CN104392226B - Fingerprint identification system and method - Google Patents
Fingerprint identification system and method Download PDFInfo
- Publication number
- CN104392226B CN104392226B CN201410776425.1A CN201410776425A CN104392226B CN 104392226 B CN104392226 B CN 104392226B CN 201410776425 A CN201410776425 A CN 201410776425A CN 104392226 B CN104392226 B CN 104392226B
- Authority
- CN
- China
- Prior art keywords
- fingerprint
- score
- processing unit
- sensor
- finger print
- 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.)
- Active
Links
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
- G06V40/13—Sensors therefor
Landscapes
- Engineering & Computer Science (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Collating Specific Patterns (AREA)
- Image Input (AREA)
Abstract
Present invention is disclosed a kind of fingerprint identification system and method, the fingerprint identification system includes：The first fingerprint sensor of the first finger print data is extracted from user；Obtain the second fingerprint sensor of second finger print data different from the first fingerprint；First finger print data and the second finger print data are carried out similarity comparison, and the authentication processing unit of authentication result is judged from the first finger print data of acquisition and the quality of the second finger print data with registered finger print data.The system also includes registration fingerprint storage unit, fingerprint processing unit, data processing units；Fingerprint processing unit includes the first fingerprint processing unit, the second fingerprint processing unit.Fingerprint identification system proposed by the present invention and method are used in certification identification, can reduce reject rate and misclassification rate so that user authentication result is more accurate after being combined by the finger print data for inputting a variety of fingerprint sensors.
Description
Technical field
The invention belongs to fingerprint identification technology fields, are related to a kind of fingerprint identification system more particularly to a kind of reduction is accidentally known
The fingerprint identification system of rate；Meanwhile the invention further relates to a kind of fingerprint verification methods.
Background technology
Existing fingerprint recognition mode, common situation are to carry out typing by single-sensor and be identified.Single
For fingerprint sensor in use, calculating inputted fingerprint and registered fingerprint similarity, similarity is more than threshold value
(threshold) it is judged as identifying successfully when.Taken the fingerprint characteristic point and registered finger print data by fingerprint sensor
It is compared, if its similar degree is more than 95% it is determined that certification success, threshold value is exactly that therefore threshold value determines 0.95. at this time
Authentication result.
Citing, when similar degree is 0.96, threshold value is set as 0.95, then certification success, but threshold value is set as 0.98 certification
Failure, this is reject rate (False Rejection Rate, FRR), but my too low non-fingerprint of threshold value is just mistakenly considered certification
Success, this is misclassification rate (False Acceptance Rate, FAR).
In view of this, nowadays there is an urgent need to design a kind of new fingerprint recognition mode, to overcome existing fingerprint recognition side
The drawbacks described above of formula.
Invention content
The technical problems to be solved by the invention are：A kind of fingerprint identification system is provided, reject rate and misclassification rate can be reduced,
So that user authentication result is more accurate.
In addition, the present invention also provides a kind of fingerprint verification method, reject rate and misclassification rate can be reduced so that user authentication knot
Fruit is more accurate.
In order to solve the above technical problems, the present invention adopts the following technical scheme that：
A kind of fingerprint identification system, the fingerprint identification system include：First fingerprint sensor, the second fingerprint sensor,
First fingerprint processing unit, the second fingerprint processing unit, data processing unit, authentication processing unit, registration fingerprint storage unit；
Fingerprint storage unit is registered to store the fingerprint of registration；
First fingerprint sensor, the second fingerprint sensor are optical fingerprint sensor or semiconductor fingerprint sensor；
First fingerprint sensor, the second fingerprint sensor are one species fingerprint sensor or different types of fingerprint sensor；
It is to obtain first that first fingerprint processing unit carries out similar degree to calculate to the first fingerprint of input and the fingerprint of registration
Score S1 and corresponding finger print data quality Q1；Second fingerprint processing unit to the fingerprint of the second fingerprint of input and registration into
Row similar degree, which calculates, obtains the second score S2 and corresponding finger print data quality Q2；Quality refers to feature point number, unit plane
Long-pending characteristic point quantity, finger wear, fingerprint clear degree；
Data processing unit calculates more accurate composite score, that is, SF, and composite score SF is (Q1*S1+Q2*S2) or takes
Standard value (Q1*S1+Q2*S2)/(Q1+Q2)；
By the importance of sensor when if the first fingerprint sensor and the second fingerprint sensor are sensor of different nature
It adds in weighted value and obtains composite S F；The weighted value of the first fingerprint sensor is set as W1, the weighted value of the second fingerprint sensor is
W2；Composite score SF for (W1*Q1*S1+W2*Q2*S2) or takes standard value (W1*Q1*S1+W2*Q2*S2)/(W1*Q1+ at this time
W2*Q2)；
Authentication processing unit judges certification success or not using the first score S1, the second score S2 and composite score SF；Tool
Body is judged by following algorithm；Wherein, there are 4 threshold values TL, TH, TM, TF, relationship is TH ＞ TM ＞ TL；
If any one in the first score S1 or the second score S2 is less than threshold value TL, it is judged as recognition failures, first point
Any one in number S1 or the second score S2 is more than threshold value TH then as certification success；
In addition, the first score S1 and the second score S2 are smaller than TH, but any of which is one bigger than TM, then composite score SF
Certification success is judged as more than threshold value TF.
A kind of fingerprint identification system, the fingerprint identification system include：
The first fingerprint sensor of the first finger print data is extracted from user；
Obtain the second fingerprint sensor of second finger print data different from the first fingerprint；
First finger print data and the second finger print data and registered finger print data are carried out similarity comparison, and from acquisition
The first finger print data and the quality of the second finger print data judge the authentication processing unit of authentication result.
As a preferred embodiment of the present invention, the system also includes registration fingerprint storage unit, fingerprint processing unit,
Data processing unit；Fingerprint processing unit includes the first fingerprint processing unit, the second fingerprint processing unit；
It is to obtain first that first fingerprint processing unit carries out similar degree to calculate to the first fingerprint of input and the fingerprint of registration
Score S1 and corresponding finger print data quality Q1；Second fingerprint processing unit to the fingerprint of the second fingerprint of input and registration into
Row similar degree, which calculates, obtains the second score S2 and corresponding finger print data quality Q2；
The result of calculation and set rule that data processing unit is obtained according to each fingerprint processing unit, obtain each fingerprint
Corresponding composite score；
The result and data processing unit that authentication processing unit is calculated according to each fingerprint processing unit obtain compound
Score judges whether certification success.
As a preferred embodiment of the present invention, data processing unit calculates more accurate composite score, that is, SF, compound
Score SF is (Q1*S1+Q2*S2) or takes standard value (Q1*S1+Q2*S2)/(Q1+Q2).
As a preferred embodiment of the present invention, if the first fingerprint sensor and the second fingerprint sensor are of different nature
Weighted value is added in by the importance of sensor obtain composite S F during sensor；The weighted value of the first fingerprint sensor is set as W1,
The weighted value of second fingerprint sensor is W2；Composite score SF for (W1*Q1*S1+W2*Q2*S2) or takes standard value (W1* at this time
Q1*S1+W2*Q2*S2)/(W1*Q1+W2*Q2)。
As a preferred embodiment of the present invention, authentication processing unit uses the first score S1, the second score S2 and compound
Score SF judges certification success or not；Specifically judged by following algorithm；Wherein, there are 4 threshold values, respectively first threshold
TL, second threshold TH, third threshold value TM, the 4th threshold value TF, relationship is TH ＞ TM ＞ TL；
If any one in the first score S1 or the second score S2 is less than threshold value TL, it is judged as recognition failures, first point
Any one in number S1 or the second score S2 is more than threshold value TH then as certification success；
In addition, the first score S1 and the second score S2 are smaller than TH, but any of which is one bigger than TM, then composite score SF
Certification success is judged as more than threshold value TF.
As a preferred embodiment of the present invention, first fingerprint sensor, the second fingerprint sensor are optical finger print
Sensor or semiconductor fingerprint sensor；First fingerprint sensor, the second fingerprint sensor for one species fingerprint sensor or
Different types of fingerprint sensor；Quality refers to feature point number, the characteristic point quantity of unit area, finger wear, and fingerprint is clear
Clear degree.
A kind of fingerprint verification method of above-mentioned fingerprint identification system, described method includes following steps：
First fingerprint sensor, the second fingerprint sensor obtain finger print data；
It is to obtain first that first fingerprint processing unit carries out similar degree to calculate to the first fingerprint of input and the fingerprint of registration
Score S1 and corresponding finger print data quality Q1；Second fingerprint processing unit to the fingerprint of the second fingerprint of input and registration into
Row similar degree, which calculates, obtains the second score S2 and corresponding finger print data quality Q2；
The result of calculation and set rule that data processing unit is obtained according to each fingerprint processing unit, obtain each fingerprint
Corresponding composite score；
The result and data processing unit that authentication processing unit is calculated according to each fingerprint processing unit obtain compound
Score judges whether certification success.
As a preferred embodiment of the present invention, data processing unit calculates more accurate composite score, that is, SF, compound
Score SF is (Q1*S1+Q2*S2) or takes standard value (Q1*S1+Q2*S2)/(Q1+Q2).
As a preferred embodiment of the present invention, if the first fingerprint sensor and the second fingerprint sensor are of different nature
Weighted value is added in by the importance of sensor obtain composite S F during sensor；The weighted value of the first fingerprint sensor is set as W1,
The weighted value of second fingerprint sensor is W2；Composite score SF for (W1*Q1*S1+W2*Q2*S2) or takes standard value (W1* at this time
Q1*S1+W2*Q2*S2)/(W1*Q1+W2*Q2)。
As a preferred embodiment of the present invention, authentication processing unit uses the first score S1, the second score S2 and compound
Score SF judges certification success or not；Specifically judged by following algorithm；Wherein, there are 4 threshold values, respectively first threshold
TL, second threshold TH, third threshold value TM, the 4th threshold value TF, relationship is TH ＞ TM ＞ TL；
If any one in the first score S1 or the second score S2 is less than threshold value TL, it is judged as recognition failures, first point
Any one in number S1 or the second score S2 is more than threshold value TH then as certification success；
In addition, the first score S1 and the second score S2 are smaller than TH, but any of which is one bigger than TM, then composite score SF
Certification success is judged as more than threshold value TF.
The beneficial effects of the present invention are：Fingerprint identification system proposed by the present invention and method, by the way that a variety of fingerprints are passed
The finger print data of sensor input is used in certification identification after being combined, can reduce reject rate and misclassification rate so that user authentication
As a result it is more accurate.
Description of the drawings
Fig. 1 is the finger print identifying schematic diagram of the present invention.
Fig. 2 is the detailed description schematic diagram of control unit in present system.
Fig. 3 is the flow chart of fingerprint verification method.
Specific embodiment
The preferred embodiment that the invention will now be described in detail with reference to the accompanying drawings.
Embodiment one
The present invention is authenticated identifying using the finger print data of multiple sensors input by compound identifying algorithm.
User obtains the first finger print data by first sensor, then passes through the second sensor different from first sensor
The second finger print data is obtained, the first finger print data and the second finger print data are carried out similarity ratio with registered finger print data
Compared with, and judge authentication result from the first finger print data of acquisition and the quality of the second finger print data.Then, the first fingerprint of acquisition
The first fractional value that data and registered finger print data calculate similar degree is multiplied by the first fingerprint quality value, and the second of acquisition refers to
The second fractional value that line data and registered finger print data calculate similar degree is multiplied by the second fingerprint quality value.It is calculated above
Two values be added obtain composite score value be authenticated judging.In addition, the difference of importance of first sensor and second sensor
It assigns different weighted values and calculates composite score.
Fig. 1 is the schematic diagram of the invention.It is made of first sensor and second sensor and control unit.First sensor
Can be the fingerprint sensor of optical sensor, semiconductor transducer or other any modes with second sensor.Although diagram
It is two sensors, but can be used alone or a variety of.It can be by making when two kinds of sensors are sensor of different nature
Suitably selected with environment, such as use environment easily by grease pollution when, can suitably select to polluting durable sensor.
The detailed description of algorithm verification process, the i.e. control unit of Fig. 1 is described in detail in Fig. 2.Control unit includes first
Finger prints processing part, the second finger prints processing part, data processing section, authentication processing part and scale fingerprint storage part.Class
Score (score) is defined as like degree.First finger prints processing part carries out similar degree to the first fingerprint of input and the fingerprint of registration
It is the first score (S1) to calculate, and the second finger prints processing part calculates the second score (S2) as a same reason.Other first finger prints processing
Part and the second finger prints processing part also calculate the quality of finger print data.Quality refers to feature point number, the feature of unit area
Point quantity, finger wear, fingerprint clear degree etc..The quality of first finger print data is Q1, and the quality of the second finger print data is Q2. numbers
More accurate composite score, that is, SF is calculated according to process part, SF is exactly (Q1*S1+Q2*S2) or takes standard value (Q1*S1+Q2*
S2)/(Q1+Q2)。
Authentication processing part judges certification success or not using the first score S1, the second score S2 and composite score SF.Tool
Body is judged by following algorithm.Wherein there are 4 threshold values TL, TH, TM, TF, relationship is TH ＞ TM ＞ TL.
Above-mentioned algorithmic translation is as follows, any one in the first score S1 or the second score S2 is less than threshold value TL, then is judged as
Any one in recognition failures, the first score S1 or the second score S2 is more than threshold value TH then as certification success.In addition, first point
Number S1 and the second score S2 is smaller than TH, but any of which is one bigger than TM, then composite score SF is judged as recognizing more than threshold value TF
It demonstrate,proves successfully.
It can add in and add by the importance of sensor when first sensor and second sensor are sensor of different nature
Weights obtain composite S F.Such as first sensor is optical sensor, when second sensor is semiconductor transducer, considers each biography
The characteristic of sensor assigns weighted value W1 and W2. respectively, and composite score SF is (W1*Q1*S1+W2*Q2*S2) or takes standard value at this time
(W1*Q1*S1+W2*Q2*S2)/(W1*Q1+W2*Q2)。
Fig. 3 is the flow chart of the invention.
The finger print data of multiple sensors is obtained first, is then compared calculating similar degree with registered finger print data
That is then the first score S1 and the second score S2. considers further that the quality of fingerprint calculates composite score SF, judged by S1, S2 and SF
Conscientious result.Different weights value W1 and W2 is assigned respectively further according to the importance of first sensor and second sensor to calculate again
Close score SF.
Embodiment two
The present invention discloses a kind of fingerprint identification system, and the fingerprint identification system includes：First fingerprint sensor, second refer to
Line sensor, the first fingerprint processing unit, the second fingerprint processing unit, data processing unit, authentication processing unit, registration fingerprint
Storage unit；Fingerprint storage unit is registered to store the fingerprint of registration.
First fingerprint sensor, the second fingerprint sensor are optical fingerprint sensor or semiconductor fingerprint sensor；
First fingerprint sensor, the second fingerprint sensor are one species fingerprint sensor or different types of fingerprint sensor.
It is to obtain first that first fingerprint processing unit carries out similar degree to calculate to the first fingerprint of input and the fingerprint of registration
Score S1 and corresponding finger print data quality Q1；Second fingerprint processing unit to the fingerprint of the second fingerprint of input and registration into
Row similar degree, which calculates, obtains the second score S2 and corresponding finger print data quality Q2；Quality refers to feature point number, unit plane
Long-pending characteristic point quantity, finger wear, fingerprint clear degree.
Data processing unit calculates more accurate composite score, that is, SF, and composite score SF is (Q1*S1+Q2*S2) or takes
Standard value (Q1*S1+Q2*S2)/(Q1+Q2).
By the importance of sensor when if the first fingerprint sensor and the second fingerprint sensor are sensor of different nature
It adds in weighted value and obtains composite S F；The weighted value of the first fingerprint sensor is set as W1, the weighted value of the second fingerprint sensor is
W2；Composite score SF for (W1*Q1*S1+W2*Q2*S2) or takes standard value (W1*Q1*S1+W2*Q2*S2)/(W1*Q1+ at this time
W2*Q2)。
Authentication processing unit judges certification success or not using the first score S1, the second score S2 and composite score SF；Tool
Body is judged by following algorithm；Wherein, there are 4 threshold values TL, TH, TM, TF, relationship is TH ＞ TM ＞ TL.
If any one in the first score S1 or the second score S2 is less than threshold value TL, it is judged as recognition failures, first point
Any one in number S1 or the second score S2 is more than threshold value TH then as certification success.
In addition, the first score S1 and the second score S2 are smaller than TH, but any of which is one bigger than TM, then composite score SF
Certification success is judged as more than threshold value TF.
This meal also discloses a kind of fingerprint verification method of above-mentioned fingerprint identification system, and described method includes following steps：
【Step S1】First fingerprint sensor, the second fingerprint sensor obtain finger print data.
【Step S2】First fingerprint processing unit carries out similar degree calculating to the first fingerprint of input and the fingerprint of registration
Obtain the first score S1 and corresponding finger print data quality Q1；Second fingerprint processing unit is to the second fingerprint of input and registration
Fingerprint carry out similar degree and calculate to obtain the second score S2 and corresponding finger print data quality Q2.
【Step S3】The result of calculation and set rule that data processing unit is obtained according to each fingerprint processing unit, obtain
The corresponding composite score of each fingerprint.
Data processing unit calculates more accurate composite score, that is, SF, and composite score SF is (Q1*S1+Q2*S2) or takes
Standard value (Q1*S1+Q2*S2)/(Q1+Q2).
By the importance of sensor when if the first fingerprint sensor and the second fingerprint sensor are sensor of different nature
It adds in weighted value and obtains composite S F；The weighted value of the first fingerprint sensor is set as W1, the weighted value of the second fingerprint sensor is
W2；Composite score SF for (W1*Q1*S1+W2*Q2*S2) or takes standard value (W1*Q1*S1+W2*Q2*S2)/(W1*Q1+ at this time
W2*Q2)。
【Step S4】The result and data processing unit that authentication processing unit is calculated according to each fingerprint processing unit obtain
To composite score judge whether certification success.
Specifically, in the present embodiment, authentication processing unit uses the first score S1, and the second score S2 and composite score SF sentence
Disconnected certification success or not；Specifically judged by following algorithm；Wherein, there are 4 threshold values, respectively first threshold TL, the second threshold
Value TH, third threshold value TM, the 4th threshold value TF, relationship is TH ＞ TM ＞ TL.
If any one in the first score S1 or the second score S2 is less than threshold value TL, it is judged as recognition failures, first point
Any one in number S1 or the second score S2 is more than threshold value TH then as certification success.
In addition, the first score S1 and the second score S2 are smaller than TH, but any of which is one bigger than TM, then composite score SF
Certification success is judged as more than threshold value TF.
Embodiment three
The present invention discloses a kind of fingerprint identification system, and the fingerprint identification system includes：
The first fingerprint sensor of the first finger print data is extracted from user；
Obtain the second fingerprint sensor of second finger print data different from the first fingerprint；
First finger print data and the second finger print data and registered finger print data are carried out similarity comparison, and from obtaining
The first finger print data and the quality of the second finger print data that take judge the authentication processing unit of authentication result.
First fingerprint sensor, the second fingerprint sensor are optical fingerprint sensor or semiconductor fingerprint sensor；
First fingerprint sensor, the second fingerprint sensor are one species fingerprint sensor or different types of fingerprint sensor；Quality
Refer to feature point number, the characteristic point quantity of unit area, finger wear, fingerprint clear degree.
Certainly, the present invention can also utilize three fingerprint sensors to obtain the data of three fingerprints, then be referred to according to three
The recognition result of line and their composite score judge whether certification success.Specific method can refer to above example.
In conclusion fingerprint identification system proposed by the present invention and method, pass through the finger for inputting a variety of fingerprint sensors
Line data are used in certification identification after being combined, can reduce reject rate and misclassification rate so that user authentication result is more accurate.
Here description of the invention and application are illustrative, are not wishing to limit the scope of the invention to above-described embodiment
In.The deformation and change of embodiments disclosed herein are possible, real for those skilled in the art
The replacement and equivalent various parts for applying example are well known.It should be appreciated by the person skilled in the art that not departing from the present invention
Spirit or essential characteristics in the case of, the present invention can in other forms, structure, arrangement, ratio and with other components,
Material and component are realized.In the case where not departing from scope and spirit of the present invention, can to embodiments disclosed herein into
The other deformations of row and change.
Claims (6)
1. a kind of fingerprint identification system, which is characterized in that the fingerprint identification system includes：First fingerprint sensor, second refer to
Line sensor, the first fingerprint processing unit, the second fingerprint processing unit, data processing unit, authentication processing unit, registration fingerprint
Storage unit；Fingerprint storage unit is registered to store the fingerprint of registration；
First fingerprint sensor, the second fingerprint sensor are optical fingerprint sensor or semiconductor fingerprint sensor；First
Fingerprint sensor, the second fingerprint sensor are one species fingerprint sensor or different types of fingerprint sensor；
It is to obtain the first score that first fingerprint processing unit carries out similar degree to calculate to the first fingerprint of input and the fingerprint of registration
S1 and corresponding finger print data quality Q1；Second fingerprint processing unit carries out class to the second fingerprint of input and the fingerprint of registration
It is calculated like degree and obtains the second score S2 and corresponding finger print data quality Q2；Quality refers to feature point number, unit area
Characteristic point quantity, finger wear, fingerprint clear degree；
Data processing unit calculates more accurate composite score, that is, SF, and composite score SF is (Q1*S1+Q2*S2) or takes standard
It is worth (Q1*S1+Q2*S2)/(Q1+Q2)；
It is added in when if the first fingerprint sensor and the second fingerprint sensor are sensor of different nature by the importance of sensor
Weighted value obtains composite S F；The weighted value of the first fingerprint sensor is set as W1, the weighted value of the second fingerprint sensor is W2；This
When composite score SF for (W1*Q1*S1+W2*Q2*S2) or take standard value (W1*Q1*S1+W2*Q2*S2)/(W1*Q1+W2*Q2)；
Authentication processing unit judges certification success or not using the first score S1, the second score S2 and composite score SF；Specifically press
Following algorithm is judged；Wherein, there are 4 threshold values TL, TH, TM, TF, relationship is TH ＞ TM ＞ TL；
If any one in the first score S1 or the second score S2 is less than threshold value TL, it is judged as recognition failures, the first score S1
Or second any one in score S2 be more than threshold value TH then as certification success；
In addition, the first score S1 and the second score S2 are smaller than TH, but any of which is one bigger than TM, then composite score SF is more than
Threshold value TF is judged as certification success.
2. a kind of fingerprint identification system, which is characterized in that the fingerprint identification system includes：
The first fingerprint sensor of the first finger print data is extracted from user；
Obtain the second fingerprint sensor of second finger print data different from the first fingerprint；
First finger print data and the second finger print data and registered finger print data are carried out similarity comparison, and from the of acquisition
The quality of one finger print data and the second finger print data judges the authentication processing unit of authentication result；
The system also includes registration fingerprint storage unit, fingerprint processing unit, data processing units；Fingerprint processing unit includes
First fingerprint processing unit, the second fingerprint processing unit；
It is to obtain the first score that first fingerprint processing unit carries out similar degree to calculate to the first fingerprint of input and the fingerprint of registration
S1 and corresponding finger print data quality Q1；Second fingerprint processing unit carries out class to the second fingerprint of input and the fingerprint of registration
It is calculated like degree and obtains the second score S2 and corresponding finger print data quality Q2；
The result of calculation and set rule that data processing unit is obtained according to each fingerprint processing unit, obtain each fingerprint and correspond to
Composite score；
The composite score that the result and data processing unit that authentication processing unit is calculated according to each fingerprint processing unit obtain
Judge whether certification success；
Authentication processing unit judges certification success or not using the first score S1, the second score S2 and composite score SF；Specifically press
Following algorithm is judged；Wherein, there are 4 threshold values, respectively first threshold TL, second threshold TH, third threshold value TM, the 4th threshold
Value TF, relationship are TH ＞ TM ＞ TL；
If any one in the first score S1 or the second score S2 is less than threshold value TL, it is judged as recognition failures, the first score S1
Or second any one in score S2 be more than threshold value TH then as certification success；
In addition, the first score S1 and the second score S2 are smaller than TH, but any of which is one bigger than TM, then composite score SF is more than
Threshold value TF is judged as certification success.
3. fingerprint identification system according to claim 2, it is characterised in that：
Data processing unit calculates more accurate composite score, that is, SF, and composite score SF is (Q1*S1+Q2*S2) or takes standard
It is worth (Q1*S1+Q2*S2)/(Q1+Q2).
4. fingerprint identification system according to claim 2, it is characterised in that：
It is added in when if the first fingerprint sensor and the second fingerprint sensor are sensor of different nature by the importance of sensor
Weighted value obtains composite S F；The weighted value of the first fingerprint sensor is set as W1, the weighted value of the second fingerprint sensor is W2；This
When composite score SF for (W1*Q1*S1+W2*Q2*S2) or take standard value (W1*Q1*S1+W2*Q2*S2)/(W1*Q1+W2*Q2).
5. fingerprint identification system according to claim 3, it is characterised in that：
First fingerprint sensor, the second fingerprint sensor are optical fingerprint sensor or semiconductor fingerprint sensor；First
Fingerprint sensor, the second fingerprint sensor are one species fingerprint sensor or different types of fingerprint sensor；
Quality refers to feature point number, the characteristic point quantity of unit area, finger wear, fingerprint clear degree.
A kind of 6. fingerprint verification method of one of claim 2 to 5 fingerprint identification system, which is characterized in that the method
Include the following steps：
First fingerprint sensor, the second fingerprint sensor obtain finger print data；
It is to obtain the first score that first fingerprint processing unit carries out similar degree to calculate to the first fingerprint of input and the fingerprint of registration
S1 and corresponding finger print data quality Q1；Second fingerprint processing unit carries out class to the second fingerprint of input and the fingerprint of registration
It is calculated like degree and obtains the second score S2 and corresponding finger print data quality Q2；
The result of calculation and set rule that data processing unit is obtained according to each fingerprint processing unit, obtain each fingerprint and correspond to
Composite score；
The composite score that the result and data processing unit that authentication processing unit is calculated according to each fingerprint processing unit obtain
Judge whether certification success；
Data processing unit calculates more accurate composite score, that is, SF, and composite score SF is (Q1*S1+Q2*S2) or takes standard
It is worth (Q1*S1+Q2*S2)/(Q1+Q2)；
It is added in when if the first fingerprint sensor and the second fingerprint sensor are sensor of different nature by the importance of sensor
Weighted value obtains composite S F；The weighted value of the first fingerprint sensor is set as W1, the weighted value of the second fingerprint sensor is W2；This
When composite score SF for (W1*Q1*S1+W2*Q2*S2) or take standard value (W1*Q1*S1+W2*Q2*S2)/(W1*Q1+W2*Q2)；
Authentication processing unit judges certification success or not using the first score S1, the second score S2 and composite score SF；Specifically press
Following algorithm is judged；Wherein, there are 4 threshold values, respectively first threshold TL, second threshold TH, third threshold value TM, the 4th threshold
Value TF, relationship are TH ＞ TM ＞ TL；
If any one in the first score S1 or the second score S2 is less than threshold value TL, it is judged as recognition failures, the first score S1
Or second any one in score S2 be more than threshold value TH then as certification success；
In addition, the first score S1 and the second score S2 are smaller than TH, but any of which is one bigger than TM, then composite score SF is more than
Threshold value TF is judged as certification success.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410776425.1A CN104392226B (en) | 2014-12-15 | 2014-12-15 | Fingerprint identification system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410776425.1A CN104392226B (en) | 2014-12-15 | 2014-12-15 | Fingerprint identification system and method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104392226A CN104392226A (en) | 2015-03-04 |
| CN104392226B true CN104392226B (en) | 2018-06-08 |
Family
ID=52610127
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410776425.1A Active CN104392226B (en) | 2014-12-15 | 2014-12-15 | Fingerprint identification system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104392226B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105095722A (en) * | 2015-08-25 | 2015-11-25 | 宇龙计算机通信科技(深圳)有限公司 | Fingerprint verification method of mobile terminal and fingerprint verification system of mobile terminal |
| JP6717068B2 (en) * | 2016-06-13 | 2020-07-01 | コニカミノルタ株式会社 | Information processing terminal, information processing system, program, and control method |
| CN109145776A (en) * | 2018-08-01 | 2019-01-04 | 上海市数字证书认证中心有限公司 | Identity identifying method, device and identification terminal |
| CN109391622A (en) * | 2018-10-31 | 2019-02-26 | 北京中电华大电子设计有限责任公司 | A kind of the finger print identifying cloud security system and method for loading rule |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN201383157Y (en) * | 2009-03-30 | 2010-01-13 | 重庆工学院 | Image acquisition device of finger vein certification system |
| CN103793696A (en) * | 2014-02-12 | 2014-05-14 | 北京海鑫科金高科技股份有限公司 | Method and system for identifying fingerprints |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR100745980B1 (en) * | 2006-01-11 | 2007-08-06 | 삼성전자주식회사 | Score fusion method and apparatus thereof for combining multiple classifiers |
-
2014
- 2014-12-15 CN CN201410776425.1A patent/CN104392226B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN201383157Y (en) * | 2009-03-30 | 2010-01-13 | 重庆工学院 | Image acquisition device of finger vein certification system |
| CN103793696A (en) * | 2014-02-12 | 2014-05-14 | 北京海鑫科金高科技股份有限公司 | Method and system for identifying fingerprints |
Non-Patent Citations (2)
| Title |
|---|
| 一种提高不同类型指纹传感器匹配性能方法的研究;王峰等;《传感器与微系统》;20100131;第29卷(第1期);第65-68页 * |
| 融合指纹和人脸的生物特征身份认证方法;王小雪等;《重庆理工大学学报》;20130731;第27卷(第7期);第67-70页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104392226A (en) | 2015-03-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106326886B (en) | Finger vein image quality appraisal procedure based on convolutional neural networks | |
| CN103824055B (en) | A kind of face identification method based on cascade neural network | |
| CN104392226B (en) | Fingerprint identification system and method | |
| CN100356388C (en) | Biocharacteristics fusioned identity distinguishing and identification method | |
| US8306282B2 (en) | Hierarchical face recognition training method and hierarchical face recognition method thereof | |
| US20110299737A1 (en) | Vision-based hand movement recognition system and method thereof | |
| CN106920206B (en) | Steganalysis method based on antagonistic neural network | |
| US20150242678A1 (en) | Method and apparatus of recognizing facial expression using adaptive decision tree based on local feature extraction | |
| JP6245880B2 (en) | Information processing apparatus, information processing method, and program | |
| US20150347804A1 (en) | Method and system for estimating fingerprint pose | |
| Lu et al. | Finger vein recognition using generalized local line binary pattern | |
| JP2013535038A (en) | Image template masking | |
| Kaur | K-nearest neighbor classification approach for face and fingerprint at feature level fusion | |
| JP2010039788A (en) | Image processing apparatus and method thereof, and image processing program | |
| Song et al. | Facial expression recognition based on mixture of basic expressions and intensities | |
| Selwal et al. | Template security analysis of multimodal biometric frameworks based on fingerprint and hand geometry | |
| JP2011128766A5 (en) | ||
| WO2021031446A1 (en) | Offline individual handwriting recognition system and method employing two-dimensional dynamic feature | |
| JP6164284B2 (en) | Authentication apparatus, authentication method, and computer program | |
| US11599613B2 (en) | Method for controlling a security system of a charging station for charging electric vehicles | |
| EP2998928B1 (en) | Apparatus and method for extracting high watermark image from continuously photographed images | |
| Prashanth et al. | Off-line signature verification based on angular features | |
| Eid et al. | Development of Iris Security System Using Adaptive Quality-Based Template Fusion | |
| WO2018137226A1 (en) | Fingerprint extraction method and device | |
| Drishya et al. | Cyberbully image and text detection using convolutional neural networks |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |