CN109409237A - A kind of fingerprint characteristic processing method and processing device - Google Patents
A kind of fingerprint characteristic processing method and processing device Download PDFInfo
- Publication number
- CN109409237A CN109409237A CN201811137203.XA CN201811137203A CN109409237A CN 109409237 A CN109409237 A CN 109409237A CN 201811137203 A CN201811137203 A CN 201811137203A CN 109409237 A CN109409237 A CN 109409237A
- Authority
- CN
- China
- Prior art keywords
- fingerprint
- fingerprint image
- value
- feature templates
- point
- 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
- 238000003672 processing method Methods 0.000 title claims abstract description 29
- 238000000034 method Methods 0.000 claims abstract description 17
- 239000000284 extract Substances 0.000 claims abstract description 5
- 238000011946 reduction process Methods 0.000 claims description 15
- 230000008569 process Effects 0.000 claims description 12
- 238000000605 extraction Methods 0.000 claims description 11
- 238000006243 chemical reaction Methods 0.000 claims description 9
- 238000001914 filtration Methods 0.000 claims description 5
- 230000009286 beneficial effect Effects 0.000 abstract 1
- 241001269238 Data Species 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 241000208340 Araliaceae Species 0.000 description 1
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 1
- 235000003140 Panax quinquefolius Nutrition 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 239000003990 capacitor Substances 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 238000005034 decoration Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 235000008434 ginseng Nutrition 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
Classifications
-
- 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
-
- 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
-
- 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
- G06V40/1365—Matching; Classification
Landscapes
- Engineering & Computer Science (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Collating Specific Patterns (AREA)
Abstract
The invention discloses a kind of fingerprint characteristic processing method and processing devices, including template generation step and fingerprinting step: template generation step includes: repeatedly to acquire the first fingerprint image；Multiple fingerprint characteristic is extracted from the first fingerprint image for being repeated as many times acquisition；If the total amount of multiple fingerprint characteristic is more than preset threshold value, feature templates are generated；Fingerprinting step includes: the second current fingerprint image data of acquisition；Extract the current finger print feature in the second fingerprint image data；Current finger print feature is compared with feature templates to obtain recognition result.The beneficial effects of the practice of the present invention: solving the safety issue of fingerprint characteristic data, can protect user fingerprints characteristic；The method for not using encryption and decryption, there is no cracked by algorithm；Acquisition, processing and the storage of fingerprint are carried out by fingerprint characteristic processing unit, the terminals such as mobile phone are read to protect the private data of user less than fingerprint characteristic data, and leaking data problem is not present.
Description
Technical field
The present invention relates to fingerprint characteristic processing technology field more particularly to a kind of fingerprint characteristic processing method and processing devices.
Background technique
Fingerprint is because its unique and uniqueness is widely used in the fields such as safety certification, and fingerprint mould group is as fingerprint spy
The indispensable acquisition device of data is levied, is also occurred frequently in relevant safety certification process.
Existing fingerprint sensor, which needs to upload to finger print data, carries out identifying processing in mobile phone or Fingerprint Lock, fingerprint is special
Data are levied other than being stolen in transmission process, finger print data can also be obtained by mobile phone/Fingerprint Lock manufacturer background data base
It obtains and saves, these finger print datas may be without being unanimously used for authentication.Therefore, how to enhance fingerprint characteristic data
Safety becomes a urgent problem to be solved.
Summary of the invention
The purpose of the present invention is to provide a kind of fingerprint characteristic processing method and processing devices, and solving existing fingerprint sensor needs
Finger print data is uploaded to and carries out identifying processing on mobile phone or Fingerprint Lock, fingerprint characteristic data in transmission process in addition to being stolen
Outside taking, finger print data can also be obtained and be saved by mobile phone/Fingerprint Lock manufacturer background data base, these finger print datas may not
The problem of being unanimously used for authentication.
Technical solution of the present invention is accomplished by
The present invention provides a kind of fingerprint characteristic processing method, including template generation step and fingerprinting step:
The template generation step includes step S11-S13:
S11, it is repeated as many times the first fingerprint image of acquisition；
S12, multiple fingerprint characteristic is extracted from the first fingerprint image for being repeated as many times acquisition；
If the total amount of S13, repeatedly fingerprint characteristic is more than preset threshold value, feature templates are generated；
The fingerprinting step includes step S21-S23:
The second current fingerprint image data of S21, acquisition；
Current finger print feature in S22, extraction second fingerprint image data；
S23, the current finger print feature is compared with the feature templates to obtain recognition result.
