information of crown word number in second binary image The crown word number image put.
- 6. crown word number image acquiring device according to claim 5, it is characterised in that：The crown word number is made up of multiple crown word number elements；Corresponding, described crown word number image acquiring device also includes：Positional information determining module, for utilizing row sciagraphy, determine the position letter of crown word number element in the crown word number image Breath；Crown word number subgraph interception module, for intercepting the crown word number figure according to the positional information of the crown word number element respectively Picture, obtain the crown word number subgraph of quantity identical with crown word number element number；Wherein, each crown word number subgraph includes One crown word number element.
- 7. crown word number image acquiring device according to claim 6, it is characterised in that the crown word number image collection module Including：Pending crown word number subgraph acquiring unit, for the positional information according to the crown word number element from the pending figure Pending crown word number subgraph is intercepted as in, obtains the pending crown word number subgraph of quantity identical with crown word number element number；Crown word number subgraph acquiring unit, for combining maximum variance between clusters and particle cluster algorithm respectively to pending crown word number Subgraph carries out binary conversion treatment and obtains the crown word number subgraph.
- 8. crown word number image acquiring device according to claim 5, it is characterised in that：The pending image includes vertical column type crown word number image and horizontal-type crown word number image in bank note.
- 9. a kind of equipment, it is characterised in that the equipment includes：One or more processors；Storage device, for storing one or more programs, when one or more of programs are by one or more of processing Device performs so that one or more of processors realize the crown word number image acquisition side as described in any in claim 1-4 Method.
- 10. a kind of computer-readable recording medium, is stored thereon with computer program, it is characterised in that the program is by processor The crown word number image acquiring method as described in any in claim 1-M is realized during execution.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710835259.1A CN107590900A (en) | 2017-09-15 | 2017-09-15 | A kind of crown word number image acquiring method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710835259.1A CN107590900A (en) | 2017-09-15 | 2017-09-15 | A kind of crown word number image acquiring method, device, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107590900A true CN107590900A (en) | 2018-01-16 |
Family
ID=61048087
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710835259.1A Pending CN107590900A (en) | 2017-09-15 | 2017-09-15 | A kind of crown word number image acquiring method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107590900A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109086766A (en) * | 2018-06-06 | 2018-12-25 | 南京华科和鼎信息科技有限公司 | A kind of multi threshold fusion crown word number extracting method based on integrogram |
| CN109635823A (en) * | 2018-12-07 | 2019-04-16 | 湖南中联重科智能技术有限公司 | The method and apparatus and engineering machinery of elevator disorder cable for identification |
| CN111524268A (en) * | 2019-01-16 | 2020-08-11 | 深圳怡化电脑股份有限公司 | Method, device and equipment for detecting paper money adhesive substance |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2010009482A (en) * | 2008-06-30 | 2010-01-14 | Oki Electric Ind Co Ltd | Security discrimination apparatus |
| CN102496156A (en) * | 2011-11-17 | 2012-06-13 | 西安电子科技大学 | Medical image segmentation method based on quantum-behaved particle swarm cooperative optimization |
| CN104318238A (en) * | 2014-11-10 | 2015-01-28 | 广州御银科技股份有限公司 | Method for extracting crown word numbers from scanned banknote images in banknote detection module |
| CN107025716A (en) * | 2017-06-05 | 2017-08-08 | 深圳怡化电脑股份有限公司 | The method and device that detection paper money number is stained |
-
2017
- 2017-09-15 CN CN201710835259.1A patent/CN107590900A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2010009482A (en) * | 2008-06-30 | 2010-01-14 | Oki Electric Ind Co Ltd | Security discrimination apparatus |
| CN102496156A (en) * | 2011-11-17 | 2012-06-13 | 西安电子科技大学 | Medical image segmentation method based on quantum-behaved particle swarm cooperative optimization |
| CN104318238A (en) * | 2014-11-10 | 2015-01-28 | 广州御银科技股份有限公司 | Method for extracting crown word numbers from scanned banknote images in banknote detection module |
| CN107025716A (en) * | 2017-06-05 | 2017-08-08 | 深圳怡化电脑股份有限公司 | The method and device that detection paper money number is stained |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109086766A (en) * | 2018-06-06 | 2018-12-25 | 南京华科和鼎信息科技有限公司 | A kind of multi threshold fusion crown word number extracting method based on integrogram |
| CN109086766B (en) * | 2018-06-06 | 2021-03-09 | 南京华科和鼎信息科技有限公司 | Multi-threshold fusion crown word number extraction method based on integral graph |
| CN109635823A (en) * | 2018-12-07 | 2019-04-16 | 湖南中联重科智能技术有限公司 | The method and apparatus and engineering machinery of elevator disorder cable for identification |
| CN111524268A (en) * | 2019-01-16 | 2020-08-11 | 深圳怡化电脑股份有限公司 | Method, device and equipment for detecting paper money adhesive substance |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Dai et al. | One-stage cascade refinement networks for infrared small target detection | |
| Wang et al. | Tracking by joint local and global search: A target-aware attention-based approach | |
| Lacerda et al. | Segmentation of connected handwritten digits using Self-Organizing Maps | |
| CN117423126B (en) | Bill image-text recognition method and system based on data analysis | |
| CN107590900A (en) | A kind of crown word number image acquiring method, device, equipment and storage medium | |
| Chen et al. | Segmentation of overlapping cervical cells with mask region convolutional neural network | |
| CN107240185B (en) | A kind of crown word number identification method, device, equipment and storage medium | |
| Jang et al. | Low-quality banknote serial number recognition based on deep neural network | |
| CN117456167A (en) | Target detection algorithm based on improved YOLOv8s | |
| CN112926592A (en) | Trademark retrieval method and device based on improved Fast algorithm | |
| Dittimi et al. | Multi-class SVM based gradient feature for banknote recognition | |
| Li et al. | Image pattern recognition in identification of financial bills risk management | |
| Murtaza et al. | DiPS: Discriminative pseudo-label sampling with self-supervised transformers for weakly supervised object localization | |
| Ying et al. | License plate detection and localization in complex scenes based on deep learning | |
| CN112949634B (en) | Railway contact net nest detection method | |
| Xia et al. | Fast template matching based on deformable best-buddies similarity measure | |
| CN107680246B (en) | Method and equipment for positioning curve boundary in paper money pattern | |
| Murtaza et al. | Constrained sampling for class-agnostic weakly supervised object localization | |
| Gu et al. | Multi-scaled license plate detection based on the label-moveable maximal MSER clique | |
| Kweon et al. | From SAM to CAMs: Exploring Segment Anything Model for Weakly Supervised Semantic Segmentation | |
| Luo et al. | Alphanumeric character recognition based on BP neural network classification and combined features | |
| Harfiya et al. | Offline signature verification based on pyramid histogram of oriented gradient features | |
| Wang et al. | Overlapping cell segmentation of cervical cytology images based on nuclear radial boundary enhancement | |
| Wang et al. | Comparison and Analysis of Several Clustering Algorithms for Pavement Crack Segmentation Guided by Computational Intelligence | |
| Lin et al. | In defense of iterated conditional mode for hyperspectral image classification |
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: 20180116 |