CN109101960A - Identity text information detection method and device - Google Patents
Identity text information detection method and device Download PDFInfo
- Publication number
- CN109101960A CN109101960A CN201810840958.XA CN201810840958A CN109101960A CN 109101960 A CN109101960 A CN 109101960A CN 201810840958 A CN201810840958 A CN 201810840958A CN 109101960 A CN109101960 A CN 109101960A
- Authority
- CN
- China
- Prior art keywords
- image
- pixel
- text information
- dark channel
- value
- 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
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/22—Image preprocessing by selection of a specific region containing or referencing a pattern; Locating or processing of specific regions to guide the detection or recognition
-
- 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
- G06V10/56—Extraction of image or video features relating to colour
Abstract
The present disclosure proposes a kind of identity text information detection method and device, wherein the identity text information detection method includes: to obtain the dark channel image of ID Card Image;And the target area comprising identity text information in the determining dark channel image, location information of the identity text information in the ID Card Image is determined according to the target area.Disclosure identity text information detection method and device, can eliminate the interference of illumination and ID Card Image background, so as to guarantee the accuracy of testing result.
Description
Technical field
The embodiment of the present disclosure is related to field of information security technology, more particularly, to a kind of identity text information detection side
Method and device.
Background technique
As the rapid development of information age has been goed deep into as the effective management tool identity card of population information
Different social sectors are arrived.Identity card is for recording basic personal information and unique identity card number, in many letters
It is required to detect the identity text information printed on identity card in breath system.In the related technology to the body on identity card
When part information is identified, OCR (Optical Character Recognition, optical character identification) skill is usually used
Art confirms the location information of identity information on identity card, and then identifies identity information based on location information.Due to ID Card Image
Background be to be made of shade grid lines and laser anti-fake figure mark, background is more complicated.The body come out by scanner scanning
In part card image, uneven illumination can cause noise jamming namely noise to be believed when laser anti-fake figure mark, shade grid lines and scanning
Breath is mutually mixed with identity text information, to increase identification difficulty, causes to identify easy error.
Summary of the invention
(1) technical problems to be solved
It is above existing at least partly to solve present disclose provides a kind of identity text information detection method and device
Technical problem.
(2) technical solution
According to one aspect of the disclosure, a kind of identity text information detection method is provided, comprising:
Obtain the dark channel image of ID Card Image;And
It determines the target area in the dark channel image comprising identity text information, institute is determined according to the target area
State location information of the identity text information in the ID Card Image.
In some embodiments, it is described obtain ID Card Image dark channel image the step of in,
According to the tri- chrominance channel value of RGB of pixel each in the ID Card Image, the gray value of each pixel is determined, thus
Obtain the dark channel image of ID Card Image.
In some embodiments, according to the tri- chrominance channel value of RGB of pixel each in the ID Card Image, each picture is determined
The step of gray value of element, comprising:
Any pixel in the ID Card Image is determined and wrapped in the ID Card Image according to preset window size
Pixel window containing any pixel and centered on any pixel;
From minimum interim gray value in the interim gray value of all pixels, is chosen in the pixel window as described any
The gray value of pixel;Wherein, the interim gray value of each pixel is that numerical value is the smallest logical in the tri- chrominance channel value of RGB of each pixel
Road value.
In some embodiments, include in determining the dark channel image identity text information target area the step of
In:
Image binaryzation processing is carried out to the dark channel image, the bianry image of the dark channel image is obtained, is based on
The bianry image determines the target area in the dark channel image comprising identity text information.
In some embodiments, image binaryzation processing is carried out to the dark channel image, obtains the dark channel image
Bianry image, comprising:
Based on the gray value of pixel in predeterminable area in the dark channel image, determines and use when image binaryzation processing
Gray value threshold value;
Maximum gradation value is set by the gray value of first kind pixel in the dark channel image, by the dark channel image
In the gray value of the second class pixel be set as minimum gradation value, to obtain the bianry image of the dark channel image;Wherein, institute
Stating first kind pixel is the pixel that gray value is less than the gray value threshold value, and the second class pixel is that gray value is greater than the ash
The pixel of angle value threshold value.