In fingerprint characteristic processing method of the present invention, the step S12 includes: step S121-S125:
S121, noise reduction process is carried out to first fingerprint image using median filtering；
S122, binary conversion treatment is carried out to the first fingerprint image after progress noise reduction process；
S123, micronization processes are carried out to the first fingerprint image after progress binary conversion treatment；
S124, feature point extraction is carried out to obtain fingerprint characteristic to the first fingerprint image after progress micronization processes；
S125, step S121-S124 is repeated as many times to obtain multiple fingerprint characteristic.
In fingerprint characteristic processing method of the present invention, the step S121 includes step S1211-S1212:
All pixels point in S1211, traversal first fingerprint image is to obtain current pixel point；
S1212, the current pixel point is replaced using the intermediate value of eight pixels of a lattice around current pixel point.
In fingerprint characteristic processing method of the present invention, the step S122 includes step S1221-S1223:
S1221, histogram is converted by first fingerprint image, and extracts the ash for meeting preset condition from histogram
Angle value is as pixel threshold；
S1222, the value for the pixel for being greater than the pixel threshold in the first fingerprint image after progress noise reduction process is set
It is set to 1；
S1223, to carry out noise reduction process after the first fingerprint image in be less than or equal to the pixel threshold pixel
Value be set as 0.
In fingerprint characteristic processing method of the present invention, the step S1221 includes step S12211-S12213:
S12211, histogram is converted by first fingerprint image；
S12212, acquisition gray value are 100 to 156 corresponding histogram values, are chosen most from acquired histogram value
Small value；
S12213, using the corresponding gray value of selected minimum value as pixel threshold.
In fingerprint characteristic processing method of the present invention, the step S123 includes step S1231-S1233:
All pixels point in S1231, traversal first fingerprint image is to obtain current pixel point；
S1232, calculate the adjacent lattice of current pixel point four pixels value weighted sum；
S1233, judge whether the weighted sum is greater than the pixel threshold, if so, the value of current pixel point is 1, if
No, then the value of current pixel point is 0.
In fingerprint characteristic processing method of the present invention, the step S124 includes step S1241-S1244:
All pixels point in S1241, traversal first fingerprint image is to obtain current pixel point；
S1242, the current pixel point difference with the value of eight pixels of a lattice around the current pixel point respectively is calculated
The absolute value of value；
S1243, calculate all absolute values and value；
If S1244, described and value the half are 7 or 3, the current pixel point is characterized a little, is not otherwise characterized a little.
In fingerprint characteristic processing method of the present invention, step S13 includes step S131-S134:
S131, any two the first fingerprint images are obtained from the first fingerprint image for being repeated as many times acquisition；
S132, two acquired the first fingerprint images are spliced, using spliced image as original template；
S133, the first fingerprint image for being repeated as many times acquisition in addition to two the first fingerprint images spliced is distinguished
Similarity is calculated with the original template:
Ri=(Si-Ai)/Si
Wherein, RiFor the first fingerprint image for being repeated as many times acquisition in addition to two the first fingerprint images spliced
The similarity of i-th the first fingerprint image and the original template, SiFor in addition to two the first fingerprint images spliced
The value of the pixel of i-th the first fingerprint image and original template of the first fingerprint image repeatedly acquired and,
AiFor i-th the first fingerprint of the first fingerprint image for being repeated as many times acquisition in addition to two the first fingerprint images spliced
The difference of the value of the pixel of image and the original template；
S134, the original template is corrected to generate feature templates according to the similarity.
In fingerprint characteristic processing method of the present invention, step S23 includes step S231-S235:
The field of direction of S231, the field of direction for calculating the second fingerprint image and feature templates；
S232, according to the second fingerprint image the field of direction and feature templates the field of direction rotate respectively the second fingerprint image and
Feature templates are so that the direction of the second fingerprint image and feature templates is consistent；
S233, the second fingerprint image and feature templates are matched to obtain the second fingerprint image and be matched with feature templates
Characteristic point quantity；
S234, the matching rate for calculating the second fingerprint image and feature templates:
Wherein, C is the matching rate of the second fingerprint image and feature templates, and N is that the second fingerprint image is matched with feature templates
Characteristic point quantity, N1For the quantity of the characteristic point of the second fingerprint image, N2It is characterized the quantity of the characteristic point of template, R
The similarity of two fingerprint images and feature templates:
R=(S-A)/S
S be the value of the pixel of the second fingerprint image and feature templates and, A is the second fingerprint image and feature templates
The difference of the value of pixel；
S235, recognition result is obtained according to the matching rate.
On the other hand, a kind of fingerprint characteristic processing unit is provided, it is described for executing above-mentioned fingerprint characteristic processing method
Fingerprint characteristic processing unit includes:
Acquisition module, for acquiring the first fingerprint image and the second fingerprint image；
Processing module, for executing template generation step and fingerprinting step；
Memory module, for storing feature templates；Wherein, the acquisition module, the processing module and the storage mould
Block is connected with each other by system bus.
Therefore, the invention has the advantages that solving the safety issue of fingerprint characteristic data, user fingerprints be can protect
Characteristic；The method for not using encryption and decryption, there is no be cracked by algorithm；It is carried out by fingerprint characteristic processing unit
Acquisition, processing and the storage of fingerprint, the terminals such as mobile phone or Fingerprint Lock are read to protect the privacy of user less than fingerprint characteristic data
Data, there is no the leaking data problems after decryption.
Detailed description of the invention
Present invention will be further explained below with reference to the attached drawings and examples, in attached drawing:
Fig. 1 is a kind of flow chart for fingerprint characteristic processing method that one embodiment of the invention provides；
Fig. 2 is the position view of eight pixels of one lattice of current pixel point and its surrounding；
Fig. 3 is the position view of four pixels of current pixel point and its an adjacent lattice；
Fig. 4 is a kind of structural block diagram for fingerprint characteristic processing unit that one embodiment of the invention provides.
Specific embodiment
For a clearer understanding of the technical characteristics, objects and effects of the present invention, will to compare attached drawing below detailed
Illustrate a specific embodiment of the invention.It should be appreciated that following explanation is only being specifically described for the embodiment of the present invention, it should not be with this
It limits the scope of the invention.
Referring to Fig. 1, Fig. 1 is a kind of flow chart for fingerprint characteristic processing method that one embodiment of the invention provides, the fingerprint
Characteristic processing method, including template generation step and fingerprinting step:
The template generation step includes step S11-S13:
S11, it is repeated as many times the first fingerprint image of acquisition；Preferably, the first fingerprint image is acquired by acquisition module, and more
The first fingerprint image of the secondary same user of acquisition.
S12, multiple fingerprint characteristic is extracted from the first fingerprint image for being repeated as many times acquisition；The step S12 includes: step
Rapid S121-S125:
S121, noise reduction process is carried out to first fingerprint image using median filtering；The step S121 includes step
S1211-S1212:
All pixels point in S1211, traversal first fingerprint image is to obtain current pixel point.
S1212, the current pixel point is replaced using the intermediate value of eight pixels of a lattice around current pixel point.Ginseng
See that Fig. 2, Fig. 2 are the position view of eight pixels of one lattice of current pixel point and its surrounding, the dotted line pixel in figure is
Current pixel point, white pixel point are eight pixels of one lattice of surrounding.Such as: first using median filtering to fingerprint image into
Row noise reduction process traverses all pixels point when specific process, with the intermediate value of 9 pixels adjacent around current pixel point come
Current pixel point is replaced, to eliminate isolated noise spot.Median calculation herein is to be counted using the gray value of pixel
It calculates.Specifically, being ranked up by the gray value of 9 pixels, that gray value for arranging the 5th is exactly intermediate value.
S122, binary conversion treatment is carried out to the first fingerprint image after progress noise reduction process；The step S122 includes step
Rapid S1221-S1223:
S1221, histogram is converted by first fingerprint image, and extracts the ash for meeting preset condition from histogram
Angle value is as pixel threshold；The step S1221 includes step S12211-S12213:
S12211, histogram is converted by first fingerprint image；Such as: binary conversion treatment is carried out to fingerprint image,
The preparation method of threshold value is the histogram for seeking image.
S12212, acquisition gray value are 100 to 156 corresponding histogram values, are chosen most from acquired histogram value
Small value；The range of the gray value of the pixel of image is 0 to 255, and after the histogram for seeking image, this 256 gray values have pair
256 histogram values answered, it is possible to find this 56 gray values of gray value in 100 to 156 sections it is corresponding 56 it is straight
Square map values.
S12213, using the corresponding gray value of selected minimum value as pixel threshold.Choose in 56 histogram values
The corresponding gray value of the smallest that histogram is as threshold value.
S1222, the value for the pixel for being greater than the pixel threshold in the first fingerprint image after progress noise reduction process is set
It is set to 1.
S1223, to carry out noise reduction process after the first fingerprint image in be less than or equal to the pixel threshold pixel
Value be set as 0, the i.e. finger print data for 8, the pixel greater than threshold value is set as 1, less than or equal to the picture of threshold value
Vegetarian refreshments is set as 0.
S123, micronization processes are carried out to the first fingerprint image after progress binary conversion treatment；The step S123 includes step
Rapid S1231-S1233:
All pixels point in S1231, traversal first fingerprint image is to obtain current pixel point.
S1232, calculate the adjacent lattice of current pixel point four pixels value weighted sum.Referring to Fig. 3, Fig. 3 is to work as
The position view of four pixels of preceding pixel point and its an adjacent lattice, the dotted line pixel in figure is current pixel point, white
Colour vegetarian refreshments is four pixels of an adjacent lattice.Here weighted sum be preferably linear weighted function and, linear weighted function and can manage
Solution are as follows: suppose there is n parameter x1, x2, x3....xn, corresponding weight coefficient is p1, p2, p3....pn then its weighted sum are as follows: S=
P1*x1+p2*x2+p3*x3+...+pn*xn=∑ (pi*xi).
S1233, judge whether the weighted sum is greater than the pixel threshold, if so, the value of current pixel point is 1, if
No, then the value of current pixel point is 0.Micronization processes are carried out to fingerprint image after binaryzation, specific method is that traversal is all
Pixel, calculate the weighted sum of adjacent four points around pixel, this weighted sum is greater than threshold value, then this pixel is 1, no
Then this pixel is 0.
S124, feature point extraction is carried out to obtain fingerprint characteristic to the first fingerprint image after progress micronization processes；It is described
Step S124 includes step S1241-S1244:
All pixels point in S1241, traversal first fingerprint image is to obtain current pixel point；The extraction of characteristic point
Be based on refinement after fingerprint image data, traverse all pixels.
S1242, the current pixel point difference with the value of eight pixels of a lattice around the current pixel point respectively is calculated
The absolute value of value；The value of pixel is the value after binaryzation herein, is 1 or 0.
S1243, calculate all absolute values and value.
If S1244, described and value the half are 7 or 3, the current pixel point is characterized a little, is not otherwise characterized a little.
Such as: current pixel point pixel value is X, and 8 pixel pixel values of surrounding are Xi, then is | X0-X |/2+..... | Xi-X |/2
(i is from 0 to 7), if calculated result is 7, current pixel point is endpoint；If calculated result is 3, then it represents that current pixel point
It is crunode；Calculated result is other values, indicates that current pixel point is not characteristic point.Endpoint and crunode are characteristic point, are
In order to handle pictures subsequent preferably.
S125, step S121-S124 is repeated as many times to obtain multiple fingerprint characteristic.That is the first of the same user of multi collect
Fingerprint image, and step S121-S124 is executed to obtain multiple fingerprint characteristic to each the first fingerprint image.
If the total amount of S13, repeatedly fingerprint characteristic is more than preset threshold value, feature templates are generated；Step S13 includes step
S131-S134:
S131, any two the first fingerprint images are obtained from the first fingerprint image for being repeated as many times acquisition；Such as: it calculates
Two images rotate and match the characteristic point of two images by the field of direction of two images according to the field of direction,
Then the similarity of the parts of images of coincidence is calculated, matched characteristic point is more, and similarity is higher.Calculate the similar of two images
The mode of degree such as step S133.
S132, two acquired the first fingerprint images are spliced, using spliced image as original template；It is excellent
Choosing, when the fingerprint image (the first fingerprint image) of registration reaches 5 frame, just calculate image between the degree of association (similarity is higher,
Then the degree of association is higher, generally can characterize the degree of association using similarity), it takes the highest two images of the degree of association to be spliced, spells
Image after connecing is as original template.
S133, the first fingerprint image for being repeated as many times acquisition in addition to two the first fingerprint images spliced is distinguished
Similarity is calculated with the original template:
Ri=(Si-Ai)/Si
Wherein, RiFor the first fingerprint image for being repeated as many times acquisition in addition to two the first fingerprint images spliced
The similarity of i-th the first fingerprint image and the original template, SiFor in addition to two the first fingerprint images spliced
The value of the pixel of i-th the first fingerprint image and original template of the first fingerprint image repeatedly acquired and,
AiFor i-th the first fingerprint of the first fingerprint image for being repeated as many times acquisition in addition to two the first fingerprint images spliced
The difference of the value of the pixel of image and the original template；Above-mentioned Si、AiValue can pass through the corresponding program of setting and obtain.Its
In, i=1,2,3 ... n, n are the first fingerprint image for being repeated as many times acquisition in addition to two the first fingerprint images spliced
The quantity of picture.
S134, the original template is corrected to generate feature templates according to the similarity.Such as: by others registration figure
As taking the highest image of similarity to be spliced into new template with original template with original template calculating similarity, successively column are pushed away, when
Can not find with splice template similarity be greater than preset threshold fingerprint image when, terminate splicing process, generate feature templates.
Wherein, splicing refers to when calculating the degree of association of two images, according to the field of direction of two images and characteristic point
Match condition is chosen the highest matching way of the degree of association and is spliced.
The fingerprinting step includes step S21-S23:
The second current fingerprint image data of S21, acquisition.
Current finger print feature in S22, extraction second fingerprint image data；The step is similar from repeatedly acquisition
The first fingerprint image in extract the step S12 of multiple fingerprint characteristic, since the second fingerprint image data is only a width, only
A step S121-S124 need to be executed to extract the current finger print feature in the second fingerprint image data, thus step S22 include with
Lower step S221-224:
S221, noise reduction process is carried out to second fingerprint image using median filtering；
S222, binary conversion treatment is carried out to the second fingerprint image after progress noise reduction process；
S223, micronization processes are carried out to the second fingerprint image after progress binary conversion treatment；
S224, feature point extraction is carried out to obtain fingerprint characteristic to the second fingerprint image after progress micronization processes.Step
The detail similar step S121-S124 of S221-224, details are not described herein.
S23, the current finger print feature is compared with the feature templates to obtain recognition result.Step S23 packet
Include step S231-S235:
The field of direction of S231, the field of direction for calculating the second fingerprint image and feature templates.
S232, according to the second fingerprint image the field of direction and feature templates the field of direction rotate respectively the second fingerprint image and
Feature templates are so that the direction of the second fingerprint image and feature templates is consistent；Such as: calculate matching sample image (the second fingerprint image
Picture) the field of direction and template image (feature templates) the field of direction, rotating image according to the field of direction makes the direction of sample and template
Unanimously, then the characteristic point of sample and template is matched, overlapping image region is calculated to each matching method respectively
Similarity.
S233, the second fingerprint image and feature templates are matched to obtain the second fingerprint image and be matched with feature templates
Characteristic point quantity；
S234, the matching rate for calculating the second fingerprint image and feature templates:
Wherein, C is the matching rate of the second fingerprint image and feature templates, and N is that the second fingerprint image is matched with feature templates
Characteristic point quantity, N1For the quantity of the characteristic point of the second fingerprint image, N2It is characterized the quantity of the characteristic point of template, R
The similarity of two fingerprint images and feature templates:
R=(S-A)/S
S be the value of the pixel of the second fingerprint image and feature templates and, A is the second fingerprint image and feature templates
The difference of the value of pixel；
S235, recognition result is obtained according to the matching rate.Such as: when maximum matching rate is greater than preset threshold, then
Expression is identified by, and is otherwise identified and is not passed through, and threshold value is to be calculated and obtained based on lot of experimental data.
Referring to fig. 4, Fig. 4 is a kind of structural block diagram for fingerprint characteristic processing unit that one embodiment of the invention provides, the dress
It sets for executing above-mentioned fingerprint characteristic processing method, the fingerprint characteristic processing unit includes processing module 2, acquisition module 1
And memory module 3.For example, fingerprint characteristic processing unit is integrated chip, processing module 2, acquisition module 1 and memory module 3 are equal
It is encapsulated in the integrated chip.
Acquisition module 1 is for acquiring the first fingerprint image and the second fingerprint image；Acquisition module 1 is responsible for acquisition fingerprint characteristic
Data can be condenser type collector, ultrasonic type collector, optical collector etc..Preferably, acquisition module 1 mainly includes
Pixel and ADC two parts, wherein fingerprint lines voltage characterization can use the original of capacitor charge and discharge by Pixel circuit
Reason, also can use the different principle of light reflective distance；The voltage signal of generation is converted to image data by adc circuit, is protected
It is stored in Data SRAM.I.e. acquisition module is responsible for acquiring fingerprint image data (the first fingerprint image), and the fingerprint of user is by hardware
Circuit adopts integrated image data.Likewise, when fingerprint recognition authenticates, first by the acquisition of acquisition module 1 when secondary fingerprint image data
(the second fingerprint image).
Processing module 2 is for executing template generation step and fingerprinting step；This fingerprint characteristic processing unit is integrated with
Processing module 2 (MCU, DSP, CPU etc.), and recognizer is run with this processing module 2, it is not necessarily to fingerprint characteristic data
Sensor external processing is passed to, the reading interface of fingerprint characteristic data is cut off to essence from hardware, protects the peace of data
Entirely, fingerprint data safety is thoroughly solved the problems, such as.I.e. processing module is mainly used to run the various algorithms of fingerprint recognition, including spy
Extraction algorithm, fuzzy matrix and identification and comparison algorithm are levied, processing module can be MCU or DSP, and MCU can use arm
The processor IP nuclear of company, such as Cortex M3, M4.
Wherein, institute's acquired image data give processing module, processing module meeting operation characteristic extraction algorithm, by feature
It is extracted from fingerprint image data；Feature templates need a certain number of features to be composed, if there is no enough
Feature, then can iterate through acquisition module 1 acquire fingerprint and by processing module 2 take the fingerprint feature obtain it is more special
Sign；After obtaining enough features, 2 operation characteristic combinational algorithm of processing module generates feature templates.Likewise, when fingerprint recognition, place
The feature templates that reason module 2 stores when registering from the reading of memory module 3, run identification and comparison algorithm, will be when time feature of extraction
It is compared with feature templates, obtains recognition result.
Memory module 3 is for storing feature templates；The feature templates generated can be saved in memory module 3.
Wherein, the acquisition module 1, the processing module 2 and the memory module 3 are connected with each other by system bus.
Memory module 3 can be made of ROM, Flash, EPPROM etc..Preferably, memory module 3 is used to save feature templates, program generation
Code, the intermediate data and fingerprint image data of algorithm operation, wherein ROM is used to store program code, and Code SRAM is used to
Space is provided for program code execution, Data SRAM is used to store feature templates and intermediate data.System bus is preferably
Arbiter bus。
In order to guarantee fingerprint characteristic processing unit and PERCOM peripheral communication, fingerprint characteristic processing unit further includes interface module 4, is connect
Mouth mold block 4 is responsible for being communicated with external equipment, the including but not limited to SPI interface of interface module 4, I2C interface, USB interface,
UART interface.I.e. interface module is interacted using SPI protocol interface with exterior terminal, also may include I2C, USB, UART etc.
Interface protocol, SPI interface are responsible for the various communication interactions with exterior terminal.Registering result is notified by interface model 4 outer
Portion's terminal carries out other processing items by exterior terminal.Likewise, interface model 4 notifies recognition result when fingerprint recognition
Exterior terminal.
In addition, the fingerprint characteristic processing unit further includes power management module 5, power management module 5 is preferably included
Bandgap, LDO25, POR and OSC, power management module 5 are responsible for powering to entire sensor modules.
In conclusion although the present invention has been disclosed above in the preferred embodiment, but above preferred embodiment is not to limit
The system present invention, those skilled in the art can make various changes and profit without departing from the spirit and scope of the present invention
Decorations, therefore protection scope of the present invention subjects to the scope of the claims.
Claims (10)
1. a kind of fingerprint characteristic processing method, which is characterized in that including template generation step and fingerprinting step:
The template generation step includes step S11-S13:
S11, it is repeated as many times the first fingerprint image of acquisition；
S12, multiple fingerprint characteristic is extracted from the first fingerprint image for being repeated as many times acquisition；
If the total amount of S13, repeatedly fingerprint characteristic is more than preset threshold value, feature templates are generated；
The fingerprinting step includes step S21-S23:
The second current fingerprint image data of S21, acquisition；
Current finger print feature in S22, extraction second fingerprint image data；
S23, the current finger print feature is compared with the feature templates to obtain recognition result.
2. fingerprint characteristic processing method according to claim 1, which is characterized in that the step S12 includes: step
S121-S125:
S121, noise reduction process is carried out to first fingerprint image using median filtering；
S122, binary conversion treatment is carried out to the first fingerprint image after progress noise reduction process；
S123, micronization processes are carried out to the first fingerprint image after progress binary conversion treatment；
S124, feature point extraction is carried out to obtain fingerprint characteristic to the first fingerprint image after progress micronization processes；
S125, step S121-S124 is repeated as many times to obtain multiple fingerprint characteristic.
3. fingerprint characteristic processing method according to claim 2, which is characterized in that the step S121 includes step
S1211-S1212:
All pixels point in S1211, traversal first fingerprint image is to obtain current pixel point；
S1212, the current pixel point is replaced using the intermediate value of eight pixels of a lattice around current pixel point.
4. fingerprint characteristic processing method according to claim 2, which is characterized in that the step S122 includes step
S1221-S1223:
S1221, histogram is converted by first fingerprint image, and extracts the gray value for meeting preset condition from histogram
As pixel threshold；
S1222, the value for the pixel for being greater than the pixel threshold in the first fingerprint image after progress noise reduction process is set as
1；
S1223, the value to the pixel for being less than or equal to the pixel threshold in the first fingerprint image after progress noise reduction process
It is set as 0.
5. fingerprint characteristic processing method according to claim 4, which is characterized in that the step S1221 includes step
S12211-S12213:
S12211, histogram is converted by first fingerprint image；
S12212, acquisition gray value are 100 to 156 corresponding histogram values, choose minimum value from acquired histogram value；
S12213, using the corresponding gray value of selected minimum value as pixel threshold.
6. fingerprint characteristic processing method according to claim 4, which is characterized in that the step S123 includes step
S1231-S1233:
All pixels point in S1231, traversal first fingerprint image is to obtain current pixel point；
S1232, calculate the adjacent lattice of current pixel point four pixels value weighted sum；
S1233, judge whether the weighted sum is greater than the pixel threshold, if so, the value of current pixel point is 1, if it is not, then
The value of current pixel point is 0.
7. fingerprint characteristic processing method according to claim 4, which is characterized in that the step S124 includes step
S1241-S1244:
All pixels point in S1241, traversal first fingerprint image is to obtain current pixel point；
S1242, calculate current pixel point respectively with the difference of the value of eight pixels of a lattice around the current pixel point
Absolute value；
S1243, calculate all absolute values and value；
If S1244, described and value the half are 7 or 3, the current pixel point is characterized a little, is not otherwise characterized a little.
8. fingerprint characteristic processing method according to claim 1, which is characterized in that step S13 includes step S131-
S134:
S131, any two the first fingerprint images are obtained from the first fingerprint image for being repeated as many times acquisition；
S132, two acquired the first fingerprint images are spliced, using spliced image as original template；
S133, by addition to two the first fingerprint images spliced be repeated as many times acquisition the first fingerprint image respectively with institute
It states original template and calculates similarity:
Ri=(Si-Ai)/Si
Wherein, RiFor the i-th width of the first fingerprint image for being repeated as many times acquisition in addition to two the first fingerprint images spliced
The similarity of first fingerprint image and the original template, SiIt is more for the repetition in addition to two the first fingerprint images spliced
The value of the pixel of i-th the first fingerprint image and original template of first fingerprint image of secondary acquisition and, AiFor except
Except two the first fingerprint images spliced be repeated as many times acquisition the first fingerprint image i-th the first fingerprint image with
The difference of the value of the pixel of the original template；
S134, the original template is corrected to generate feature templates according to the similarity.
9. fingerprint characteristic processing method according to claim 8, which is characterized in that step S23 includes step S231-
S235:
The field of direction of S231, the field of direction for calculating the second fingerprint image and feature templates；
S232, the second fingerprint image and feature are rotated respectively according to the field of direction of the second fingerprint image and the field of direction of feature templates
Template is so that the direction of the second fingerprint image and feature templates is consistent；
S233, the second fingerprint image and feature templates are matched to obtain the second fingerprint image and the matched spy of feature templates
Levy the quantity of point；
S234, the matching rate for calculating the second fingerprint image and feature templates:
Wherein, C is the matching rate of the second fingerprint image and feature templates, and N is the second fingerprint image and the matched spy of feature templates
Levy the quantity of point, N1For the quantity of the characteristic point of the second fingerprint image, N2It is characterized the quantity of the characteristic point of template, R is the second finger
The similarity of print image and feature templates:
R=(S-A)/S
S be the value of the pixel of the second fingerprint image and feature templates and, A for the second fingerprint image and feature templates pixel
The difference of the value of point；
S235, recognition result is obtained according to the matching rate.
10. a kind of fingerprint characteristic processing unit, which is characterized in that require the described in any item fingerprints of 1-9 special for perform claim
Processing method is levied, the fingerprint characteristic processing unit includes:
Acquisition module, for acquiring the first fingerprint image and the second fingerprint image；
Processing module, for executing template generation step and fingerprinting step；
Memory module, for storing feature templates；Wherein, the acquisition module, the processing module and the memory module are logical
Cross system bus interconnection.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811137203.XA CN109409237B (en) | 2018-09-28 | 2018-09-28 | Fingerprint feature processing method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811137203.XA CN109409237B (en) | 2018-09-28 | 2018-09-28 | Fingerprint feature processing method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109409237A true CN109409237A (en) | 2019-03-01 |
| CN109409237B CN109409237B (en) | 2022-03-29 |
Family
ID=65466492
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811137203.XA Active CN109409237B (en) | 2018-09-28 | 2018-09-28 | Fingerprint feature processing method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109409237B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112837222A (en) * | 2021-01-25 | 2021-05-25 | 深圳市奔凯安全技术股份有限公司 | Fingerprint image splicing method and device, storage medium and electronic equipment |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104281841A (en) * | 2014-09-30 | 2015-01-14 | 深圳市汇顶科技股份有限公司 | Fingerprint identification system and fingerprint processing method and device thereof |
| CN106778461A (en) * | 2016-03-17 | 2017-05-31 | 深圳信炜科技有限公司 | Finger prints processing method, finger prints processing device, fingerprint recognition system and electronic equipment |
| CN108121946A (en) * | 2017-11-15 | 2018-06-05 | 大唐微电子技术有限公司 | A kind of Pre-processing Method for Fingerprint Image and device |
-
2018
- 2018-09-28 CN CN201811137203.XA patent/CN109409237B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104281841A (en) * | 2014-09-30 | 2015-01-14 | 深圳市汇顶科技股份有限公司 | Fingerprint identification system and fingerprint processing method and device thereof |
| CN106778461A (en) * | 2016-03-17 | 2017-05-31 | 深圳信炜科技有限公司 | Finger prints processing method, finger prints processing device, fingerprint recognition system and electronic equipment |
| CN108121946A (en) * | 2017-11-15 | 2018-06-05 | 大唐微电子技术有限公司 | A kind of Pre-processing Method for Fingerprint Image and device |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112837222A (en) * | 2021-01-25 | 2021-05-25 | 深圳市奔凯安全技术股份有限公司 | Fingerprint image splicing method and device, storage medium and electronic equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109409237B (en) | 2022-03-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2020186886A1 (en) | Method and device for generating face recognition model | |
| Du et al. | Unsupervised approach to color video thresholding | |
| WO2020038136A1 (en) | Facial recognition method and apparatus, electronic device and computer-readable medium | |
| Zhou et al. | Appearance characterization of linear lambertian objects, generalized photometric stereo, and illumination-invariant face recognition | |
| US7925650B2 (en) | Image management methods, image management systems, and articles of manufacture | |
| CN111539255B (en) | Cross-modal pedestrian re-identification method based on multi-modal image style conversion | |
| JP2013012190A (en) | Method of approximating gabor filter as block-gabor filter, and memory to store data structure for access by application program running on processor | |
| US20180053040A1 (en) | System and method for 3d local surface matching | |
| WO2020253304A1 (en) | Face recognition device and image processing method, feature extraction model, and storage medium | |
| CN110852311A (en) | Three-dimensional human hand key point positioning method and device | |
| Soltanpour et al. | Multimodal 2D–3D face recognition using local descriptors: pyramidal shape map and structural context | |
| Sleit et al. | Image clustering using color, texture and shape features | |
| CN112507897A (en) | Cross-modal face recognition method, device, equipment and storage medium | |
| Abdullah et al. | Smart card with iris recognition for high security access environment | |
| CN111126250A (en) | Pedestrian re-identification method and device based on PTGAN | |
| CN109409237A (en) | A kind of fingerprint characteristic processing method and processing device | |
| Narang et al. | Robust face recognition method based on SIFT features using Levenberg-Marquardt Backpropagation neural networks | |
| CN104252614A (en) | SIFT algorithm-based two-generation identity card face comparison method | |
| Lian et al. | A novel efficient local illumination compensation method based on DCT in logarithm domain | |
| CN116311650A (en) | Man-machine interaction method based on intelligent entrance guard's sight tracking and gesture recognition | |
| CN112949518B (en) | Iris image processing method, device, equipment and storage medium | |
| Yi et al. | Registration of infrared and visible images based on the correlation of the edges | |
| Lei et al. | Histogram of oriented gradient detector with color-invariant gradients in Gaussian color space | |
| CN108090866B (en) | Method, system and equipment for converting photo into artistic photo | |
| Youssef et al. | A new method for face recognition based on color information and a neural network |
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 | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20211208 Address after: 518000 Guangdong city of Shenzhen province Nanshan District South Road No. 10 four Applicant after: Wang Haibin Address before: 518000 room 003, floor 9, Beike building, No. 18, Keyuan Road, high tech Industrial Park, Yuehai street, Nanshan District, Shenzhen, Guangdong Applicant before: SHENZHEN HAOHAIXIN TECHNOLOGY Co.,Ltd. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |