CN106682567A - Acquisition processing method of fingerprint images and device - Google Patents
Acquisition processing method of fingerprint images and device Download PDFInfo
- Publication number
- CN106682567A CN106682567A CN201510767607.7A CN201510767607A CN106682567A CN 106682567 A CN106682567 A CN 106682567A CN 201510767607 A CN201510767607 A CN 201510767607A CN 106682567 A CN106682567 A CN 106682567A
- Authority
- CN
- China
- Prior art keywords
- fingerprint
- fingerprint image
- frame
- image
- threshold value
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- 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
Abstract
The invention discloses an acquisition processing method of fingerprint images and a device. The method and the device are used for improving fingerprint acquisition speed, thereby avoiding a condition of mis-acquisition or mistakenly considering that a machine crashes. The method comprises steps of after starting fingerprint acquisition, generating a frame of fingerprint image according to an acquired fingerprint; when determining that any one of the standard difference, the average gradient and space frequency of the frame of fingerprint image is smaller than a corresponding preset threshold value, restarting the fingerprint acquisition, and taking the frame of fingerprint image as a to-be-judged fingerprint image until determining that the standard difference, the average gradient and space frequency of the frame of fingerprint image are larger than or equal to the corresponding preset threshold values; determining whether the to-be-judged fingerprint image is a qualified fingerprint image and finishing the fingerprint acquisition of this time after determining that the to-be-judged fingerprint image is the qualified fingerprint image; and restarting the fingerprint acquisition when determining that the to-be-judged fingerprint image is an unqualified fingerprint image.
Description
Technical field
The present invention relates to fingerprint image acquisition technical field, more particularly to a kind of acquisition process side of fingerprint image
Method and device.
Background technology
During fingerprint collecting, the fingerprint for having many acquisition targets has damage or gathered person to mismatch
Situation, this just greatly have impact on the result of fingerprint collecting.The judgement of fingerprint collecting beginning and end is forbidden
Really, machine deadlock is easily gathered or is mistakenly considered by mistake, and the fingerprint integrity degree of the people of fingerprint damage is not enough,
Lack in individuality a little, easily do not gather because fingerprint image quality judges unqualified.
Collection fingerprint image after, in the deterministic process of fingerprint image quality, finger it is in different size,
It is simple according to size discrimination will make the IMAQ of some little fingerprints less than；When fingerprint overly moist or overdrying
Also the quality of fingerprint can be affected；Fingerprint can produce motion blur or mistake during collection either splicing
With the problems such as, fingerprint image can be made smudgy；The position of fingerprint does not produce skew at the center of fingerprint image
The judgement of fingerprint image quality can be affected etc. factor, in prior art fingerprint image is being judged
As only calculating a comprehensive quality fraction during quality, without specific index, what fingerprint image quality judged
The degree of accuracy is relatively low.
In sum, prior art is during fingerprint collecting, due to sentencing for fingerprint collecting beginning and end
It is fixed inaccurate, machine deadlock is easily gathered or is mistakenly considered by mistake.
The content of the invention
The acquiring and processing method and device of a kind of fingerprint image are embodiments provided, to improve fingerprint
The speed of collection, it is to avoid gather or be mistakenly considered the situation of machine deadlock by mistake.
A kind of acquiring and processing method of fingerprint image provided in an embodiment of the present invention, the method includes：Starting
After fingerprint collecting, a frame fingerprint image is generated according to the fingerprint for being collected；When it is determined that the frame fingerprint image
Standard deviation, average gradient and spatial frequency in any one when being less than corresponding predetermined threshold value, again
Start fingerprint collecting, until determining that the standard deviation of the frame fingerprint image, average gradient and spatial frequency are big
In or during equal to corresponding predetermined threshold value, using the frame fingerprint image as fingerprint image to be adjudicated；It is determined that described
Whether unsentenced fingerprint image is qualified fingerprint image, and it is determined that the unsentenced fingerprint image is conjunction
During lattice fingerprint image, terminate this fingerprint collecting；And it is determined that the unsentenced fingerprint image is not conform to
During lattice fingerprint image, fingerprint collecting is restarted.
In said method provided in an embodiment of the present invention, during fingerprint collecting, according to the finger for being collected
Line generates a frame fingerprint image, when it is determined that the standard deviation of the frame fingerprint image, average gradient and spatial frequency
In any one be less than corresponding predetermined threshold value when, restart fingerprint collecting, until determining the frame fingerprint
The standard deviation of image, average gradient and spatial frequency are all higher than or during equal to corresponding predetermined threshold value, by this
Frame fingerprint image as fingerprint image to be adjudicated, and it is determined that unsentenced fingerprint image be qualified fingerprint image
When, terminate this fingerprint collecting；And when it is determined that unsentenced fingerprint image is unqualified fingerprint image,
During restarting fingerprint collecting, with prior art fingerprint collecting, due to fingerprint collecting beginning and end
Judge inaccurate, easily gather or be mistakenly considered machine by mistake and crash to compare, when it is determined that the fingerprint image for generating
Any one in standard deviation, average gradient and spatial frequency is less than corresponding predetermined threshold value or waits to adjudicate
Fingerprint image when being unqualified fingerprint image, fingerprint collecting is restarted, and in unsentenced fingerprint image
For qualified fingerprint image when, terminate this fingerprint collecting, the relative speed that can improve fingerprint collecting is kept away
Exempt from the situation for gathering or being mistakenly considered machine deadlock by mistake.
In a kind of possible embodiment, in said method provided in an embodiment of the present invention, it is determined that described treat
Whether the fingerprint image of judgement is qualified fingerprint image, including：Determine many in the unsentenced fingerprint image
The fraction of individual fingerprint, and the fraction sum of the plurality of fingerprint is calculated, wherein, the fingerprint refers to
Mark includes：Fingerprint area accounting, fingerprint humidity, fingerprint skew and fingerprint clear degree；Will be the plurality of
The fraction sum of fingerprint is compared with the first predetermined threshold value, when the plurality of fingerprint fraction it
During with more than or equal to the first predetermined threshold value, determine that the unsentenced fingerprint image is qualified fingerprint image；
Otherwise, it determines the unsentenced fingerprint image is unqualified fingerprint image.
In said method provided in an embodiment of the present invention, by multiple fingerprints in the unsentenced fingerprint image of determination
The fraction of index, including：What the fraction of fingerprint area accounting, the fraction of fingerprint humidity, fingerprint offset divides
The fraction of number and fingerprint clear degree, calculates the fraction sum of multiple fingerprints, and by multiple fingerprints
Fraction sum be compared with the first predetermined threshold value, so as to determine unsentenced fingerprint image according to comparative result
The quality of picture, according to fingerprint area accounting, fingerprint humidity, four fingers of fingerprint skew and fingerprint clear degree
The fraction sum of line index determines the quality of fingerprint image so that the judgement of fingerprint image quality is more comprehensive,
So as to improve the degree of accuracy of fingerprint image quality judgement.
In a kind of possible embodiment, in said method provided in an embodiment of the present invention, when it is determined that described
Unsentenced fingerprint image is that the method also includes after unqualified fingerprint image：For multiple fingerprints
In each fingerprint, the fraction of fingerprint predetermined threshold value corresponding with the index is compared,
Determine whether the fraction of the fingerprint is qualified according to comparative result, and show underproof fingerprint.
In said method provided in an embodiment of the present invention, when it is determined that unsentenced fingerprint image is unqualified fingerprint
After image, for each fingerprint in multiple fingerprints, the fraction of the fingerprint is referred to this
Mark corresponding predetermined threshold value to be compared, determine whether the fraction of the fingerprint is qualified according to comparative result,
And underproof fingerprint is shown, to exist during a fingerprint collecting before avoiding in a rear fingerprint collecting
Problem, improve secondary acquisition the degree of accuracy so that the definition and availability of fingerprint image is lifted.
It is described when determination in said method provided in an embodiment of the present invention in a kind of possible embodiment
Any one is less than corresponding default threshold in the standard deviation of the frame fingerprint image, average gradient and spatial frequency
During value, fingerprint collecting is restarted, until determining the standard deviation of the frame fingerprint image, average gradient and sky
Between frequency be all higher than or during equal to corresponding predetermined threshold value, using the frame fingerprint image as fingerprint image to be adjudicated
Picture, including：Determine the standard deviation of the frame fingerprint image, and the standard deviation of the frame fingerprint image is pre- with second
If threshold value is compared, when the standard deviation of the frame fingerprint image is less than the second predetermined threshold value, restarting refers to
Line is gathered；Otherwise, it determines the average gradient of the frame fingerprint image, and by the average gradient of the frame fingerprint image
It is compared with the 3rd predetermined threshold value, when the average gradient of the frame fingerprint image is less than three predetermined threshold values,
Restarting fingerprint collecting；Otherwise, it determines the spatial frequency of the frame fingerprint image, and by the frame fingerprint image
Spatial frequency be compared with the 4th predetermined threshold value, when the spatial frequency of the frame fingerprint image is less than the 4th pre-
If during threshold value, restarting fingerprint collecting；Otherwise, using the frame fingerprint image as unsentenced fingerprint image.
A kind of acquisition processing device of fingerprint image provided in an embodiment of the present invention, including：Collecting unit, uses
In after fingerprint collecting is started, a frame fingerprint image is generated according to the fingerprint for being collected；First processes single
Unit, for when any one in standard deviation, average gradient and the spatial frequency for determining the frame fingerprint image
During less than corresponding predetermined threshold value, restart fingerprint collecting, until determine the standard deviation of the frame fingerprint image,
Average gradient and spatial frequency are all higher than or during equal to corresponding predetermined threshold value, using the frame fingerprint image as
Fingerprint image to be adjudicated；Second processing unit, for determining whether the unsentenced fingerprint image is qualified
Fingerprint image, and when it is determined that the unsentenced fingerprint image is qualified fingerprint image, and it is determined that institute
State unsentenced fingerprint image for unqualified fingerprint image when, restart fingerprint collecting.
In said apparatus provided in an embodiment of the present invention, during fingerprint collecting, according to the finger for being collected
Line generates a frame fingerprint image, when it is determined that the standard deviation of the frame fingerprint image, average gradient and spatial frequency
In any one be less than corresponding predetermined threshold value when, restart fingerprint collecting, until determining the frame fingerprint
The standard deviation of image, average gradient and spatial frequency are all higher than or during equal to corresponding predetermined threshold value, by this
Frame fingerprint image as fingerprint image to be adjudicated, and it is determined that unsentenced fingerprint image be qualified fingerprint image
When, terminate this fingerprint collecting；And when it is determined that unsentenced fingerprint image is unqualified fingerprint image,
During restarting fingerprint collecting, with prior art fingerprint collecting, due to fingerprint collecting beginning and end
Judge inaccurate, easily gather or be mistakenly considered machine by mistake and crash to compare, when it is determined that the fingerprint image for generating
Any one in standard deviation, average gradient and spatial frequency is less than corresponding predetermined threshold value or waits to adjudicate
Fingerprint image when being unqualified fingerprint image, fingerprint collecting is restarted, and in unsentenced fingerprint image
For qualified fingerprint image when, terminate this fingerprint collecting, the relative speed that can improve fingerprint collecting is kept away
Exempt from the situation for gathering or being mistakenly considered machine deadlock by mistake.
In a kind of possible embodiment, in said apparatus provided in an embodiment of the present invention, at described second
Reason unit determines whether the unsentenced fingerprint image is qualified fingerprint image, specifically for：Described second
Processing unit determines the fraction of multiple fingerprints in the unsentenced fingerprint image, and calculates the plurality of
The fraction sum of fingerprint, wherein, the fingerprint includes：Fingerprint area accounting, fingerprint humidity,
Fingerprint offsets and fingerprint clear degree；The second processing unit is by the fraction sum of the plurality of fingerprint
It is compared with the first predetermined threshold value, when the fraction sum of the plurality of fingerprint is more than or equal to first pre-
If during threshold value, the second processing unit determines that the unsentenced fingerprint image is qualified fingerprint image；It is no
Then, the second processing unit determines that the unsentenced fingerprint image is unqualified fingerprint image.
In said apparatus provided in an embodiment of the present invention, by multiple fingerprints in the unsentenced fingerprint image of determination
The fraction of index, including：What the fraction of fingerprint area accounting, the fraction of fingerprint humidity, fingerprint offset divides
The fraction of number and fingerprint clear degree, calculates the fraction sum of multiple fingerprints, and by multiple fingerprints
Fraction sum be compared with the first predetermined threshold value, so as to determine unsentenced fingerprint image according to comparative result
The quality of picture, according to fingerprint area accounting, fingerprint humidity, four fingers of fingerprint skew and fingerprint clear degree
The fraction sum of line index determines the quality of fingerprint image so that the judgement of fingerprint image quality is more comprehensive,
So as to improve the degree of accuracy of fingerprint image quality judgement.
In a kind of possible embodiment, in said apparatus provided in an embodiment of the present invention, when described second
Processing unit determines the unsentenced fingerprint image after unqualified fingerprint image, to be additionally operable to：For many
Each fingerprint in individual fingerprint, the second processing unit refers to the fraction of the fingerprint with this
Mark corresponding predetermined threshold value to be compared, determine whether the fraction of the fingerprint is qualified according to comparative result,
And show underproof fingerprint.
In said apparatus provided in an embodiment of the present invention, when it is determined that unsentenced fingerprint image is unqualified fingerprint
After image, for each fingerprint in multiple fingerprints, the fraction of the fingerprint is referred to this
Mark corresponding predetermined threshold value to be compared, determine whether the fraction of the fingerprint is qualified according to comparative result,
And underproof fingerprint is shown, to exist during a fingerprint collecting before avoiding in a rear fingerprint collecting
Problem, improve secondary acquisition the degree of accuracy so that the definition and availability of fingerprint image is lifted.
In a kind of possible embodiment, in said apparatus provided in an embodiment of the present invention, at described first
Reason unit specifically for：Determine the standard deviation of the frame fingerprint image, and by the standard deviation of the frame fingerprint image with
Second predetermined threshold value is compared, when the standard deviation of the frame fingerprint image is less than the second predetermined threshold value, again
Start fingerprint collecting；Otherwise, it determines the average gradient of the frame fingerprint image, and putting down the frame fingerprint image
Gradient is compared with the 3rd predetermined threshold value, when the average gradient of the frame fingerprint image is less than the 3rd default threshold
During value, fingerprint collecting is restarted；Otherwise, it determines the spatial frequency of the frame fingerprint image, and the frame is referred to
The spatial frequency of print image is compared with the 4th predetermined threshold value, when the spatial frequency of the frame fingerprint image is less than
During four predetermined threshold values, fingerprint collecting is restarted；Otherwise, using the frame fingerprint image as unsentenced finger
Print image.
Description of the drawings
Fig. 1 is a kind of schematic flow diagram of the acquiring and processing method of fingerprint image provided in an embodiment of the present invention；
Fig. 2 is the schematic flow diagram of the processing method of the fingerprint image to generation provided in an embodiment of the present invention；
Fig. 3 is the exemplary flow of the processing method to unsentenced fingerprint image provided in an embodiment of the present invention
Figure；
Fig. 4 is a kind of structural representation of the acquisition processing device of fingerprint image provided in an embodiment of the present invention.
Specific embodiment
Below in conjunction with the accompanying drawings, to the acquiring and processing method and dress of a kind of fingerprint image provided in an embodiment of the present invention
The specific embodiment put is described in detail.
The process acquisition method of a kind of fingerprint image provided in an embodiment of the present invention, as shown in figure 1, the method
Including：
Step 102, after fingerprint collecting is started, according to the fingerprint for being collected a frame fingerprint image is generated；
Step 104, when it is determined that appointing in the standard deviation of the frame fingerprint image, average gradient and spatial frequency
When meaning one is less than corresponding predetermined threshold value, fingerprint collecting is restarted, until determining the frame fingerprint image
Standard deviation, average gradient and spatial frequency are all higher than or during equal to corresponding predetermined threshold value, by the frame fingerprint
Image is used as fingerprint image to be adjudicated；
Step 106, determines whether unsentenced fingerprint image is qualified fingerprint image, and it is determined that waiting to adjudicate
Fingerprint image be qualified fingerprint image when, terminate this fingerprint collecting；And it is determined that unsentenced fingerprint
When image is unqualified fingerprint image, fingerprint collecting is restarted.
In method provided in an embodiment of the present invention, during fingerprint collecting, according to the fingerprint life for being collected
Into a frame fingerprint image, when it is determined that in the standard deviation of the frame fingerprint image, average gradient and spatial frequency
When any one is less than corresponding predetermined threshold value, fingerprint collecting is restarted, until determining the frame fingerprint image
Standard deviation, average gradient and spatial frequency be all higher than or during equal to corresponding predetermined threshold value, the frame is referred to
Print image as fingerprint image to be adjudicated, and it is determined that unsentenced fingerprint image be qualified fingerprint image when,
Terminate this fingerprint collecting；And when it is determined that unsentenced fingerprint image is unqualified fingerprint image, again
During starting fingerprint collecting, with prior art fingerprint collecting, due to the judgement of fingerprint collecting beginning and end
It is inaccurate, machine deadlock is easily gathered or be mistakenly considered by mistake and is compared, when it is determined that the standard of the fingerprint image for generating
Any one in difference, average gradient and spatial frequency is less than corresponding predetermined threshold value or unsentenced finger
When print image is unqualified fingerprint image, fingerprint collecting is restarted, and be conjunction in unsentenced fingerprint image
During lattice fingerprint image, terminate this fingerprint collecting, the relative speed that can improve fingerprint collecting, it is to avoid by mistake
Collection is mistakenly considered the situation that machine crashes.
When being embodied as, the standard deviation of fingerprint image, average gradient and spatial frequency can adopt existing
Mode in technology is calculated, and here is omitted.
In a kind of possible embodiment, in method provided in an embodiment of the present invention, when it is determined that the frame fingerprint
When any one is less than corresponding predetermined threshold value in the standard deviation of image, average gradient and spatial frequency, weight
It is new to start fingerprint collecting, until determining that the standard deviation of the frame fingerprint image, average gradient and spatial frequency are equal
During more than or equal to corresponding predetermined threshold value, using the frame fingerprint image as fingerprint image to be adjudicated, including：
Determine the standard deviation of the frame fingerprint image, and the standard deviation of the frame fingerprint image is carried out with the second predetermined threshold value
Relatively, when the standard deviation of the frame fingerprint image is less than the second predetermined threshold value, fingerprint collecting is restarted；It is no
Then, determine the average gradient of the frame fingerprint image, and the average gradient of the frame fingerprint image is preset with the 3rd
Threshold value is compared, and when the average gradient of the frame fingerprint image is less than three predetermined threshold values, restarting refers to
Line is gathered；Otherwise, it determines the spatial frequency of the frame fingerprint image, and by the spatial frequency of the frame fingerprint image
It is compared with the 4th predetermined threshold value, when the spatial frequency of the frame fingerprint image is less than four predetermined threshold values,
Restarting fingerprint collecting；Otherwise, using the frame fingerprint image as unsentenced fingerprint image.
As more specific embodiment, during fingerprint collecting, the process side of the fingerprint image to generating
The step of method, as shown in Fig. 2 including：
Step 202, after starting fingerprint collecting, according to the fingerprint for being gathered a frame fingerprint image is generated；
Step 204, calculates the standard deviation of the frame fingerprint image, and determines whether the standard deviation of the two field picture is little
In the first predetermined threshold value, when the standard deviation of the two field picture is less than the first predetermined threshold value, execution step 212,
Otherwise, execution step 206；
Step 206, calculates the average gradient of the frame fingerprint image, and determines that the average gradient of the two field picture is
It is no to be less than the second predetermined threshold value, when the average gradient of the two field picture is less than the second predetermined threshold value, execution step
212, otherwise, execution step 208；
Step 208, calculates the spatial frequency of the frame fingerprint image, and determines that the spatial frequency of the two field picture is
It is no to be less than the 3rd predetermined threshold value, when the spatial frequency of the two field picture is less than three predetermined threshold values, execution step
212, otherwise, execution step 210；
Step 210, determine the frame fingerprint image standard deviation, average gradient and spatial frequency be all higher than or
Equal to corresponding predetermined threshold value, using the frame fingerprint image as unsentenced fingerprint image；
Step 212, restarts fingerprint collecting.
In this embodiment, the first predetermined threshold value, the second predetermined threshold value and the 3rd predetermined threshold value can be with roots
According to free setting is required, for example：First predetermined threshold value, the second predetermined threshold value and the 3rd predetermined threshold value are all provided with
It is set to 60.The determination order of the standard deviation of fingerprint image, average gradient and spatial frequency is in the embodiment
Standard deviation, average gradient, the order of spatial frequency, in other embodiments of the present invention, fingerprint image
Standard deviation, average gradient and spatial frequency determination order can be it is arbitrary, for example：Average gradient,
Spatial frequency, the order of standard deviation or spatial frequency, standard deviation, the order of average gradient.
In a kind of possible embodiment, in method provided in an embodiment of the present invention, unsentenced finger is determined
Whether print image is qualified fingerprint image, including：Determine multiple fingerprints in unsentenced fingerprint image
Fraction, and the fraction sum of multiple fingerprints is calculated, wherein, fingerprint includes：Fingerprint area accounting,
Fingerprint humidity, fingerprint skew and fingerprint clear degree；The fraction sum of multiple fingerprints is pre- with first
If threshold value is compared, when the fraction sum of multiple fingerprints is more than or equal to the first predetermined threshold value, really
Fixed unsentenced fingerprint image is qualified fingerprint image；Otherwise, it determines unsentenced fingerprint image is unqualified
Fingerprint image.
In method provided in an embodiment of the present invention, by multiple fingerprints in the unsentenced fingerprint image of determination
Fraction, including：The fraction of fingerprint area accounting, the fraction of fingerprint humidity, fingerprint skew fraction with
And the fraction of fingerprint clear degree, calculate the fraction sum of multiple fingerprints, and dividing multiple fingerprints
Number sum is compared with the first predetermined threshold value, so as to determine unsentenced fingerprint image according to comparative result
Quality, refers to according to fingerprint area accounting, fingerprint humidity, fingerprint skew and four fingerprints of fingerprint clear degree
Target fraction sum determines the quality of fingerprint image so that the judgement of fingerprint image quality is more comprehensive, so as to
Improve the degree of accuracy of fingerprint image quality judgement.
When being embodied as, the first predetermined threshold value can set according to the requirement to fingerprint image quality, right
The quality requirement of fingerprint image is higher, then the value for arranging can be bigger, for example：Each fingerprint point
Number is 100 points, then the first predetermined threshold value could be arranged to 380 points, when the fraction sum of multiple fingerprints
More than or equal to 380 timesharing, unsentenced fingerprint image is determined for qualified fingerprint image, each fingerprint
The calculation of fraction is as follows, specifically：
Fingerprint area accounting：Can be with by the way of intensity slicing and automatic threshold method, specifically, first
By the front background separation of unsentenced fingerprint image out, this part uses intensity slicing method and treats
The fingerprint image of judgement carries out separation calculation gray variance, then finds suitable threshold value, can adopt iteration
Method carrys out selected threshold, filters out suitable block as foreground blocks, and remaining is background block, calculates ratio.
Fingerprint humidity：Gray variance method can be combined using split plot design, specifically, be accounted for fingerprint area
The calculation of ratio, needs to judge dry fingerprint-block and wet fingerprint-block by standard deviation, and then it is dry to calculate fingerprint
Humidity.
Fingerprint offsets：Need to calculate fingerprint center and center picture angulation, and then calculate fingerprint skew
Fraction.
Fingerprint clear degree：Local Resolution method is combined using global definition, namely is needed to global and local
Definition all evaluate, can first using global determining method, for example：The methods such as Brenner, local
The theoretical method of ridge paddy line definition can be used.
In a kind of possible embodiment, in method provided in an embodiment of the present invention, when it is determined that unsentenced
Fingerprint image is that the method also includes after unqualified fingerprint image：For each in multiple fingerprints
Fingerprint, the fraction of fingerprint predetermined threshold value corresponding with the index is compared, according to comparing
As a result determine whether the fraction of the fingerprint is qualified, and show underproof fingerprint.
In method provided in an embodiment of the present invention, when it is determined that unsentenced fingerprint image is unqualified fingerprint image
Afterwards, for each fingerprint in multiple fingerprints, by the fraction of the fingerprint and the index pair
The predetermined threshold value answered is compared, and determines whether the fraction of the fingerprint is qualified according to comparative result, and shows
Show underproof fingerprint, with asking for existing during a fingerprint collecting before avoiding in a rear fingerprint collecting
Topic, improves the degree of accuracy of secondary acquisition so that the definition and availability of fingerprint image is lifted.Wherein,
The corresponding predetermined threshold value of each fingerprint can freely set according to the requirement of the fingerprint.
As more specific embodiment, the process to unsentenced fingerprint image provided in an embodiment of the present invention
The step of method, as shown in figure 3, including：
Step 302, obtains unsentenced fingerprint image；
Step 304, determines the fraction of each fingerprint, specifically, calculates dividing for fingerprint area accounting
Number, the fraction for calculating fingerprint humidity, the fraction for calculating fingerprint skew and the fraction for calculating fingerprint clear degree；
Step 306, calculates the fraction sum of multiple fingerprints, judges the fraction sum of multiple fingerprints
It is whether qualified, specifically, the fraction sum of multiple fingerprints and the first predetermined threshold value are compared,
When the fraction sum of multiple fingerprints is more than or equal to the first predetermined threshold value, multiple fingerprints are determined
Fraction sum is qualified, execution step 312, when the fraction sum of multiple fingerprints is less than the first predetermined threshold value
When, determine that the fraction sum of multiple fingerprints is unqualified, execution step 308；
Step 308, when the fraction sum of multiple fingerprints is unqualified, determines unsentenced fingerprint image
For unqualified fingerprint image, fingerprint collecting is restarted；
Step 310, for each fingerprint in multiple fingerprints, by the fraction of the fingerprint with
The corresponding predetermined threshold value of the index is compared, and determines whether the fraction of the fingerprint closes according to comparative result
Lattice, and underproof fingerprint is shown, for example：The fraction of fingerprint area accounting shows fingerprint when unqualified
IMAQ is imperfect, and the fraction of fingerprint humidity shows fingerprint overdrying or overly moist, fingerprint skew when unqualified
Fraction it is unqualified when show that fingerprint degrees of offset is excessive, the fraction of fingerprint clear degree shows fingerprint when unqualified
Fuzzy, definition is not enough；
Step 312, when the fraction sum of multiple fingerprints is qualified, it is determined that the fingerprint image for collecting is
Qualified fingerprint image, terminates this fingerprint collecting.
A kind of acquisition processing device of fingerprint image provided in an embodiment of the present invention, as shown in figure 4, including：
Collecting unit 402, for after fingerprint collecting is started, according to the fingerprint for being collected a frame fingerprint being generated
Image；First processing units 404, for when determine the standard deviation of the frame fingerprint image, average gradient and
When any one in spatial frequency is less than corresponding predetermined threshold value, fingerprint collecting is restarted, until determining
The standard deviation of the frame fingerprint image, average gradient and spatial frequency are all higher than or equal to corresponding predetermined threshold value
When, using the frame fingerprint image as fingerprint image to be adjudicated；Second processing unit 406, waits to sentence for determining
Whether fingerprint image certainly is qualified fingerprint image, and it is determined that unsentenced fingerprint image is qualified fingerprint image
During picture, and when it is determined that unsentenced fingerprint image is unqualified fingerprint image, fingerprint collecting is restarted.
In device provided in an embodiment of the present invention, during fingerprint collecting, according to the fingerprint life for being collected
Into a frame fingerprint image, when it is determined that in the standard deviation of the frame fingerprint image, average gradient and spatial frequency
When any one is less than corresponding predetermined threshold value, fingerprint collecting is restarted, until determining the frame fingerprint image
Standard deviation, average gradient and spatial frequency be all higher than or during equal to corresponding predetermined threshold value, the frame is referred to
Print image as fingerprint image to be adjudicated, and it is determined that unsentenced fingerprint image be qualified fingerprint image when,
Terminate this fingerprint collecting；And when it is determined that unsentenced fingerprint image is unqualified fingerprint image, again
During starting fingerprint collecting, with prior art fingerprint collecting, due to the judgement of fingerprint collecting beginning and end
It is inaccurate, machine deadlock is easily gathered or be mistakenly considered by mistake and is compared, when it is determined that the standard of the fingerprint image for generating
Any one in difference, average gradient and spatial frequency is less than corresponding predetermined threshold value or unsentenced finger
When print image is unqualified fingerprint image, fingerprint collecting is restarted, and be conjunction in unsentenced fingerprint image
During lattice fingerprint image, terminate this fingerprint collecting, the relative speed that can improve fingerprint collecting, it is to avoid by mistake
Collection is mistakenly considered the situation that machine crashes.
In a kind of possible embodiment, in device provided in an embodiment of the present invention, second processing unit 406
Determine whether unsentenced fingerprint image is qualified fingerprint image, specifically for：Second processing unit 406 is true
The fraction of multiple fingerprints in fixed unsentenced fingerprint image, and calculate multiple fingerprints fraction it
With, wherein, fingerprint includes：Fingerprint area accounting, fingerprint humidity, fingerprint skew and fingerprint are clear
Clear degree；Second processing unit 406 is compared the fraction sum of multiple fingerprints and the first predetermined threshold value,
When the fraction sum of multiple fingerprints is more than or equal to the first predetermined threshold value, second processing unit 406 is true
Fixed unsentenced fingerprint image is qualified fingerprint image；Otherwise, second processing unit 406 determines unsentenced
Fingerprint image is unqualified fingerprint image.
In device provided in an embodiment of the present invention, by multiple fingerprints in the unsentenced fingerprint image of determination
Fraction, including：The fraction of fingerprint area accounting, the fraction of fingerprint humidity, fingerprint skew fraction with
And the fraction of fingerprint clear degree, calculate the fraction sum of multiple fingerprints, and dividing multiple fingerprints
Number sum is compared with the first predetermined threshold value, so as to determine unsentenced fingerprint image according to comparative result
Quality, refers to according to fingerprint area accounting, fingerprint humidity, fingerprint skew and four fingerprints of fingerprint clear degree
Target fraction sum determines the quality of fingerprint image so that the judgement of fingerprint image quality is more comprehensive, so as to
Improve the degree of accuracy of fingerprint image quality judgement.
In a kind of possible embodiment, in device provided in an embodiment of the present invention, when second processing unit
406 determine that unsentenced fingerprint image is after unqualified fingerprint image, to be additionally operable to：Refer to for multiple fingerprints
Each fingerprint in mark, second processing unit 406 is corresponding with the index by the fraction of the fingerprint
Predetermined threshold value is compared, and determines whether the fraction of the fingerprint is qualified according to comparative result, and shows not
Qualified fingerprint.
In device provided in an embodiment of the present invention, when it is determined that unsentenced fingerprint image is unqualified fingerprint image
Afterwards, for each fingerprint in multiple fingerprints, by the fraction of the fingerprint and the index pair
The predetermined threshold value answered is compared, and determines whether the fraction of the fingerprint is qualified according to comparative result, and shows
Show underproof fingerprint, with asking for existing during a fingerprint collecting before avoiding in a rear fingerprint collecting
Topic, improves the degree of accuracy of secondary acquisition so that the definition and availability of fingerprint image is lifted.
In a kind of possible embodiment, in device provided in an embodiment of the present invention, first processing units 404
Specifically for：Determine the standard deviation of the frame fingerprint image, and the standard deviation of the frame fingerprint image is pre- with second
If threshold value is compared, when the standard deviation of the frame fingerprint image is less than the second predetermined threshold value, restarting refers to
Line is gathered；Otherwise, it determines the average gradient of the frame fingerprint image, and by the average gradient of the frame fingerprint image
It is compared with the 3rd predetermined threshold value, when the average gradient of the frame fingerprint image is less than three predetermined threshold values,
Restarting fingerprint collecting；Otherwise, it determines the spatial frequency of the frame fingerprint image, and by the frame fingerprint image
Spatial frequency be compared with the 4th predetermined threshold value, when the spatial frequency of the frame fingerprint image is less than the 4th pre-
If during threshold value, restarting fingerprint collecting；Otherwise, using the frame fingerprint image as unsentenced fingerprint image.
The harvester of fingerprint image provided in an embodiment of the present invention, can be integrated in fingerprint capturer or refer to
In line identifier, wherein, collecting unit 402 can adopt image collection chip, first processing units 404
Can be using processors such as CPU with second processing unit 406.
In sum, the acquiring and processing method and device of a kind of fingerprint image provided in an embodiment of the present invention,
During fingerprint collecting, a frame fingerprint image is generated according to the fingerprint for being collected, when it is determined that the frame fingerprint image
When any one in the standard deviation of picture, average gradient and spatial frequency is less than corresponding predetermined threshold value, weight
It is new to start fingerprint collecting, until determining that the standard deviation of the frame fingerprint image, average gradient and spatial frequency are equal
During more than or equal to corresponding predetermined threshold value, using the frame fingerprint image as fingerprint image to be adjudicated, and true
When fixed unsentenced fingerprint image is qualified fingerprint image, terminate this fingerprint collecting；And it is determined that waiting to sentence
When fingerprint image certainly is unqualified fingerprint image, fingerprint collecting is restarted, when it is determined that the fingerprint image for generating
Any one in the standard deviation of picture, average gradient and spatial frequency is less than corresponding predetermined threshold value or treats
When the fingerprint image of judgement is unqualified fingerprint image, fingerprint collecting is restarted, and in unsentenced fingerprint
When image is qualified fingerprint image, terminate this fingerprint collecting, the relative speed that can improve fingerprint collecting,
Avoid gathering or being mistakenly considered the situation of machine deadlock by mistake.
Those skilled in the art are it should be appreciated that embodiments of the invention can be provided as method, system or meter
Calculation machine program product.Therefore, the present invention can be using complete hardware embodiment, complete software embodiment or knot
Close the form of the embodiment in terms of software and hardware.And, the present invention can be adopted and wherein wrapped at one or more
Computer-usable storage medium containing computer usable program code (including but not limited to magnetic disc store and
Optical memory etc.) on implement computer program form.
The present invention is produced with reference to method according to embodiments of the present invention, equipment (system) and computer program
The flow chart and/or block diagram of product is describing.It should be understood that can by computer program instructions flowchart and
/ or block diagram in each flow process and/or square frame and flow chart and/or the flow process in block diagram and/
Or the combination of square frame.These computer program instructions can be provided to all-purpose computer, special-purpose computer, embedded
The processor of formula processor or other programmable data processing devices is producing a machine so that by calculating
The instruction of the computing device of machine or other programmable data processing devices is produced for realizing in flow chart one
The device of the function of specifying in individual flow process or one square frame of multiple flow processs and/or block diagram or multiple square frames.
These computer program instructions may be alternatively stored in can guide computer or other programmable datas process to set
In the standby computer-readable memory for working in a specific way so that in being stored in the computer-readable memory
Instruction produce and include the manufacture of command device, command device realization is in one flow process or multiple of flow chart
The function of specifying in one square frame of flow process and/or block diagram or multiple square frames.
These computer program instructions also can be loaded in computer or other programmable data processing devices, made
Obtain and series of operation steps is performed on computer or other programmable devices to produce computer implemented place
Reason, so as to the instruction performed on computer or other programmable devices is provided for realizing in flow chart one
The step of function of specifying in flow process or one square frame of multiple flow processs and/or block diagram or multiple square frames.
Obviously, those skilled in the art can carry out various changes and modification without deviating from this to the present invention
Bright spirit and scope.So, if the present invention these modification and modification belong to the claims in the present invention and
Within the scope of its equivalent technologies, then the present invention is also intended to comprising these changes and modification.
Claims (8)
1. a kind of acquiring and processing method of fingerprint image, it is characterised in that the method includes：
After fingerprint collecting is started, a frame fingerprint image is generated according to the fingerprint for being collected；
When it is determined that any one in the standard deviation of the frame fingerprint image, average gradient and spatial frequency is less than
During corresponding predetermined threshold value, fingerprint collecting is restarted, until determining the standard deviation of the frame fingerprint image, putting down
Gradient and spatial frequency are all higher than or during equal to corresponding predetermined threshold value, using the frame fingerprint image as treating
Judgement fingerprint image；
Determine whether the unsentenced fingerprint image is qualified fingerprint image, and it is determined that described unsentenced
When fingerprint image is qualified fingerprint image, terminate this fingerprint collecting；And it is determined that the unsentenced finger
When print image is unqualified fingerprint image, fingerprint collecting is restarted.
2. acquiring and processing method according to claim 1, it is characterised in that it is determined that described wait to adjudicate
Fingerprint image whether be qualified fingerprint image, including：
Determine the fraction of multiple fingerprints in the unsentenced fingerprint image, and calculate the plurality of fingerprint
The fraction sum of index, wherein, the fingerprint includes：Fingerprint area accounting, fingerprint humidity, refer to
Line offsets and fingerprint clear degree；
The fraction sum of the plurality of fingerprint and the first predetermined threshold value are compared, when the plurality of finger
When the fraction sum of line index is more than or equal to the first predetermined threshold value, determine that the unsentenced fingerprint image is
Qualified fingerprint image；Otherwise, it determines the unsentenced fingerprint image is unqualified fingerprint image.
3. acquiring and processing method according to claim 2, it is characterised in that when it is determined that described wait to sentence
Fingerprint image certainly is that the method also includes after unqualified fingerprint image：
It is for each fingerprint in multiple fingerprints, the fraction of the fingerprint is corresponding with the index
Predetermined threshold value be compared, determine whether the fraction of the fingerprint qualified according to comparative result, and show
Underproof fingerprint.
4. acquiring and processing method according to claim 1, it is characterised in that described when determining the frame
Any one is less than corresponding predetermined threshold value in the standard deviation of fingerprint image, average gradient and spatial frequency
When, fingerprint collecting is restarted, until determining the standard deviation of the frame fingerprint image, average gradient and space
Frequency is all higher than or during equal to corresponding predetermined threshold value, using the frame fingerprint image as fingerprint image to be adjudicated,
Including：
Determine the standard deviation of the frame fingerprint image, and by the standard deviation of the frame fingerprint image and the second predetermined threshold value
It is compared, when the standard deviation of the frame fingerprint image is less than the second predetermined threshold value, restarts fingerprint collecting；
Otherwise,
Determine the average gradient of the frame fingerprint image, and the average gradient of the frame fingerprint image is preset with the 3rd
Threshold value is compared, and when the average gradient of the frame fingerprint image is less than three predetermined threshold values, restarting refers to
Line is gathered；Otherwise,
Determine the spatial frequency of the frame fingerprint image, and the spatial frequency of the frame fingerprint image is preset with the 4th
Threshold value is compared, and when the spatial frequency of the frame fingerprint image is less than four predetermined threshold values, restarting refers to
Line is gathered；Otherwise, using the frame fingerprint image as unsentenced fingerprint image.
5. a kind of acquisition processing device of fingerprint image, it is characterised in that include：
Collecting unit, for after fingerprint collecting is started, according to the fingerprint for being collected a frame fingerprint being generated
Image；
First processing units, for when the standard deviation, average gradient and the space frequency that determine the frame fingerprint image
When any one in rate is less than corresponding predetermined threshold value, fingerprint collecting is restarted, until determining that the frame refers to
The standard deviation of print image, average gradient and spatial frequency are all higher than or during equal to corresponding predetermined threshold value, will
The frame fingerprint image is used as fingerprint image to be adjudicated；
Second processing unit, for determining whether the unsentenced fingerprint image is qualified fingerprint image, and
When it is determined that the unsentenced fingerprint image is qualified fingerprint image, and it is determined that the unsentenced finger
When print image is unqualified fingerprint image, fingerprint collecting is restarted.
6. acquisition processing device according to claim 5, it is characterised in that the second processing list
Unit determines whether the unsentenced fingerprint image is qualified fingerprint image, specifically for：
The second processing unit determines the fraction of multiple fingerprints in the unsentenced fingerprint image, and
The fraction sum of the plurality of fingerprint is calculated, wherein, the fingerprint includes：Fingerprint area accounting,
Fingerprint humidity, fingerprint skew and fingerprint clear degree；
The second processing unit carries out the fraction sum of the plurality of fingerprint and the first predetermined threshold value
Relatively, when the fraction sum of the plurality of fingerprint is more than or equal to the first predetermined threshold value, described second
Processing unit determines that the unsentenced fingerprint image is qualified fingerprint image；Otherwise, the second processing list
Unit determines that the unsentenced fingerprint image is unqualified fingerprint image.
7. acquisition processing device according to claim 6, it is characterised in that when the second processing
Unit determines the unsentenced fingerprint image after unqualified fingerprint image, to be additionally operable to：
For each fingerprint in multiple fingerprints, the second processing unit is by the fingerprint
Fraction predetermined threshold value corresponding with the index is compared, and according to comparative result the fraction of the fingerprint is determined
It is whether qualified, and show underproof fingerprint.
8. acquisition processing device according to claim 5, it is characterised in that described first processes single
Unit specifically for：
Determine the standard deviation of the frame fingerprint image, and by the standard deviation of the frame fingerprint image and the second predetermined threshold value
It is compared, when the standard deviation of the frame fingerprint image is less than the second predetermined threshold value, restarts fingerprint collecting；
Otherwise,
Determine the average gradient of the frame fingerprint image, and the average gradient of the frame fingerprint image is preset with the 3rd
Threshold value is compared, and when the average gradient of the frame fingerprint image is less than three predetermined threshold values, restarting refers to
Line is gathered；Otherwise,
Determine the spatial frequency of the frame fingerprint image, and the spatial frequency of the frame fingerprint image is preset with the 4th
Threshold value is compared, and when the spatial frequency of the frame fingerprint image is less than four predetermined threshold values, restarting refers to
Line is gathered；Otherwise, using the frame fingerprint image as unsentenced fingerprint image.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510767607.7A CN106682567A (en) | 2015-11-11 | 2015-11-11 | Acquisition processing method of fingerprint images and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510767607.7A CN106682567A (en) | 2015-11-11 | 2015-11-11 | Acquisition processing method of fingerprint images and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106682567A true CN106682567A (en) | 2017-05-17 |
Family
ID=58864964
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510767607.7A Pending CN106682567A (en) | 2015-11-11 | 2015-11-11 | Acquisition processing method of fingerprint images and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106682567A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107491727A (en) * | 2017-07-07 | 2017-12-19 | 广东欧珀移动通信有限公司 | Fingerprint identification method, device and terminal |
| CN107690655A (en) * | 2017-09-04 | 2018-02-13 | 深圳市汇顶科技股份有限公司 | Fingerprint register method, apparatus and electric terminal |
| CN110389127A (en) * | 2019-07-03 | 2019-10-29 | 浙江大学 | A kind of identification of cermet part and surface defects detection system and method |
| CN110674691A (en) * | 2019-08-22 | 2020-01-10 | 联想图像（天津）科技有限公司 | Fingerprint identification and verification method and device and printing equipment |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1604139A (en) * | 2004-10-28 | 2005-04-06 | 上海交通大学 | Method for constructing image fusion estimation system |
| CN101030246A (en) * | 2007-04-09 | 2007-09-05 | 黄东运 | Method for discriminating fingerprint |
| CN101303728A (en) * | 2008-07-01 | 2008-11-12 | 山东大学 | Method for identifying fingerprint facing image quality |
| CN101901336A (en) * | 2010-06-11 | 2010-12-01 | 哈尔滨工程大学 | Fingerprint and finger vein bimodal recognition decision level fusion method |
| US7936907B2 (en) * | 2006-04-26 | 2011-05-03 | Aware, Inc. | Fingerprint preview quality and segmentation |
| CN103065134A (en) * | 2013-01-22 | 2013-04-24 | 江苏超创信息软件发展股份有限公司 | Fingerprint identification device and method with prompt information |
-
2015
- 2015-11-11 CN CN201510767607.7A patent/CN106682567A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1604139A (en) * | 2004-10-28 | 2005-04-06 | 上海交通大学 | Method for constructing image fusion estimation system |
| US7936907B2 (en) * | 2006-04-26 | 2011-05-03 | Aware, Inc. | Fingerprint preview quality and segmentation |
| CN101030246A (en) * | 2007-04-09 | 2007-09-05 | 黄东运 | Method for discriminating fingerprint |
| CN101303728A (en) * | 2008-07-01 | 2008-11-12 | 山东大学 | Method for identifying fingerprint facing image quality |
| CN101901336A (en) * | 2010-06-11 | 2010-12-01 | 哈尔滨工程大学 | Fingerprint and finger vein bimodal recognition decision level fusion method |
| CN103065134A (en) * | 2013-01-22 | 2013-04-24 | 江苏超创信息软件发展股份有限公司 | Fingerprint identification device and method with prompt information |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107491727A (en) * | 2017-07-07 | 2017-12-19 | 广东欧珀移动通信有限公司 | Fingerprint identification method, device and terminal |
| CN107690655A (en) * | 2017-09-04 | 2018-02-13 | 深圳市汇顶科技股份有限公司 | Fingerprint register method, apparatus and electric terminal |
| CN110389127A (en) * | 2019-07-03 | 2019-10-29 | 浙江大学 | A kind of identification of cermet part and surface defects detection system and method |
| CN110389127B (en) * | 2019-07-03 | 2020-08-14 | 浙江大学 | System and method for identifying metal ceramic parts and detecting surface defects |
| CN110674691A (en) * | 2019-08-22 | 2020-01-10 | 联想图像（天津）科技有限公司 | Fingerprint identification and verification method and device and printing equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10268950B2 (en) | Face detection using machine learning | |
| CN106682567A (en) | Acquisition processing method of fingerprint images and device | |
| US20180107890A1 (en) | Performing object detection in an image | |
| EP3113072A1 (en) | Methods and apparatuses for updating user authentication data | |
| WO2019201204A1 (en) | Method and device for detecting nodule in image | |
| CN108805789A (en) | A kind of method, apparatus, equipment and readable medium removing watermark based on confrontation neural network | |
| US11158053B2 (en) | Image processing method, apparatus and device, and image display method | |
| CN108875516B (en) | Face recognition method, device, system, storage medium and electronic equipment | |
| CN108875469A (en) | In vivo detection and identity authentication method, device and computer storage medium | |
| CN106161962A (en) | A kind of image processing method and terminal | |
| JP6603477B2 (en) | Information processing apparatus and information processing method | |
| CN112036491A (en) | Method and device for determining training sample and method for training deep learning model | |
| CN110188640A (en) | Face identification method, device, server and computer-readable medium | |
| EP3819862A1 (en) | Determination method, determination program, and information processing device | |
| CN103578102B (en) | Object detection device and subject detection method | |
| CN103839032B (en) | A kind of recognition methods and electronic equipment | |
| CN110598652B (en) | Fundus data prediction method and device | |
| CN109871939B (en) | Image processing method and image processing device | |
| CN109598201B (en) | Action detection method and device, electronic equipment and readable storage medium | |
| CN110097061A (en) | A kind of image display method and apparatus | |
| CN115100161A (en) | Battery top cover defect detection method and device, electronic equipment and storage medium | |
| CN107729909B (en) | Application method and device of attribute classifier | |
| CN114821756A (en) | Blink data statistical method and device based on deep learning | |
| CN107590826A (en) | Control method, control system and the unmanned plane of unmanned plane automatic camera | |
| CN113435229A (en) | Face iris multi-mode recognition method and device, readable storage medium and equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170517 |
|
| RJ01 | Rejection of invention patent application after publication |