In some embodiments, determine to include identity text information in the dark channel image based on the bianry image
The step of target area, comprising:
Edges of regions detection is carried out to the bianry image, is determined in the bianry image comprising the identity text information
To favored area;
Position based on each location information to favored area and the identity text information in the ID Card Image
Confidence ceases value interval, screens to all to favored area, determines to include identity text information in the dark channel image
Target area.
In some embodiments, described to determine the identity text information in the identity card figure according to the target area
Location information as in, comprising:
According to the location information of edge pixel point in the target area, determine comprising the target area and area minimum
Rectangular area, the position using the location information of the rectangular area as the identity text information in the ID Card Image
Confidence breath.
A kind of identity text information detection device another aspect of the present disclosure provides, comprising:
Module is obtained, for obtaining the dark channel image of ID Card Image;
First determining module, for determining the target area in the dark channel image comprising identity text information;And
Second determining module, for determining the identity text information in the ID Card Image according to the target area
In location information.
A kind of identity text information detection device another aspect of the present disclosure provides, comprising:
At least one processor;And
At least one processor being connect with the processor communication, in which:
The memory is stored with the program instruction that can be executed by the processor, and the processor calls described program to refer to
It enables and is able to carry out the method.
A kind of non-transient computer readable storage medium another aspect of the present disclosure provides, it is described non-transient
Computer-readable recording medium storage computer instruction, the computer instruction make the computer execute the method.
(3) beneficial effect
It can be seen from the above technical proposal that disclosure identity text information detection method and device at least have and following have
Beneficial effect:
By the dark channel image for obtaining ID Card Image.Determine the target in dark channel image comprising identity text information
Region determines location information of the identity text information in ID Card Image according to target area.Since ID Card Image being turned
Dark channel image is turned to, the interference of illumination and ID Card Image background can be eliminated, so as to guarantee the accuracy of testing result.
Detailed description of the invention
In order to illustrate more clearly of the embodiment of the present disclosure or technical solution in the prior art, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is this public affairs
The some embodiments opened for those of ordinary skill in the art without creative efforts, can be with root
Other attached drawings are obtained according to these attached drawings.
Fig. 1 is a kind of identity text information detection method flow chart that one embodiment of the disclosure provides;
Fig. 2 is a kind of identity text information schematic diagram for identity card that another embodiment of the disclosure provides;
Fig. 3 is a kind of pixel window schematic diagram that the another embodiment of the disclosure provides;
Fig. 4 is a kind of structural schematic diagram for identity text information detection device that one embodiment of the disclosure provides;
Fig. 5 is a kind of structural schematic diagram for identity text information detection device that one embodiment of the disclosure provides.
Specific embodiment
For the purposes, technical schemes and advantages of the disclosure are more clearly understood, below in conjunction with specific embodiment, and reference
The disclosure is further described in attached drawing.
The embodiment of the present disclosure provides a kind of identity text information detection method.This method can be applied to different identity card and know
Other scene, the embodiment of the present disclosure are also not especially limited this.As shown in Figure 1, this method comprises:
101, the dark channel image of ID Card Image is obtained.
Wherein, ID Card Image can be obtained by way of taking pictures to identity card, can also be using to identity card
The mode being scanned is obtained, and it is not limited in this embodiment of the present disclosure.
The dark channel image refers to that in the regional area of most images, certain pixels always have at least one
A Color Channel has very low value, the gray value of these pixels is determined with this, and there was only the pixel institute group of gray value by these
At gray level image.By carrying out dark processing to ID Card Image, dark channel image can be obtained.
102, it determines the target area in dark channel image comprising identity text information, identity text is determined according to target area
Location information of this information in ID Card Image.
As shown in Fig. 2, the identity text information of identity card reverse side generally includes " name ", " gender ", " nationality ", " birth
Date " and " identity card number ".And above-mentioned identity text information is generally placed on the fixation position on identity card or is being consolidated
Determine in region, so as to first determine the target area in dark channel image including identity text information.If with ID Card Image
Lower left corner fixed point is that origin establishes coordinate system, then the location information of each target area is it was determined that can determine
Location information of the identity text information in ID Card Image.
It, can be according to location information by identity card figure after determining location information of the identity text information in ID Card Image
Image-region as in comprising identity text information intercepts out, to further sample more accurately image recognition technology, knows
It Chu not identity text information in figure line region.
The method that the disclosure provides, by the dark channel image for obtaining ID Card Image.It determines in dark channel image and includes
The target area of identity text information determines location information of the identity text information in ID Card Image according to target area.
Since dark channel image can be converted by ID Card Image, the interference of illumination and ID Card Image background can be eliminated, so as to
Guarantee the accuracy of recognition result.
Based on above content, as a kind of alternative embodiment, the embodiment of the present disclosure is not helped acquisition ID Card Image secretly
The mode of road image specifically limits, including but not limited to: identity-based demonstrate,proves the tri- chrominance channel value of RGB of each pixel in image,
The gray value of each pixel is determined, to obtain dark channel image.
Wherein, each pixel is corresponding with tri- chrominance channel value of RGB in ID Card Image, and tri- chrominance channel RGB is red green respectively
Blue three chrominance channels, the value range in each channel are 0 to 255.According to the tri- chrominance channel value of RGB of each pixel, it may be determined that each
The gray value of pixel.And in determining all ID Card Images after the gray value of all pixels, the grayscale image of all pixels composition
Picture as dark channel image.
Content based on the above embodiment, as a kind of alternative embodiment, the embodiment of the present disclosure, which is not demonstrate,proved identity-based, to be schemed
The tri- chrominance channel value of RGB of each pixel, determines that the mode of the gray value of each pixel specifically limits, including but unlimited as in
In: for any pixel in ID Card Image, according to preset window size, determine in ID Card Image comprising any pixel and with
Pixel window centered on any pixel;From the interim gray value of pixel each in pixel window, minimum interim gray scale is chosen
It is worth the gray value as any pixel;Wherein, the interim gray value of each pixel is number in the tri- chrominance channel value of RGB of each pixel
It is worth the smallest channel value.
For any pixel in ID Card Image, the process of the gray value of the above-mentioned determination pixel can refer to following formula:
In above-mentioned formula, X indicates the pixel.J-dark(x) gray value of the pixel, min are indicatedC ∈ (rg, b)Jc(y) it indicates
The smallest channel value of numerical value in the tri- chrominance channel value of RGB of the pixel.Ω(X)It indicates comprising the pixel and centered on the pixel
Pixel window,Indicate in the pixel window the smallest interim gray value in the interim gray value of all pixels.
As shown in figure 3, each square represents a pixel in Fig. 3.For the pixel 1 in Fig. 3, comprising the pixel 1 and
The centrally located pixel window of pixel 1 is dark border region in Fig. 3.If the tri- chrominance channel value of RGB of pixel 1 is respectively
46,58 and 128, then it can determine that the interim gray value of pixel 1 is the smallest channel of numerical value in tri- chrominance channel value of RGB by the above process
Value, also as 46.Similarly, it may be determined that in the pixel window in pixel 2 to 9 each pixel interim gray value.Finally, from the picture
Minimum interim gray value, the gray value as pixel 1 are chosen in plain window in pixel 1 to 9.Wherein, the picture out of this pixel window
Minimum interim gray value is chosen in element 1 to 9, as the gray value of pixel 1, the as process of mini-value filtering.
For other pixels, pixel window can also be first determined centered on pixel 2, and determines pixel 2 as procedure described above
Gray value.It should be noted that the pixel centered on edge pixel may be can not find for the pixel for being located at image border
Window can not then make the process of mini-value filtering to edge pixel, only need to be by numerical value in the tri- chrominance channel value of RGB of edge pixel most
Gray value of the small channel value as the edge pixel.
By the above process, that is, it can determine the gray value of each pixel in ID Card Image, and can accordingly obtain identity card
The gray level image namely dark channel image of image.
Content based on the above embodiment, as a kind of alternative embodiment, the embodiment of the present disclosure is not to determining dark channel diagram
The mode of target area as in comprising identity text information specifically limits, including but not limited to: carrying out to dark channel image
Image binaryzation obtains the bianry image of dark channel image, determines the target area in bianry image comprising identity text information.
Wherein, image binaryzation refers to that the gray value by pixel on image is set as 0 or 255, also i.e. by whole image
Show the process of apparent black and white effect.After by image binaryzation, the pixel of different gray values can be distinguished more obvious.
Wherein, for the identity text information in the pixel of presentation black in binary image, namely corresponding ID Card Image.Due to body
Part text information corresponds to the pixel of black in binary image, and the pixel of these black is usually to join together, and passes through picture
The plain modes such as retrieval one by one, it may be determined that include the target area of identity text information in bianry image.
Content based on the above embodiment is made two-value processing about to dark channel image, is obtained as a kind of alternative embodiment
To the mode of the bianry image of dark channel image, it is not limited in this embodiment of the present disclosure, including but not limited to: based on dark
In channel image in predeterminable area pixel gray value, the gray value threshold value that uses when determining two-value processing;By dark channel image
The gray value of middle first kind pixel is re-set as maximum gradation value, again by the gray value of the second class pixel in dark channel image
It is set as minimum gradation value;Wherein, first kind pixel is the pixel that gray value is less than gray value threshold value, and the second class pixel is gray scale
Value is greater than the pixel of gray value threshold value.
Wherein, the predeterminable area can be the corresponding entire area of dark channel image, can also part dark channel image
Corresponding partial region, it is not limited in this embodiment of the present disclosure.In view of identity text information is logical in ID Card Image
It is frequently located in the left side of ID Card Image, so that predeterminable area can be the left area of dark channel image.Correspondingly, two are being determined
When the gray value threshold value used when value processing, it can average to the gray value of left area all pixels, and will be calculated
Average value as gray value threshold value.
After determining gray value threshold value, the pixel of gray value threshold value is less than for gray value in dark channel image, it can be by this
The gray value of a little pixels is re-set as maximum gradation value 255.Gray value threshold value is greater than for gray value in dark channel image
The gray value of these pixels can be re-set as minimum gradation value 0, to obtain the bianry image of dark channel image by pixel.
Content based on the above embodiment, as a kind of alternative embodiment, the embodiment of the present disclosure is not to determining bianry image
In the mode of target area comprising identity text information specifically limit, including but not limited to: region is carried out to bianry image
Edge detection determines in bianry image to include identity text information to favored area;Based on each location information to favored area
And location information value interval of the identity text information in ID Card Image, it screens, obtains to favored area to all
Target area.
Since bianry image only includes the pixel of two kinds of gray values, so that both pixels can respectively surround different areas
Domain.Wherein, the pixel area defined color that gray value is 0 is black, namely comprising identity text information to favored area.
By edges of regions detection algorithm, that is, can determine in bianry image to include identity text information to favored area.
As shown in Figure 2, the ID card information in ID Card Image generally comprises several row informations.Wherein, line number is determining,
And every row information is usually within the scope of fixed position or fixed area.Therefore, can by way of counting in advance,
Determine the location information value interval of identity text information in ID Card Image namely the fixed area that identity text information is fallen into
Domain range, then by each location information to favored area and location information value area of the identity text information in ID Card Image
Between be compared, to screen out not comprising identity text information to favored area.
For example, as shown in Fig. 2, the first row information is " name XXX ".Wherein, " XXX " is practical name.And name is usual
2 words to its width of region shared by 4 words or so namely the first row information be usually have it is a certain range of.Based on this, i.e.,
It can determine location information value interval of the first row identity text information in ID Card Image.It is equally fallen to favored area if it exists
In the first row (namely the longitudinal length to favored area is in longitudinal extent of the first row), and it is somebody's turn to do the transverse direction to favored area
Width also in the corresponding location information value interval of the first row identity text information, that is, can determine that this can be used as mesh to favored area
Mark region.It by the above process, can be from all to filter out target area in favored area.
Content based on the above embodiment, as a kind of alternative embodiment, the embodiment of the present disclosure is not to according to target area
Determine that the mode of location information of the identity text information in ID Card Image specifically limits, including but not limited to: according to mesh
The location information of edge pixel point in region is marked, determines to include target area and the smallest rectangular area of area, by rectangular area
Location information of the location information as identity text information in ID Card Image.
Specifically, target area may exist jagged edge (namely positioned at edge pixel be not be neatly to arrange
Column), for the ease of obtaining the location information of identity text information, it may be determined that include target area and the smallest rectangle region of area
Domain.It include identity text information in the rectangular area, so as to push up the lower left corner apex coordinate of the rectangular area and the upper right corner
Location information of the point coordinate as identity text information in ID Card Image.
It should be noted that above-mentioned all alternative embodiments, can form the optional implementation of the disclosure using any combination
Example, this is no longer going to repeat them.
Content based on the above embodiment, the embodiment of the present disclosure provide a kind of identity text information detection device, the body
Part text information detection device is used to execute the identity text information detection method in above method embodiment.Referring to fig. 4, the dress
It sets and includes:
Module 401 is obtained, for obtaining the dark channel image of ID Card Image;
First determining module 402 is connect with the acquisition module, for determining in dark channel image comprising identity text envelope
The target area of breath;
Second determining module 403 is connect with first determining module, for determining identity text envelope according to target area
Cease the location information in ID Card Image.
As a kind of alternative embodiment, module 401 is obtained, tri- color of RGB for each pixel in identity-based card image
Channel value determines the gray value of each pixel, to obtain dark channel image.
As a kind of alternative embodiment, module 401 is obtained, is used for for any pixel in ID Card Image, according to default
Window size determines in ID Card Image comprising any pixel and the pixel window centered on any pixel;From pixel window
In each pixel interim gray value in, choose minimum interim gray value of the gray value as any pixel;Wherein, each pixel
Interim gray value be each pixel tri- chrominance channel value of RGB in the smallest channel value of numerical value.
As a kind of alternative embodiment, the first determining module 402, comprising:
Binarization unit obtains the bianry image of dark channel image for carrying out image binaryzation to dark channel image;
Determination unit, for determining the target area in bianry image comprising identity text information.
As a kind of alternative embodiment, binarization unit, for the ash based on pixel in predeterminable area in dark channel image
Angle value determines the gray value threshold value used when two-value processing;The gray value of first kind pixel in dark channel image is reset
For maximum gradation value, the gray value of the second class pixel in dark channel image is re-set as minimum gradation value;Wherein, the first kind
Pixel is the pixel that gray value is less than gray value threshold value, and the second class pixel is the pixel that gray value is greater than gray value threshold value.
As a kind of alternative embodiment, determination unit determines binary map for carrying out edges of regions detection to bianry image
It include identity text information as in favored area;Based on each location information to favored area and identity text information in body
Location information value interval in part card image, screens to favored area to all, obtains target area.
As a kind of alternative embodiment, the second determining module 403, for the position according to edge pixel point in target area
Information determines to include target area and the smallest rectangular area of area, using the location information of rectangular area as identity text envelope
Cease the location information in ID Card Image.
The device that the embodiment of the present disclosure provides, by the dark channel image for obtaining ID Card Image.Determine dark channel image
In include identity text information target area, position of the identity text information in ID Card Image is determined according to target area
Information.Since dark channel image can be converted by ID Card Image, the interference of illumination and ID Card Image background can be eliminated, thus
It can guarantee the accuracy of recognition result.
Fig. 5 illustrates a kind of entity structure schematic diagram of identity text information detection device, as shown in figure 5, the equipment can
To include: processor (processor) 510,520, memory communication interface (Communications Interface)
(memory) 530 and bus 540, wherein processor 510, communication interface 520, memory 530 are completed mutually by bus 540
Between communication.Communication interface 540 can be used for the transmission of the information between server and smart television.Processor 510 can call
Logical order in memory 530, to execute following method: obtaining the dark channel image of ID Card Image;Determine dark channel diagram
Comprising the target area of identity text information as in, position of the identity text information in ID Card Image is determined according to target area
Confidence breath.
In addition, the logical order in above-mentioned memory 530 can be realized by way of SFU software functional unit and conduct
Independent product when selling or using, can store in a computer readable storage medium.Based on this understanding, originally
Substantially the part of the part that contributes to existing technology or the technical solution can be in other words for disclosed technical solution
The form of software product embodies, which is stored in a storage medium, including some instructions to
So that a computer equipment (can be personal computer, server or the network equipment etc.) executes each implementation of the disclosure
The all or part of the steps of example method.And storage medium above-mentioned includes: USB flash disk, mobile hard disk, read-only memory (ROM, Read-
Only Memory), random access memory (RAM, Random Access Memory), magnetic or disk etc. are various can be with
Store the medium of program code.
The embodiment of the present disclosure provides a kind of non-transient computer readable storage medium, the non-transient computer readable storage medium
Matter stores computer instruction, which makes computer execute method provided by above-described embodiment, for example, obtains
The dark channel image of ID Card Image;The target area in dark channel image comprising identity text information is determined, according to target area
Domain determines location information of the identity text information in ID Card Image.
Those of ordinary skill in the art will appreciate that: realize that all or part of the steps of above method embodiment can pass through
The relevant hardware of program instruction is completed, and program above-mentioned can be stored in a computer readable storage medium, the program
When being executed, step including the steps of the foregoing method embodiments is executed;And storage medium above-mentioned includes: ROM, RAM, magnetic disk or light
The various media that can store program code such as disk.
The apparatus embodiments described above are merely exemplary, wherein described, unit can as illustrated by the separation member
It is physically separated with being or may not be, component shown as a unit may or may not be physics list
Member, it can it is in one place, or may be distributed over multiple network units.It can be selected according to the actual needs
In some or all of the modules achieve the purpose of the solution of this embodiment.Those of ordinary skill in the art are not paying creativeness
Labour in the case where, it can understand and implement.
Through the above description of the embodiments, those skilled in the art can be understood that each embodiment can
It realizes by means of software and necessary general hardware platform, naturally it is also possible to pass through hardware.Based on this understanding, on
Stating technical solution, substantially the part that contributes to existing technology can be embodied in the form of software products in other words, should
Computer software product may be stored in a computer readable storage medium, such as ROM/RAM, magnetic disk, CD, including several fingers
It enables and using so that a computer equipment (can be personal computer, server or the network equipment etc.) executes each implementation
Method described in certain parts of example or embodiment.
Particular embodiments described above has carried out further in detail the purpose of the disclosure, technical scheme and beneficial effects
Describe in detail it is bright, it is all it should be understood that be not limited to the disclosure the foregoing is merely the specific embodiment of the disclosure
Within the spirit and principle of the disclosure, any modification, equivalent substitution, improvement and etc. done should be included in the guarantor of the disclosure
Within the scope of shield.
So far, attached drawing is had been combined the embodiment of the present disclosure is described in detail.According to above description, art technology
Personnel should have clear understanding to disclosure identity text information detection method and device.
It should be noted that in attached drawing or specification text, the implementation for not being painted or describing is affiliated technology
Form known to a person of ordinary skill in the art, is not described in detail in field.In addition, the above-mentioned definition to each element and method is simultaneously
It is not limited only to various specific structures, shape or the mode mentioned in embodiment, those of ordinary skill in the art can carry out letter to it
It singly changes or replaces.
Certainly, according to actual needs, the step of method of disclosure also includes other, due to the same disclosure innovation without
It closes, details are not described herein again.
Particular embodiments described above has carried out further in detail the purpose of the disclosure, technical scheme and beneficial effects
Describe in detail bright, it should be understood that the foregoing is merely the specific embodiment of the disclosure, be not limited to the disclosure, it is all
Within the spirit and principle of the disclosure, any modification, equivalent substitution, improvement and etc. done should be included in the protection of the disclosure
Within the scope of.
Claims (10)
1. a kind of identity text information detection method, comprising:
Obtain the dark channel image of ID Card Image;And
It determines the target area in the dark channel image comprising identity text information, the body is determined according to the target area
Location information of part text information in the ID Card Image.
2. according to the method described in claim 1, wherein, the dark channel image for obtaining ID Card Image the step of in,
According to the tri- chrominance channel value of RGB of pixel each in the ID Card Image, the gray value of each pixel is determined, to obtain
The dark channel image of ID Card Image.
3. according to the method described in claim 2, wherein, according to tri- chrominance channel RGB of pixel each in the ID Card Image
The step of being worth, determining the gray value of each pixel, comprising:
For any pixel in the ID Card Image, according to preset window size, determine in the ID Card Image comprising institute
State any pixel and the pixel window centered on any pixel;
From minimum interim gray value in the interim gray value of all pixels, is chosen in the pixel window as any pixel
Gray value;Wherein, the interim gray value of each pixel is the smallest channel of numerical value in the tri- chrominance channel value of RGB of each pixel
Value.
4. according to the method described in claim 1, wherein, the mesh of identity text information is included in determining the dark channel image
In the step of marking region:
Image binaryzation processing is carried out to the dark channel image, obtains the bianry image of the dark channel image, based on described
Bianry image determines the target area in the dark channel image comprising identity text information.
5. according to the method described in claim 4, wherein, carrying out image binaryzation processing to the dark channel image, obtaining institute
State the bianry image of dark channel image, comprising:
Based on the gray value of pixel in predeterminable area in the dark channel image, the gray scale used when image binaryzation processing is determined
It is worth threshold value;
Maximum gradation value is set by the gray value of first kind pixel in the dark channel image, by the dark channel image
The gray value of two class pixels is set as minimum gradation value, to obtain the bianry image of the dark channel image;Wherein, described
A kind of pixel is the pixel that gray value is less than the gray value threshold value, and the second class pixel is that gray value is greater than the gray value
The pixel of threshold value.
6. according to the method described in claim 4, wherein, being determined in the dark channel image based on the bianry image comprising body
The step of target area of part text information, comprising:
Edges of regions detection is carried out to the bianry image, determine in the bianry image comprising the identity text information to
Favored area;
Position letter based on each location information to favored area and the identity text information in the ID Card Image
Value interval is ceased, is screened to all to favored area, determines the target in the dark channel image comprising identity text information
Region.
7. described to determine that the identity text information exists according to the target area according to the method described in claim 1, wherein
Location information in the ID Card Image, comprising:
According to the location information of edge pixel point in the target area, determine to include the target area and the smallest square of area
Shape region is believed the location information of the rectangular area as position of the identity text information in the ID Card Image
Breath.
8. a kind of identity text information detection device, comprising:
Module is obtained, for obtaining the dark channel image of ID Card Image;
First determining module, for determining the target area in the dark channel image comprising identity text information;And
Second determining module, for determining the identity text information in the ID Card Image according to the target area
Location information.
9. a kind of identity text information detection device, comprising:
At least one processor;And
At least one processor being connect with the processor communication, in which:
The memory is stored with the program instruction that can be executed by the processor, and the processor calls described program to instruct energy
Enough methods executed as described in any one of claims 1 to 7.
10. a kind of non-transient computer readable storage medium, the non-transient computer readable storage medium storage computer refers to
It enables, the computer instruction makes the computer execute the method as described in any one of claims 1 to 7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810840958.XA CN109101960A (en) | 2018-07-26 | 2018-07-26 | Identity text information detection method and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810840958.XA CN109101960A (en) | 2018-07-26 | 2018-07-26 | Identity text information detection method and device |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109101960A true CN109101960A (en) | 2018-12-28 |
Family
ID=64847629
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810840958.XA Pending CN109101960A (en) | 2018-07-26 | 2018-07-26 | Identity text information detection method and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109101960A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110297920A (en) * | 2019-06-24 | 2019-10-01 | 江苏圆昱智能科技有限公司 | A kind of yard of fingerprint method for anti-counterfeit |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101008985A (en) * | 2007-01-18 | 2007-08-01 | 章毅 | Seal identification system and controlling method thereof |
CN103065127A (en) * | 2012-12-30 | 2013-04-24 | 信帧电子技术(北京)有限公司 | Method and device for recognizing human face in fog day image |
CN103488984A (en) * | 2013-10-11 | 2014-01-01 | 从兴技术有限公司 | Method and device for identifying second-generation identity cards based on intelligent mobile equipment |
US20140355883A1 (en) * | 2013-06-03 | 2014-12-04 | Alipay.com Co., Ltd. | Method and system for recognizing information |
CN104680161A (en) * | 2015-01-09 | 2015-06-03 | 安徽清新互联信息科技有限公司 | Digit recognition method for identification cards |
CN104680130A (en) * | 2015-01-09 | 2015-06-03 | 安徽清新互联信息科技有限公司 | Chinese character recognition method for identification cards |
CN106250831A (en) * | 2016-07-22 | 2016-12-21 | 北京小米移动软件有限公司 | Image detecting method, device and the device for image detection |
CN107644222A (en) * | 2016-07-22 | 2018-01-30 | 花生米浙江数据信息服务股份有限公司 | Information locating method in a kind of ID Card Image |
-
2018
- 2018-07-26 CN CN201810840958.XA patent/CN109101960A/en active Pending
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101008985A (en) * | 2007-01-18 | 2007-08-01 | 章毅 | Seal identification system and controlling method thereof |
CN103065127A (en) * | 2012-12-30 | 2013-04-24 | 信帧电子技术(北京)有限公司 | Method and device for recognizing human face in fog day image |
US20140355883A1 (en) * | 2013-06-03 | 2014-12-04 | Alipay.com Co., Ltd. | Method and system for recognizing information |
CN103488984A (en) * | 2013-10-11 | 2014-01-01 | 从兴技术有限公司 | Method and device for identifying second-generation identity cards based on intelligent mobile equipment |
CN104680161A (en) * | 2015-01-09 | 2015-06-03 | 安徽清新互联信息科技有限公司 | Digit recognition method for identification cards |
CN104680130A (en) * | 2015-01-09 | 2015-06-03 | 安徽清新互联信息科技有限公司 | Chinese character recognition method for identification cards |
CN106250831A (en) * | 2016-07-22 | 2016-12-21 | 北京小米移动软件有限公司 | Image detecting method, device and the device for image detection |
CN107644222A (en) * | 2016-07-22 | 2018-01-30 | 花生米浙江数据信息服务股份有限公司 | Information locating method in a kind of ID Card Image |
Non-Patent Citations (1)
Title |
---|
方徐伟等: "基于投影法和 Caffe框架的身份证分割算法", 《计算机工程与应用》 * |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110297920A (en) * | 2019-06-24 | 2019-10-01 | 江苏圆昱智能科技有限公司 | A kind of yard of fingerprint method for anti-counterfeit |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US9135722B2 (en) | Perceptually lossless color compression | |
US9769354B2 (en) | Systems and methods of processing scanned data | |
CN110008954B (en) | Complex background text image extraction method and system based on multi-threshold fusion | |
US8103104B2 (en) | Text extraction and its application to compound document image compression | |
US8300141B2 (en) | Portable terminal apparatus, image output apparatus, method of controlling portable terminal apparatus, and recording medium | |
JP5810628B2 (en) | Image processing apparatus and image processing program | |
US20050047656A1 (en) | Systems and methods of detecting and correcting redeye in an image suitable for embedded applications | |
JP2016517587A (en) | Classification of objects in digital images captured using mobile devices | |
KR101597739B1 (en) | Image processing apparatus, image processing method, and computer readable medium | |
CN102955943A (en) | Image processing apparatus, and image processing method | |
US7400776B2 (en) | Visual enhancement for reduction of visual noise in a text field | |
JP6779688B2 (en) | Image processing equipment, image processing method, computer program | |
JP2000175038A (en) | Image binary processing system on area basis | |
KR100524072B1 (en) | Method for improving image quality | |
JP6890427B2 (en) | Car number recognition device | |
KR101549495B1 (en) | An apparatus for extracting characters and the method thereof | |
WO2019201184A1 (en) | License plate enhancement method, apparatus and electronic device | |
CN111259891B (en) | Method, device, equipment and medium for identifying identity card in natural scene | |
KR102311367B1 (en) | Image processing apparatus, image processing method, and storage medium | |
WO2018219005A1 (en) | File processing method and terminal | |
CN109101960A (en) | Identity text information detection method and device | |
CN113569859A (en) | Image processing method and device, electronic equipment and storage medium | |
CN112991470B (en) | Certificate photo background color checking method and system under complex background | |
CN108596874B (en) | Image definition judging method and device, computer equipment and product | |
Selami | Analysis of image features taken from different camera types |
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: 20181228 |