CN110309738A - The method that a kind of pair of OCT fingerprint image is labeled - Google Patents
The method that a kind of pair of OCT fingerprint image is labeled Download PDFInfo
- Publication number
- CN110309738A CN110309738A CN201910522011.9A CN201910522011A CN110309738A CN 110309738 A CN110309738 A CN 110309738A CN 201910522011 A CN201910522011 A CN 201910522011A CN 110309738 A CN110309738 A CN 110309738A
- Authority
- CN
- China
- Prior art keywords
- fingerprint image
- dimensional
- fingerprint
- dimentional
- oct
- 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.)
- Granted
Links
Classifications
-
- 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
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/64—Three-dimensional objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/12—Fingerprints or palmprints
- G06V40/13—Sensors therefor
- G06V40/1318—Sensors therefor using electro-optical elements or layers, e.g. electroluminescent sensing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/12—Fingerprints or palmprints
- G06V40/1347—Preprocessing; Feature extraction
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Data Mining & Analysis (AREA)
- Human Computer Interaction (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Collating Specific Patterns (AREA)
Abstract
The present invention provides the method that a kind of pair of OCT fingerprint image is labeled, comprising the following steps: step S1 reads the three-dimensional fingerprint image of preset quantity；Step S2 pre-processes the three-dimensional fingerprint image, obtains the corresponding one-dimensional vector of three-dimensional fingerprint image, one-dimensional vector is then combined into two-dimentional fingerprint image according to the sequence of initial three-dimensional fingerprint image；Step S3 selects the tab area of two-dimentional fingerprint image, forms two-dimentional fingerprint label；Two-dimentional fingerprint label mapping is returned the three-dimensional space of the three-dimensional fingerprint image by mapping algorithm by step S4.The present invention is by being processed into two-dimentional fingerprint image for three-dimensional fingerprint image, and then two-dimentional fingerprint image can be labeled, and it is returned two-dimentional fingerprint label mapping is formed in the three-dimensional space of the three-dimensional fingerprint image, to realize the mark to OCT fingerprint image, so as to find out each category feature of fingerprint under tab area more accurately.
Description
Technical field
It is labeled the present invention relates to a kind of OCT fingerprint image processing method more particularly to a kind of pair of OCT fingerprint image
Method.
Background technique
With the maturation of Optical coherence tomography, we be can use in OCT three-dimensional fingerprint image analysis fingerprint
Portion's information, the OCT is optical coherence tomography, therefore conventional two-dimensional fingerprint image biological characteristic can preferably be avoided to know
Other faced variety of problems, for example, avoid finger surface there are various spots, finger epidermis is badly damaged the problems such as.But it is existing
Have in technology, there is no for the method being labeled based on the OCT fingerprint image that OCT fingerprint imaging technique is formed.
Summary of the invention
It can be to the side that OCT fingerprint image is labeled the technical problem to be solved by the present invention is to need to provide one kind
Method.
In this regard, the present invention provides the method that a kind of pair of OCT fingerprint image is labeled, comprising the following steps:
Step S1 reads the three-dimensional fingerprint image of preset quantity；
Step S2 pre-processes the three-dimensional fingerprint image, obtains the corresponding one-dimensional vector of three-dimensional fingerprint image, then will
One-dimensional vector is combined into two-dimentional fingerprint image according to the sequence of initial three-dimensional fingerprint image；
Step S3 selects the tab area of two-dimentional fingerprint image, forms two-dimentional fingerprint label；
Two-dimentional fingerprint label mapping is returned the three-dimensional space of the three-dimensional fingerprint image by mapping algorithm by step S4.
A further improvement of the present invention is that the step S2 includes following sub-step:
Each Zhang San dimension fingerprint image is processed into the greyish white picture of fingerprint by step S201；
The greyish white picture of fingerprint is carried out cumulative summation according to fingerprint length, is combined into corresponding to the greyish white picture of fingerprint by step S202
One-dimensional vector；
One-dimensional vector corresponding to the greyish white picture of fingerprint is combined into two according to the sequence of initial three-dimensional fingerprint image by step S203
Matrix is tieed up, two-dimentional fingerprint image is obtained.
A further improvement of the present invention is that reading 400 OCT three-dimensional fingerprint images in the step S1；The step
In S202, the greyish white picture of every fingerprint is divided by 1500 column vectors according to fingerprint length, to 1500 column vectors respectively into
The cumulative summation of row has obtained 1500 numerical value, then that 1500 numerical value are combined sequentially into the greyish white picture institute of the fingerprint in order is right
The one-dimensional vector answered, and so on, 400 greyish white pictures of fingerprint are handled to obtain 400 corresponding one-dimensional vectors.
A further improvement of the present invention is that in the step S202, also by each numerical value in each one-dimensional vector
Be currently located the summation of vector divided by this numerical value, and then realize normalization, after obtaining 400 normalizeds it is one-dimensional to
Amount.
A further improvement of the present invention is that in the step S203, by 400 one-dimensional vectors according to initial three-dimensional fingerprint
The sequence of image is combined into two-dimensional matrix, obtains the two-dimentional fingerprint image after OCT three-dimensional fingerprint image is rebuild.
A further improvement of the present invention is that further including step S5, in the step S5,400 two dimensions will be regenerated
Fingerprint image and 400 greyish white pictures of fingerprint are saved into corresponding file.
A further improvement of the present invention is that the step S3 includes following sub-step:
Step S301 selects the tab area of two-dimentional fingerprint image by mouse or keyboard；
Step S302 is labeled the tab area by matrix dimensioning algorithm or circle dimensioning algorithm, obtains two-dimentional fingerprint
Label.
A further improvement of the present invention is that in the step S3, by matrix dimensioning algorithm to the tab area into
The process of rower note is as follows: carrying out the selection of the first matrix dot to two-dimentional fingerprint image by mouse or keyboard；Then pass through mouse
The selection of mobile the second matrix dot of carry out of mark or keyboard, second matrix dot are the matrix diagonals coordinate of the first matrix dot
Point, and then the length of the matrix and wide is respectively obtained by the matrix coordinate difference where the first matrix dot and the second matrix dot；Finally
Change the picture color in the matrix to complete to mark, two dimensional image at this time is two-dimentional fingerprint label.
A further improvement of the present invention is that being carried out by circle dimensioning algorithm to the tab area in the step S3
The process of mark is as follows: first passing through mouse or keyboard and carries out the first circle coordinates point and the second circle coordinates point to two-dimentional fingerprint image
It chooses, radical sign is opened to the coordinate difference of two squares of the first circle coordinates point and the second circle coordinates point and obtains diameter of a circle, and then obtain circle
Radius；Then the midpoint for calculating two the first circle coordinates points and the second circle coordinates point, using this midpoint as the center of circle；Finally with
Centered on the center of circle, the picture color in the circle is changed to complete to mark with the radius of the circle, two dimensional image at this time is two dimension
Fingerprint label.
A further improvement of the present invention is that two-dimentional fingerprint label mapping is returned three-dimensional by mapping algorithm by the step S4
The realization process in space are as follows: using putting in order for initial three-dimensional fingerprint image, two-dimentional fingerprint label is corresponded to each
Zhang San ties up on the width coordinate of fingerprint image, and then obtains the three-dimensional dactylotype information for having two-dimentional fingerprint label.
Compared with prior art, the beneficial effects of the present invention are: by the way that three-dimensional fingerprint image is processed into two-dimentional fingerprint
Image, and then two-dimentional fingerprint image can be labeled, and two-dimentional fingerprint label mapping will be formed and return the three-dimensional fingerprint image
In the three-dimensional space of picture, to realize that the OCT fingerprint image for marking completion can more accurately to the mark of OCT fingerprint image
Each category feature for finding out fingerprint under tab area can be used in all kinds of neural networks based on OCT fingerprint image, to expand
The application of OCT fingerprint image provides good data basis.
Detailed description of the invention
Fig. 1 is the workflow schematic diagram of an embodiment of the present invention；
Fig. 2 is the three-dimensional fingerprint image schematic diagram of an embodiment of the present invention；
Fig. 3 is the working principle that an embodiment of the present invention was handled three-dimensional fingerprint image and be combined into two-dimentional fingerprint image
Schematic diagram；
Fig. 4 is the schematic diagram of individual OCT fingerprint image with tab area of an embodiment of the present invention.
Specific embodiment
With reference to the accompanying drawing, preferably embodiment of the invention is described in further detail.
As shown in Figure 1, this example provides the method that a kind of pair of OCT fingerprint image is labeled, comprising the following steps:
Step S1 reads the three-dimensional fingerprint image of preset quantity；
Step S2 pre-processes the three-dimensional fingerprint image, obtains the corresponding one-dimensional vector of three-dimensional fingerprint image, then will
One-dimensional vector is combined into two-dimentional fingerprint image according to the sequence of initial three-dimensional fingerprint image；
Step S3 selects the tab area of two-dimentional fingerprint image, forms two-dimentional fingerprint label；
Two-dimentional fingerprint label mapping is returned the three-dimensional space of the three-dimensional fingerprint image by mapping algorithm by step S4.
Three-dimensional fingerprint image described in this example is OCT three-dimensional fingerprint image, can also abbreviation OCT fingerprint image；Described in this example
The three-dimensional fingerprint image (3D fingerprint image) for the user that step S1 is acquired by OCT (optical coherence tomography) is as reading
Data, preferably acquire and read the same finger at least 400 three-dimensional fingerprint images of same user as fingerprint image
As data, i.e., the described preset quantity is the numerical value that predefined setting is carried out according to actual needs, preferably 400.
As shown in Fig. 2, this example places 400 three-dimensional fingerprint images in three-dimensional coordinate, wherein X-axis indicates that fingerprint is long
Degree, i.e., the picture length of three-dimensional fingerprint image, what the numerical value of X-axis indicated is the width coordinate of three-dimensional fingerprint image；Y-axis indicates
The numerical value that the quantity of the three-dimensional fingerprint image of 400 (or other preset quantities), i.e. Y-axis represent preset quantity；Z axis expression refers to
Line depth, i.e., the picture width of three-dimensional fingerprint image.
This example cardinal principle is 400 (or other preset quantities) three-dimensional fingerprint image/tri- formed using OCT technology
Fingerprint picture is tieed up, three-dimensional fingerprint image is first subjected to gray processing, the fingerprint of fingerprint inside fingerprint image is tieed up according still further to each Zhang San
Depth (i.e. using z-axis as the picture width in direction in Fig. 2) carries out the tired of the direction z and tires out and be normalized later, obtain 400
The sequence for the picture that 400 vectors are formed according to OCT technology is finally combined into a two-dimensional matrix again by the one-dimensional vector of item,
Then this matrix is exactly the two-dimentional fingerprint image after a width three-dimensional fingerprint image is rebuild.
After mark two-dimentional fingerprint image reduction cardinal principle be according to the sequence of original three-dimensional fingerprint image, will
The two-dimentional fingerprint image of mark maps back in the three-dimensional fingerprint image of OCT, and during mapping, data processing is concentrated in marking
Region is infused, these tab areas are newly to be converted into fingerprint cross section, we can be experimentally observed their phases in this way
The three-dimensional structure information answered, and the mark to OCT fingerprint image is realized by the mark to two-dimentional fingerprint image, as shown in figure 4,
White area in Fig. 4 is exactly tab area.
Step S2 described in this example carries out the three-dimensional fingerprint image according to the fingerprint depth that each Zhang San ties up fingerprint image pre-
Processing, obtains the corresponding one-dimensional vector of three-dimensional fingerprint image, then by one-dimensional vector according to the sequence of initial three-dimensional fingerprint image
It is combined into two-dimentional fingerprint image.
Specifically, as shown in figure 3, step S2 described in this example includes following sub-step:
Each Zhang San dimension fingerprint image is processed into the greyish white picture of fingerprint by step S201；
The greyish white picture of fingerprint is carried out cumulative summation according to fingerprint length, is combined into corresponding to the greyish white picture of fingerprint by step S202
One-dimensional vector；
One-dimensional vector corresponding to the greyish white picture of fingerprint is combined into two according to the sequence of initial three-dimensional fingerprint image by step S203
Matrix is tieed up, two-dimentional fingerprint image is obtained.
In Fig. 3, in left-half, what Z-direction indicated is the depth of fingerprint in every fingerprint image, and Y direction indicates
Be OCT fingerprint image quantity, X-direction indicate is every fingerprint image length；In right half part, four two dimensions refer to
Print image indicates that the different depth (Z axis) for having chosen 4 fingerprints respectively carries out the result of two-dimentional fingerprint building.
400 OCT three-dimensional fingerprint images are read in step S1 described in this example, as long as this process reading read passes through
OCT acquisition 400 or other preset quantities three-dimensional fingerprint image.The step S201 will be each according to fingerprint depth
Zhang San ties up fingerprint image and is processed into the greyish white picture of fingerprint, i.e., RGB color picture is become greyish white picture, then in the next steps
Realize cumulative and normalization.
In step S202 described in this example, the greyish white picture of every fingerprint is divided into according to fingerprint length (i.e. X-axis in Fig. 2)
1500 column vectors carry out cumulative summation respectively to 1500 column vectors, have obtained 1500 numerical value, then 1500 numerical value are pressed
Sequence is combined sequentially into one-dimensional vector corresponding to the greyish white picture of the fingerprint, and so on, the greyish white picture of 400 fingerprints is carried out
400 corresponding one-dimensional vectors are obtained in processing.
Step S202 described in this example is further preferably by each numerical value in each one-dimensional vector divided by the current institute of this numerical value
In the summation of vector, and then realize normalization, the one-dimensional vector after obtaining 400 normalizeds.Specifically, by each one
Each numerical value in dimensional vector and then realizes normalization divided by the summation of one-dimensional vector where this numerical value, obtains at normalization
400 new one-dimensional vectors after reason.
In step S203 described in this example, 400 one-dimensional vectors are combined into two according to the sequence of initial three-dimensional fingerprint image
Matrix is tieed up, the two-dimentional fingerprint image after OCT three-dimensional fingerprint image is rebuild is obtained.
That is, the initial three-dimensional that step S203 forms 400 one-dimensional vectors according to OCT image technology described in this example
The sequence of fingerprint image is combined into a two-dimensional matrix, i.e., the described step S203 is by 400 y-axis sides of the one-dimensional vector in Fig. 2
To being combined to obtain two-dimensional matrix by the sequence of initial three-dimensional fingerprint image, then this two-dimensional matrix is exactly a width three-dimensional fingerprint
Two-dimentional fingerprint image after image reconstruction.
Certainly, above-mentioned that the greyish white picture of fingerprint is subjected to cumulative summation and normalized in step S202 described in this example
Realization process belongs to preferred realization process, and the realization process that the step S203 is combined into two-dimensional matrix also belongs to preferably
Realization process, this example are that the greyish white picture of fingerprint is first processed into corresponding one-dimensional vector and then is combined into two-dimensional matrix, so as to
Follow-up data processing；In practical applications, the step S2 can also be using realizing, as long as by three-dimensional fingerprint image otherwise
As being processed into two-dimensional matrix, mark can be realized so as to subsequent.
Step S3 described in this example includes following sub-step:
Step S301 selects the tab area of two-dimentional fingerprint image by mouse or keyboard；
Step S302 is labeled the tab area by matrix dimensioning algorithm or circle dimensioning algorithm, obtains two-dimentional fingerprint
Label.
Wherein, in step S3 described in this example, the process being labeled by matrix dimensioning algorithm to the tab area is such as
Under: the selection of the first matrix dot is carried out to two-dimentional fingerprint image by mouse or keyboard；Then pass through the movement of mouse or keyboard
The selection of the second matrix dot is carried out, second matrix dot is the matrix diagonals coordinate points of the first matrix dot, and then passes through first
Matrix coordinate difference where matrix dot and the second matrix dot respectively obtains the length and width of the matrix；Finally change the figure in the matrix
Piece color is to complete to mark, for example be changed to black or white etc., and Fig. 4 is that the picture color of matrix is changed to white, at this time
Two dimensional image is two-dimentional fingerprint label, as shown in Figure 4.The matrix refer to the matrix for mark, state the first matrix dot
Refer to choosing that first point of matrix tab area, second matrix dot refer to choosing second of matrix tab area
Point, the two put the diagonal coordinate points as matrix, can be realized matrix mark.
In step S3 described in this example, the process being labeled by circle dimensioning algorithm to the tab area is as follows: first leading to
The selection that mouse or keyboard carry out the first circle coordinates point and the second circle coordinates point to two-dimentional fingerprint image is crossed, to the first circle coordinates point
Radical sign is opened with the coordinate difference of two squares of the second circle coordinates point and obtains diameter of a circle, and then obtains round radius (diameter can be obtained divided by 2
To radius)；Then the midpoint for calculating two the first circle coordinates points and the second circle coordinates point, using this midpoint as the center of circle；Most
Afterwards centered on the center of circle, the picture color in the circle is changed to complete to mark with the radius of the circle, for example, be changed to black or
White etc., two dimensional image at this time are two-dimentional fingerprint label.The first circle coordinates point refers to choosing circle markings region
First point, the second circle coordinates point refer to choosing second point in circle markings region, the two points obtain round mark
The center of circle and the radius for infusing region, can be realized circle markings.
Two-dimentional fingerprint label mapping is returned the realization process of three-dimensional space by mapping algorithm by step S4 described in this example are as follows: benefit
With initial three-dimensional fingerprint image put in order and the step S2 in two-dimentional fingerprint image and the initial three-dimensional fingerprint image
The two-dimentional fingerprint label is corresponded to each Zhang San and ties up the width coordinate of fingerprint image (i.e. in Fig. 2 by the corresponding relationship of picture
X-axis) on, and change width corresponding to all three-dimensional fingerprint images toward the depth direction of initial three-dimensional fingerprint image in this approach
Coordinate value is spent, and then obtains the three-dimensional dactylotype information for having two-dimentional fingerprint label
Step S4 described in this example is used to that two-dimentional fingerprint label mapping to be returned three-dimensional space by mapping algorithm, and algorithm can concentrate on
The tab area of reconstruction, these tab areas are newly to be converted into fingerprint cross section, and specific implementation process is: utilizing initial three-dimensional
Put in order and the two-dimentional fingerprint image one-to-one relationship in the y-axis direction of fingerprint image, by the two-dimentional fingerprint label
(including identified areas) corresponds onto the width coordinate (i.e. x-axis in Fig. 2) of the three-dimensional fingerprint image of each OCT；So
Each Zhang San, which is changed, toward the depth direction of OCT original fingerprint image (i.e. y-axis in Fig. 2) afterwards ties up width corresponding to fingerprint image
Coordinate value can be realized two-dimentional fingerprint label mapping returning three-dimensional space.
This example further preferably includes step S5, in the step S5, will regenerate 400 two-dimentional fingerprint images and 400
The greyish white picture of fingerprint is saved into corresponding file, is convenient for subsequent data processing.
In conclusion this example is by being processed into two-dimentional fingerprint image for three-dimensional fingerprint image, and then can be to two-dimentional fingerprint
Image is labeled, and is returned two-dimentional fingerprint label mapping is formed in the three-dimensional space of the three-dimensional fingerprint image, with realization pair
The mark of OCT fingerprint image, the OCT fingerprint image for marking completion can find out all kinds of of fingerprint under tab area more accurately
Feature can be used in all kinds of neural networks based on OCT fingerprint image, provide to expand the application of OCT fingerprint image
Good data basis.
The above content is a further detailed description of the present invention in conjunction with specific preferred embodiments, and it cannot be said that
Specific implementation of the invention is only limited to these instructions.For those of ordinary skill in the art to which the present invention belongs, exist
Under the premise of not departing from present inventive concept, a number of simple deductions or replacements can also be made, all shall be regarded as belonging to of the invention
Protection scope.
Claims (10)
1. the method that a kind of pair of OCT fingerprint image is labeled, which comprises the following steps:
Step S1 reads the three-dimensional fingerprint image of preset quantity；
Step S2 pre-processes the three-dimensional fingerprint image, obtains the corresponding one-dimensional vector of three-dimensional fingerprint image, then will
One-dimensional vector is combined into two-dimentional fingerprint image according to the sequence of initial three-dimensional fingerprint image；
Step S3 selects the tab area of two-dimentional fingerprint image, forms two-dimentional fingerprint label；
Two-dimentional fingerprint label mapping is returned the three-dimensional space of the three-dimensional fingerprint image by mapping algorithm by step S4.
2. the method according to claim 1 being labeled to OCT fingerprint image, which is characterized in that the step S2 packet
Include following sub-step:
Each Zhang San dimension fingerprint image is processed into the greyish white picture of fingerprint by step S201；
The greyish white picture of fingerprint is carried out cumulative summation according to fingerprint length, is combined into corresponding to the greyish white picture of fingerprint by step S202
One-dimensional vector；
One-dimensional vector corresponding to the greyish white picture of fingerprint is combined into two according to the sequence of initial three-dimensional fingerprint image by step S203
Matrix is tieed up, two-dimentional fingerprint image is obtained.
3. the method according to claim 2 being labeled to OCT fingerprint image, which is characterized in that in the step S1
Read 400 OCT three-dimensional fingerprint images；In the step S202, the greyish white picture of every fingerprint is divided into according to fingerprint length
1500 column vectors carry out cumulative summation respectively to 1500 column vectors, have obtained 1500 numerical value, then 1500 numerical value are pressed
Sequence is combined sequentially into one-dimensional vector corresponding to the greyish white picture of the fingerprint, and so on, the greyish white picture of 400 fingerprints is carried out
Processing obtains 400 corresponding one-dimensional vectors.
4. the method according to claim 3 being labeled to OCT fingerprint image, which is characterized in that the step S202
In, each numerical value in each one-dimensional vector is also currently located to the summation of vector divided by this numerical value, and then realize normalizing
Change, the one-dimensional vector after obtaining 400 normalizeds.
5. the method according to claim 3 being labeled to OCT fingerprint image, which is characterized in that the step S203
In, 400 one-dimensional vectors are combined into two-dimensional matrix according to the sequence of initial three-dimensional fingerprint image, obtain OCT three-dimensional fingerprint image
As the two-dimentional fingerprint image after rebuilding.
6. the method according to claim 3 being labeled to OCT fingerprint image, which is characterized in that it further include step S5,
In the step S5,400 two-dimentional fingerprint images will be regenerated and 400 greyish white pictures of fingerprint are saved to corresponding file
In.
7. according to claim 1 to the method being labeled described in 5 any one to OCT fingerprint image, which is characterized in that institute
Stating step S3 includes following sub-step:
Step S301 selects the tab area of two-dimentional fingerprint image by mouse or keyboard；
Step S302 is labeled the tab area by matrix dimensioning algorithm or circle dimensioning algorithm, obtains two-dimentional fingerprint
Label.
8. the method according to claim 7 being labeled to OCT fingerprint image, which is characterized in that in the step S3,
The process being labeled by matrix dimensioning algorithm to the tab area is as follows: by mouse or keyboard to two-dimentional fingerprint image
Carry out the selection of the first matrix dot；Then pass through the selection of mouse or mobile the second matrix dot of carry out of keyboard, second square
Lattice point is the matrix diagonals coordinate points of the first matrix dot, and then passes through the matrix coordinate where the first matrix dot and the second matrix dot
Difference respectively obtains the length and width of the matrix；Change the picture color in the matrix finally to complete to mark, two dimensional image at this time
For two-dimentional fingerprint label.
9. the method according to claim 7 being labeled to OCT fingerprint image, which is characterized in that in the step S3,
The process being labeled by circle dimensioning algorithm to the tab area is as follows: first passing through mouse or keyboard to two-dimentional fingerprint image
The selection for carrying out the first circle coordinates point and the second circle coordinates point, to the coordinate difference of two squares of the first circle coordinates point and the second circle coordinates point
It opens radical sign and obtains diameter of a circle, and then obtain round radius；Then two the first circle coordinates points and the second circle coordinates are calculated
The midpoint of point, using this midpoint as the center of circle；Finally centered on the center of circle, the picture color in the circle is changed with the radius of the circle
To complete mark, two dimensional image at this time is two-dimentional fingerprint label.
10. according to claim 1 to the method being labeled described in 5 any one to OCT fingerprint image, which is characterized in that
Two-dimentional fingerprint label mapping is returned the realization process of three-dimensional space by mapping algorithm by the step S4 are as follows: is referred to using initial three-dimensional
Print image puts in order, and two-dimentional fingerprint label is corresponded to each Zhang San on the width coordinate for tieing up fingerprint image, in turn
Obtain the three-dimensional dactylotype information for having two-dimentional fingerprint label.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910522011.9A CN110309738B (en) | 2019-06-17 | 2019-06-17 | Method for labeling OCT fingerprint image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910522011.9A CN110309738B (en) | 2019-06-17 | 2019-06-17 | Method for labeling OCT fingerprint image |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110309738A true CN110309738A (en) | 2019-10-08 |
| CN110309738B CN110309738B (en) | 2022-09-30 |
Family
ID=68076576
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910522011.9A Active CN110309738B (en) | 2019-06-17 | 2019-06-17 | Method for labeling OCT fingerprint image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110309738B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113570699A (en) * | 2021-06-24 | 2021-10-29 | 清华大学 | Method and device for reconstructing three-dimensional fingerprint |
Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101593349A (en) * | 2009-06-26 | 2009-12-02 | 福州华映视讯有限公司 | Bidimensional image is converted to the method for 3-dimensional image |
| CN103810709A (en) * | 2014-02-25 | 2014-05-21 | 南京理工大学 | Vessel-based registration method for eye fundus image and SD-OCT projection image |
| CN106021610A (en) * | 2016-06-28 | 2016-10-12 | 电子科技大学 | Video fingerprint extracting method based on salient region |
| CN106407896A (en) * | 2016-08-29 | 2017-02-15 | 华蓥市高科德电子科技有限公司 | 3D fingerprint information extraction method for handset equipment |
| CN106778663A (en) * | 2016-12-29 | 2017-05-31 | 苏州塞罗尔医学影像科技有限公司 | A kind of fingerprint recognition system |
| CN107146262A (en) * | 2017-04-18 | 2017-09-08 | 清华大学深圳研究生院 | The three-dimensional visualization method and system of a kind of OCT image |
| US20180157924A1 (en) * | 2015-11-01 | 2018-06-07 | Joshua Noel Hogan | Optical coherence tomography array based subdermal imaging device |
| CN108446633A (en) * | 2018-03-20 | 2018-08-24 | 深圳大学 | A kind of method, system and device of novel finger print automatic anti-fake and In vivo detection |
| CN108664940A (en) * | 2018-05-16 | 2018-10-16 | 山东大学 | A kind of partial fingerprints matching process and system |
| CN108932507A (en) * | 2018-08-06 | 2018-12-04 | 深圳大学 | A kind of automatic anti-fake method and system based on OCT fingerprint image |
| CN109377549A (en) * | 2018-09-29 | 2019-02-22 | 浙江工业大学 | A kind of real-time processing of OCT finger tip data and three-dimensional visualization method |
| CN109376687A (en) * | 2018-11-16 | 2019-02-22 | 深圳市趣创科技有限公司 | Shield lower unlocked by fingerprint discrimination method for improving, device, terminal and storage medium |
| CN109508692A (en) * | 2018-11-30 | 2019-03-22 | 深圳大学 | A kind of gender identification method and system based on 3D fingerprint image |
| CN109657567A (en) * | 2018-11-30 | 2019-04-19 | 深圳大学 | A kind of Weakly supervised characteristic analysis method and system based on 3D fingerprint image |
| US20190180071A1 (en) * | 2017-12-11 | 2019-06-13 | Samsung Electronics Co., Ltd. | Three-dimensional fingerprint sensing device, method of sensing fingerprint by using the same, and electronic apparatus including the same |
-
2019
- 2019-06-17 CN CN201910522011.9A patent/CN110309738B/en active Active
Patent Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101593349A (en) * | 2009-06-26 | 2009-12-02 | 福州华映视讯有限公司 | Bidimensional image is converted to the method for 3-dimensional image |
| CN103810709A (en) * | 2014-02-25 | 2014-05-21 | 南京理工大学 | Vessel-based registration method for eye fundus image and SD-OCT projection image |
| US20180157924A1 (en) * | 2015-11-01 | 2018-06-07 | Joshua Noel Hogan | Optical coherence tomography array based subdermal imaging device |
| CN106021610A (en) * | 2016-06-28 | 2016-10-12 | 电子科技大学 | Video fingerprint extracting method based on salient region |
| CN106407896A (en) * | 2016-08-29 | 2017-02-15 | 华蓥市高科德电子科技有限公司 | 3D fingerprint information extraction method for handset equipment |
| CN106778663A (en) * | 2016-12-29 | 2017-05-31 | 苏州塞罗尔医学影像科技有限公司 | A kind of fingerprint recognition system |
| CN107146262A (en) * | 2017-04-18 | 2017-09-08 | 清华大学深圳研究生院 | The three-dimensional visualization method and system of a kind of OCT image |
| US20190180071A1 (en) * | 2017-12-11 | 2019-06-13 | Samsung Electronics Co., Ltd. | Three-dimensional fingerprint sensing device, method of sensing fingerprint by using the same, and electronic apparatus including the same |
| CN108446633A (en) * | 2018-03-20 | 2018-08-24 | 深圳大学 | A kind of method, system and device of novel finger print automatic anti-fake and In vivo detection |
| CN108664940A (en) * | 2018-05-16 | 2018-10-16 | 山东大学 | A kind of partial fingerprints matching process and system |
| CN108932507A (en) * | 2018-08-06 | 2018-12-04 | 深圳大学 | A kind of automatic anti-fake method and system based on OCT fingerprint image |
| CN109377549A (en) * | 2018-09-29 | 2019-02-22 | 浙江工业大学 | A kind of real-time processing of OCT finger tip data and three-dimensional visualization method |
| CN109376687A (en) * | 2018-11-16 | 2019-02-22 | 深圳市趣创科技有限公司 | Shield lower unlocked by fingerprint discrimination method for improving, device, terminal and storage medium |
| CN109508692A (en) * | 2018-11-30 | 2019-03-22 | 深圳大学 | A kind of gender identification method and system based on 3D fingerprint image |
| CN109657567A (en) * | 2018-11-30 | 2019-04-19 | 深圳大学 | A kind of Weakly supervised characteristic analysis method and system based on 3D fingerprint image |
Non-Patent Citations (6)
| Title |
|---|
| EGIDIJUS AUKSORIUS 等: "Fast subsurface fingerprint imaging with full-field optical coherence tomography system equipped with a silicon camera", 《JOURNAL OF BIOMEDICAL OPTICS》 * |
| GANGJUN LIU 等: "Capturing the vital vascular fingerprint with optical coherence tomography", 《APPLIED OPTICS》 * |
| NASIBE AKBARI 等: "Automation of Fingerprint Recognition Using OCT Fingerprint Images", 《JOURNAL OF SIGNAL AND INFORMATION PROCESSING》 * |
| 李康 等: "常用指纹细节特征标注方法的比较研究", 《刑事技术》 * |
| 王勇 等: "指纹自动识别与人工识别的差异及人机配合策略", 《刑事技术》 * |
| 王恒 等: "3D指纹的获取与重建技术", 《加解密技术与图形识别》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113570699A (en) * | 2021-06-24 | 2021-10-29 | 清华大学 | Method and device for reconstructing three-dimensional fingerprint |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110309738B (en) | 2022-09-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107169475B (en) | A kind of face three-dimensional point cloud optimized treatment method based on kinect camera | |
| CN102739951B (en) | Image processing apparatus and image processing method | |
| Yan et al. | Multi-feature fusing local directional ternary pattern for facial expressions signal recognition based on video communication system | |
| CN103839058A (en) | Information locating method for document image based on standard template | |
| CN104794479B (en) | This Chinese detection method of natural scene picture based on the transformation of local stroke width | |
| CN104537705B (en) | Mobile platform three dimensional biological molecular display system and method based on augmented reality | |
| CN105068918B (en) | A kind of page method of testing and device | |
| JPH03140140A (en) | Area extracting method | |
| CN108734078B (en) | Image processing method, image processing apparatus, electronic device, storage medium, and program | |
| CN105574527A (en) | Quick object detection method based on local feature learning | |
| CN107038701B (en) | The detection method and system of cable surface blemish in a kind of industrial production | |
| CN104732541B (en) | The acquisition methods and device of PET crystal positions look-up tables | |
| CN112785582A (en) | Training method and device for thermodynamic diagram generation model, electronic equipment and storage medium | |
| CN111784706A (en) | Automatic identification method and system for primary tumor image of nasopharyngeal carcinoma | |
| CN105869122A (en) | Image processing method and apparatus | |
| CN113112490B (en) | Three-dimensional medical image mark point extraction method and system | |
| CN112132812B (en) | Certificate verification method and device, electronic equipment and medium | |
| CN110309738A (en) | The method that a kind of pair of OCT fingerprint image is labeled | |
| CN108876776B (en) | Classification model generation method, fundus image classification method and device | |
| Staib et al. | Intermodality 3D medical image registration with global search | |
| CN107729863A (en) | Human body refers to vein identification method | |
| CN109829502B (en) | Image pair efficient dense matching method facing repeated textures and non-rigid deformation | |
| CN107590829B (en) | Seed point picking method suitable for multi-view dense point cloud data registration | |
| CN113554748B (en) | Medical instrument three-dimensional modeling method and device | |
| CN110533638A (en) | A kind of method and device of measurement object size |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |