CN108268851A - Online fingerprint collecting method - Google Patents
Online fingerprint collecting method Download PDFInfo
- Publication number
- CN108268851A CN108268851A CN201810069330.4A CN201810069330A CN108268851A CN 108268851 A CN108268851 A CN 108268851A CN 201810069330 A CN201810069330 A CN 201810069330A CN 108268851 A CN108268851 A CN 108268851A
- Authority
- CN
- China
- Prior art keywords
- finger
- image
- hand
- point
- palm
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/12—Fingerprints or palmprints
- G06V40/13—Sensors therefor
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
- G06V10/267—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion by performing operations on regions, e.g. growing, shrinking or watersheds
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/30—Noise filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/12—Fingerprints or palmprints
- G06V40/1347—Preprocessing; Feature extraction
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Human Computer Interaction (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Processing (AREA)
- Collating Specific Patterns (AREA)
Abstract
In order to improve the identification degree of online fingerprint collecting, the present invention provides a kind of online fingerprint collecting methods, include the following steps：(1) the first gradation correction processing is carried out to collected first frame hand image with initial gray, obtains finger-image, the hand image includes the palm image and finger-image that correspond to left hand and the right hand respectively；(2) obtain representing the first intermediate image of the corresponding finger-print region of each finger using finger lines physiological characteristic；(3) the second gradation correction processing is carried out to collected second frame hand image with the second gray scale, obtains finger-image, the hand image includes the palm image and finger-image that correspond to left hand and the right hand respectively；(4) obtain representing the second intermediate image of the corresponding finger-print region of each finger using finger lines physiological characteristic；(5) noise reduction process is carried out to the first intermediate image and the second intermediate image, obtains fingerprint image.
Description
Technical field
The invention belongs to physical characteristics collecting fields, and in particular to a kind of online fingerprint collecting method.
Background technology
It is increasingly diversified with the function of integrated circuit, belong to spy's product or the device that can not be obtained at all in the past,
It all gradually popularizes now.Such as fingerprint scanner, it is exactly an example.It is past, few on traditional consumer product market
See or even listen the fingerprint recognition system all do not listened, also due to the appearance of integrated circuit finger scanner, in concern
It is increasingly popularized between the user of access control and identification identification；The application field of fingerprint recognition system no longer only limits
In government and Security Officer.These devices are for ensuring that the user for only obtaining mandate just can be in a computer system
Or database can be put into portable computer into line access moreover, its volume has also narrowed down to.
Under the increasingly mature background of web development, the networked instruments of fingerprint scanner are ready to appear.However, due to
Network transmission and distal end fingerprint scanner user instruct without professional person, and the picture quality of acquisition is bad, noise
It is excessive.
Invention content
In order to improve the identification degree of online fingerprint collecting, the present invention provides a kind of online fingerprint collecting method, including
Following steps：
(1) the first gradation correction processing is carried out to collected first frame hand image with initial gray, obtains finger figure
Picture, the hand image include the palm image and finger-image that correspond to left hand and the right hand respectively；
(2) obtain representing the first intermediate image of the corresponding finger-print region of each finger using finger lines physiological characteristic；
(3) the second gradation correction processing is carried out to collected second frame hand image with the second gray scale, obtains finger figure
Picture, the hand image include the palm image and finger-image that correspond to left hand and the right hand respectively；
(4) obtain representing the second intermediate image of the corresponding finger-print region of each finger using finger lines physiological characteristic；
(5) noise reduction process is carried out to the first intermediate image and the second intermediate image, obtains fingerprint image.
Further, the step (1) includes：
A. according to first frame image, average gray A gray scales=(the left palm+A right sides of A of left hand and right hand hand image are calculated
The palm)/2；
B. in hand image, on the basis of finger shape and length, the figure with finger shortest in hand image is determined
As the corresponding image of thumb, determining that the image of secondary short finger as the corresponding image of little finger of toe, determines the figure close to thumb
As the corresponding image of forefinger, determining that the image close to little finger of toe as nameless corresponding image, determines remaining finger-shaped
Image is as the corresponding image of middle finger；
C. determine that finger root crotch position is finger root bifurcation in hand image；
D. left hand hand image is handled as follows：By each finger root bifurcation carry out line, and by middle finger with
The line of the two crotches of the finger root bifurcation and the third finger with the finger root bifurcation of little finger of toe of the third finger prolongs
In long line and hand image metacarpus close to the intersection point of the profile of little finger of toe as first point, by middle finger and the finger root bifurcated of forefinger
Metacarpus leans in the extended line and hand image of the line of the two crotches of point and forefinger and the finger root bifurcation of thumb
The intersection point of the profile of nearly thumb is as second point；According to each finger root bifurcation of left hand hand image and first point and
Second point removes left-hand palm image in left hand hand image, obtains left-hand finger image；
E. right hand hand image is handled as follows：By each finger root bifurcation carry out line, and by middle finger with
The line of the two crotches of the finger root bifurcation and the third finger with the finger root bifurcation of little finger of toe of the third finger prolongs
Long line is used as with intersection point of the metacarpus in hand image close to the profile of little finger of toe thirdly, by middle finger and the finger root bifurcated of forefinger
Metacarpus leans in the extended line and hand image of the line of the two crotches of point and forefinger and the finger root bifurcation of thumb
The intersection point of the profile of nearly thumb is as the 4th point；According to each finger root bifurcation of right hand hand image and first point and
Second point removes right hand palm image in right hand hand image, obtains right finger image；
F. calculate respectively first point, second point, thirdly, centered on the 4th point, r be radius neighborhood territory pixel gray scale it is equal
Value is formed 1 × 4 matrix M with this 4 gray averages；
G. using the image at tip in left hand hand image as the corresponding image of each finger tip of left hand, by right hand metacarpus figure
The image at tip is calculated as the corresponding image of each finger tip of the right hand with finger tip in the corresponding image of each finger tip as in
Centered on position, r be radius neighborhood gray average, formed with this 10 gray averages 10 × 1 matrix N；
H. the characteristic value A ' i.e. of the matrix feature vector a that N × M is obtained are calculated；
I. using first point as origin, establish the plane right-angle coordinate of left-hand finger image, the coordinate of second point for da and
Db using the 4th point as origin, establishes the plane right-angle coordinate of right finger image, and coordinate thirdly is d ' a and d ' b；
J. intersection correction coefficient alpha=A ' × (1-A gray scales of each pixel in left-hand finger image and right finger image are calculated
× (1-x × e d ' a/da)/(1-y × edb/d ' b)), obtain the left hand after gray correction and right finger image, wherein x, y
It is horizontal stroke, ordinate value of each pixel in the coordinate system of left hand and the right hand respectively.
Further, described (2) step includes the following steps：
For some finger, along finger tip to finger and palm junction direction, hang down according to each finger extending direction
The fineness of straight lines searches a most thick lines, using this lines as line of demarcation, obtains the line of demarcation to corresponding hand
The region of finger tip, the first intermediate image as the corresponding finger.
Further, the step (3) includes：
A. the bias light gray scale for acquiring hand image is adjusted to A gray scale/2；
B. according to the second frame image, average gray A gray scales 2=(the left palm 2+A of A of left hand and right hand hand image are calculated
The right palm is 2)/2；
C. in hand image, on the basis of finger shape and length, the figure with finger shortest in hand image is determined
As the corresponding image of thumb, determining that the image of secondary short finger as the corresponding image of little finger of toe, determines the figure close to thumb
As the corresponding image of forefinger, determining that the image close to little finger of toe as nameless corresponding image, determines remaining finger-shaped
Image is as the corresponding image of middle finger；
D. determine that finger root crotch position is finger root bifurcation in hand image；
E. left hand hand image is handled as follows：By each finger root bifurcation carry out line, and by middle finger with
The line of the two crotches of the finger root bifurcation and the third finger with the finger root bifurcation of little finger of toe of the third finger prolongs
In long line and hand image metacarpus close to the intersection point of the profile of little finger of toe as first point, by middle finger and the finger root bifurcated of forefinger
Metacarpus leans in the extended line and hand image of the line of the two crotches of point and forefinger and the finger root bifurcation of thumb
The intersection point of the profile of nearly thumb is as second point；According to each finger root bifurcation of left hand hand image and first point and
Second point removes left-hand palm image in left hand hand image, obtains left-hand finger image；
F. right hand hand image is handled as follows：By each finger root bifurcation carry out line, and by middle finger with
The line of the two crotches of the finger root bifurcation and the third finger with the finger root bifurcation of little finger of toe of the third finger prolongs
Long line is used as with intersection point of the metacarpus in hand image close to the profile of little finger of toe thirdly, by middle finger and the finger root bifurcated of forefinger
Metacarpus leans in the extended line and hand image of the line of the two crotches of point and forefinger and the finger root bifurcation of thumb
The intersection point of the profile of nearly thumb is as the 4th point；According to each finger root bifurcation of right hand hand image and first point and
Second point removes right hand palm image in right hand hand image, obtains right finger image；
G. calculate respectively first point, second point, thirdly, centered on the 4th point, R be radius neighborhood territory pixel gray scale it is equal
Value is formed 1 × 4 matrix M with this 4 gray averages；
H. using the image at tip in left hand hand image as the corresponding image of each finger tip of left hand, by right hand metacarpus figure
The image at tip is calculated as the corresponding image of each finger tip of the right hand with finger tip in the corresponding image of each finger tip as in
Centered on position, R be radius neighborhood gray average, formed with this 10 gray averages 10 × 1 matrix N；
I. the characteristic value A " i.e. of the matrix feature vector b that N × M is obtained are calculated；
J. using second point as origin, establish the plane right-angle coordinate of left-hand finger image, first point of coordinate for fa and
Fb, thirdly for origin, to establish the plane right-angle coordinate of right finger image, the 4th point of coordinate is f ' a and f ' b；
K. intersection correction coefficient alpha=A " × (1-A gray scales of each pixel in left-hand finger image and right finger image are calculated
2 × (1-x × lg (f ' a/fa))/(1-y × lg (fb/f ' b))), the left hand after gray correction and right finger image are obtained,
Middle x, y are horizontal stroke, ordinate value of each pixel in the coordinate system of left hand and the right hand respectively.
Further, described (4) step includes the following steps：
For some finger, along finger tip to finger and palm junction direction, hang down according to each finger extending direction
The fineness of straight lines searches a most thin lines, using this lines as line of demarcation, obtains the line of demarcation to corresponding hand
The region of finger tip, the second intermediate image as the corresponding finger.
Further, the step (5) includes：
A. the boundary of left-hand palm area B 1 and right hand palm area B2 in calculating first frame, palm and finger is with reference to each hand
Finger root bifurcation line；
B. left-hand palm area B ' 1 and right hand palm area B ' 2 in the second frame are calculated, the boundary reference of palm and finger is each
The finger root bifurcation line of hand；
C. to the finger of left hand and the right hand, add up respectively each first intermediate image area and the second intermediate image
Area, and then obtain the area of the first intermediate image and the area and C2 of C1 and the second intermediate image；
D. calculating matrix a × b obtains matrix E；
E. the palm area factor of left hand and the right hand is calculated respectively：The p left hands palm=ln (r × (B1/ (2 × B ' 1))), p are right
Palm=ln (R × (B2/ (2 × B ' 2)))；
F. image noise filter is constructed, filtering factor β is：
β (x, y, g)=∏ _ (k=1) ^ ∞〖(1+x/y g)^(-1)e^(|(|c1|)|·||c2||\/(|(|E|)
| k)) " × | | a × p left hand palms+b × p right hands palm | | 3
G. according to the picture noise wave filter that filtering factor is β, to first intermediate image and the second intermediate image into
Row index filters, wherein filtering parameter i.e. filtering factor β.
Further, it is 0.08~0.3 that the r value ranges, which are 0.02~0.1, R,.
Further, the R is 3 times of r.
Further, the initial gray is RGB (255,255,255).
Technical scheme of the present invention has the following advantages：
Using background gray scale when actively changing online fingerprint collecting and creatively with the finger of left hand and the right hand, palm
Gray balance technology, since dither frame or network transmission signal-to-noise ratio are to the matter of fingerprint collecting image when reducing online acquisition
Amount influences.After tested, discrimination, which is compared, has more than 40% online acquisition technology raising.
Description of the drawings
Fig. 1 shows flow chart according to the method for the present invention.
Specific embodiment
As shown in Figure 1, online fingerprint collecting method, includes the following steps：
(1) the first gradation correction processing is carried out to collected first frame hand image with initial gray, obtains finger figure
Picture, the hand image include the palm image and finger-image that correspond to left hand and the right hand respectively；
(2) obtain representing the first intermediate image of the corresponding finger-print region of each finger using finger lines physiological characteristic；
(3) the second gradation correction processing is carried out to collected second frame hand image with the second gray scale, obtains finger figure
Picture, the hand image include the palm image and finger-image that correspond to left hand and the right hand respectively；
(4) obtain representing the second intermediate image of the corresponding finger-print region of each finger using finger lines physiological characteristic；
(5) noise reduction process is carried out to the first intermediate image and the second intermediate image, obtains fingerprint image.
Preferably, the step (1) includes：
A. according to first frame image, average gray A gray scales=(the left palm+A right sides of A of left hand and right hand hand image are calculated
The palm)/2；
B. in hand image, on the basis of finger shape and length, the figure with finger shortest in hand image is determined
As the corresponding image of thumb, determining that the image of secondary short finger as the corresponding image of little finger of toe, determines the figure close to thumb
As the corresponding image of forefinger, determining that the image close to little finger of toe as nameless corresponding image, determines remaining finger-shaped
Image is as the corresponding image of middle finger；
C. determine that finger root crotch position is finger root bifurcation in hand image；
D. left hand hand image is handled as follows：By each finger root bifurcation carry out line, and by middle finger with
The line of the two crotches of the finger root bifurcation and the third finger with the finger root bifurcation of little finger of toe of the third finger prolongs
In long line and hand image metacarpus close to the intersection point of the profile of little finger of toe as first point, by middle finger and the finger root bifurcated of forefinger
Metacarpus leans in the extended line and hand image of the line of the two crotches of point and forefinger and the finger root bifurcation of thumb
The intersection point of the profile of nearly thumb is as second point；According to each finger root bifurcation of left hand hand image and first point and
Second point removes left-hand palm image in left hand hand image, obtains left-hand finger image；
E. right hand hand image is handled as follows：By each finger root bifurcation carry out line, and by middle finger with
The line of the two crotches of the finger root bifurcation and the third finger with the finger root bifurcation of little finger of toe of the third finger prolongs
Long line is used as with intersection point of the metacarpus in hand image close to the profile of little finger of toe thirdly, by middle finger and the finger root bifurcated of forefinger
Metacarpus leans in the extended line and hand image of the line of the two crotches of point and forefinger and the finger root bifurcation of thumb
The intersection point of the profile of nearly thumb is as the 4th point；According to each finger root bifurcation of right hand hand image and first point and
Second point removes right hand palm image in right hand hand image, obtains right finger image；
F. calculate respectively first point, second point, thirdly, centered on the 4th point, r be radius neighborhood territory pixel gray scale it is equal
Value is formed 1 × 4 matrix M with this 4 gray averages；
G. using the image at tip in left hand hand image as the corresponding image of each finger tip of left hand, by right hand metacarpus figure
The image at tip is calculated as the corresponding image of each finger tip of the right hand with finger tip in the corresponding image of each finger tip as in
Centered on position, r be radius neighborhood gray average, formed with this 10 gray averages 10 × 1 matrix N；
H. the characteristic value A ' i.e. of the matrix feature vector a that N × M is obtained are calculated；
I. using first point as origin, establish the plane right-angle coordinate of left-hand finger image, the coordinate of second point for da and
Db using the 4th point as origin, establishes the plane right-angle coordinate of right finger image, and coordinate thirdly is d ' a and d ' b；
J. intersection correction coefficient alpha=A ' × (1-A gray scales of each pixel in left-hand finger image and right finger image are calculated
× (1-x × e d ' a/da)/(1-y × edb/d ' b)), obtain the left hand after gray correction and right finger image, wherein x, y
It is horizontal stroke, ordinate value of each pixel in the coordinate system of left hand and the right hand respectively.
Preferably, described (2) step includes the following steps：
For some finger, along finger tip to finger and palm junction direction, hang down according to each finger extending direction
The fineness of straight lines searches a most thick lines, using this lines as line of demarcation, obtains the line of demarcation to corresponding hand
The region of finger tip, the first intermediate image as the corresponding finger.
Preferably, the step (3) includes：
A. the bias light gray scale for acquiring hand image is adjusted to A gray scale/2；
B. according to the second frame image, average gray A gray scales 2=(the left palm 2+A of A of left hand and right hand hand image are calculated
The right palm is 2)/2；
C. in hand image, on the basis of finger shape and length, the figure with finger shortest in hand image is determined
As the corresponding image of thumb, determining that the image of secondary short finger as the corresponding image of little finger of toe, determines the figure close to thumb
As the corresponding image of forefinger, determining that the image close to little finger of toe as nameless corresponding image, determines remaining finger-shaped
Image is as the corresponding image of middle finger；
D. determine that finger root crotch position is finger root bifurcation in hand image；
E. left hand hand image is handled as follows：By each finger root bifurcation carry out line, and by middle finger with
The line of the two crotches of the finger root bifurcation and the third finger with the finger root bifurcation of little finger of toe of the third finger prolongs
In long line and hand image metacarpus close to the intersection point of the profile of little finger of toe as first point, by middle finger and the finger root bifurcated of forefinger
Metacarpus leans in the extended line and hand image of the line of the two crotches of point and forefinger and the finger root bifurcation of thumb
The intersection point of the profile of nearly thumb is as second point；According to each finger root bifurcation of left hand hand image and first point and
Second point removes left-hand palm image in left hand hand image, obtains left-hand finger image；
F. right hand hand image is handled as follows：By each finger root bifurcation carry out line, and by middle finger with
The line of the two crotches of the finger root bifurcation and the third finger with the finger root bifurcation of little finger of toe of the third finger prolongs
Long line is used as with intersection point of the metacarpus in hand image close to the profile of little finger of toe thirdly, by middle finger and the finger root bifurcated of forefinger
Metacarpus leans in the extended line and hand image of the line of the two crotches of point and forefinger and the finger root bifurcation of thumb
The intersection point of the profile of nearly thumb is as the 4th point；According to each finger root bifurcation of right hand hand image and first point and
Second point removes right hand palm image in right hand hand image, obtains right finger image；
G. calculate respectively first point, second point, thirdly, centered on the 4th point, R be radius neighborhood territory pixel gray scale it is equal
Value is formed 1 × 4 matrix M with this 4 gray averages；
H. using the image at tip in left hand hand image as the corresponding image of each finger tip of left hand, by right hand metacarpus figure
The image at tip is calculated as the corresponding image of each finger tip of the right hand with finger tip in the corresponding image of each finger tip as in
Centered on position, R be radius neighborhood gray average, formed with this 10 gray averages 10 × 1 matrix N；
I. the characteristic value A " i.e. of the matrix feature vector b that N × M is obtained are calculated；
J. using second point as origin, establish the plane right-angle coordinate of left-hand finger image, first point of coordinate for fa and
Fb, thirdly for origin, to establish the plane right-angle coordinate of right finger image, the 4th point of coordinate is f ' a and f ' b；
K. intersection correction coefficient alpha=A " × (1-A gray scales of each pixel in left-hand finger image and right finger image are calculated
2 × (1-x × lg (f ' a/fa))/(1-y × lg (fb/f ' b))), the left hand after gray correction and right finger image are obtained,
Middle x, y are horizontal stroke, ordinate value of each pixel in the coordinate system of left hand and the right hand respectively.
Preferably, described (4) step includes the following steps：
For some finger, along finger tip to finger and palm junction direction, hang down according to each finger extending direction
The fineness of straight lines searches a most thin lines, using this lines as line of demarcation, obtains the line of demarcation to corresponding hand
The region of finger tip, the second intermediate image as the corresponding finger.
Preferably, the step (5) includes：
A. the boundary of left-hand palm area B 1 and right hand palm area B2 in calculating first frame, palm and finger is with reference to each hand
Finger root bifurcation line；
B. left-hand palm area B ' 1 and right hand palm area B ' 2 in the second frame are calculated, the boundary reference of palm and finger is each
The finger root bifurcation line of hand；
C. to the finger of left hand and the right hand, add up respectively each first intermediate image area and the second intermediate image
Area, and then obtain the area of the first intermediate image and the area and C2 of C1 and the second intermediate image；
D. calculating matrix a × b obtains matrix E；
E. the palm area factor of left hand and the right hand is calculated respectively：The p left hands palm=ln (r × (B1/ (2 × B ' 1))), p are right
Palm=ln (R × (B2/ (2 × B ' 2)))；
F. image noise filter is constructed, filtering factor β is：
β (x, y, g)=∏ _ (k=1) ^ ∞〖(1+x/y g)^(-1)e^(|(|c1|)|·||c2||\/(|(|E|)
| k)) " × | | a × p left hand palms+b × p right hands palm | | 3
G. according to the picture noise wave filter that filtering factor is β, to first intermediate image and the second intermediate image into
Row index filters, wherein filtering parameter i.e. filtering factor β.
Preferably, it is 0.08~0.3 that the r value ranges, which are 0.02~0.1, R,.
Preferably, the R is 3 times of r.
Preferably, the initial gray is RGB (255,255,255).
The foregoing is merely illustrative of the preferred embodiments of the present invention, is not intended to limit the invention, all essences in the present invention
All any modification, equivalent and improvement made within refreshing and principle etc., should all be included in the protection scope of the present invention.
Claims (9)
1. a kind of online fingerprint collecting method, includes the following steps：
(1) the first gradation correction processing is carried out to collected first frame hand image with initial gray, obtains finger-image, institute
It states hand image and includes the palm image and finger-image that correspond to left hand and the right hand respectively；
(2) obtain representing the first intermediate image of the corresponding finger-print region of each finger using finger lines physiological characteristic；
(3) the second gradation correction processing is carried out to collected second frame hand image with the second gray scale, obtains finger-image, institute
It states hand image and includes the palm image and finger-image that correspond to left hand and the right hand respectively；
(4) obtain representing the second intermediate image of the corresponding finger-print region of each finger using finger lines physiological characteristic；
(5) noise reduction process is carried out to the first intermediate image and the second intermediate image, obtains fingerprint image.
2. online fingerprint collecting method as described in claim 1, the step (1) include：
A. according to first frame image, the average gray A of left hand and right hand hand image is calculatedGray scale=(AThe left palm+AThe right palm)/2；
B. it in hand image, on the basis of finger shape and length, determines to make with the image of finger shortest in hand image
For the corresponding image of thumb, determine that the image of secondary short finger as the corresponding image of little finger of toe, determines that the image close to thumb is made
For the corresponding image of forefinger, determine that the image close to little finger of toe as nameless corresponding image, determines remaining finger-shaped image
As the corresponding image of middle finger；
C. determine that finger root crotch position is finger root bifurcation in hand image；
D. left hand hand image is handled as follows：By each finger root bifurcation carry out line, and by middle finger with it is unknown
The extended line of the line of the two crotches of the finger root bifurcation and the third finger with the finger root bifurcation of little finger of toe of finger
With metacarpus in hand image close to the profile of little finger of toe intersection point as first point, by the finger root bifurcation of middle finger and forefinger with
And in the extended line and hand image of the line of forefinger and the finger root bifurcation of thumb the two crotches metacarpus close to thumb
The intersection point of the profile of finger is as second point；According to each finger root bifurcation of left hand hand image and first point and second
Point removes left-hand palm image in left hand hand image, obtains left-hand finger image；
E. right hand hand image is handled as follows：By each finger root bifurcation carry out line, and by middle finger with it is unknown
The extended line of the line of the two crotches of the finger root bifurcation and the third finger with the finger root bifurcation of little finger of toe of finger
With metacarpus in hand image close to the profile of little finger of toe intersection point as thirdly, by the finger root bifurcation of middle finger and forefinger with
And in the extended line and hand image of the line of forefinger and the finger root bifurcation of thumb the two crotches metacarpus close to thumb
The intersection point of the profile of finger is as the 4th point；According to each finger root bifurcation of right hand hand image and first point and second
Point removes right hand palm image in right hand hand image, obtains right finger image；
F. calculate respectively first point, second point, thirdly, centered on the 4th point, r be radius neighborhood territory pixel gray average,
1 × 4 matrix M is formed with this 4 gray averages；
It g., will be in right hand hand image using the image at tip in left hand hand image as the corresponding image of each finger tip of left hand
The image at tip is calculated as the corresponding image of each finger tip of the right hand with finger tip position in the corresponding image of each finger tip
Centered on, r be radius neighborhood gray average, formed with this 10 gray averages 10 × 1 matrix N；
H. the characteristic value A ' i.e. of the matrix feature vector a that N × M is obtained are calculated；
I. using first point as origin, the plane right-angle coordinate of left-hand finger image is established, the coordinate of second point is daAnd db, with
4th point is origin, establishes the plane right-angle coordinate of right finger image, and coordinate thirdly is d 'aAnd d 'b；
J. intersection correction coefficient alpha=A ' × (1-A of each pixel in left-hand finger image and right finger image is calculatedGray scale×(1-x
×ed’a/da)/(1-y×edb/d’b)), the left hand after gray correction and right finger image, wherein x are obtained, y is each pixel respectively
Horizontal stroke, ordinate value in the coordinate system of left hand and the right hand.
3. online fingerprint collecting method as described in claim 1, described (2) step include the following steps：
For some finger, along finger tip to finger and palm junction direction, according to vertical with each finger extending direction
The fineness of lines searches a most thick lines, using this lines as line of demarcation, obtains the line of demarcation to corresponding finger tip
Region, the first intermediate image as the corresponding finger.
4. online fingerprint collecting method as described in claim 1, the step (3) include：
A. the bias light gray scale for acquiring hand image is adjusted to AGray scale/2；
B. according to the second frame image, the average gray A of left hand and right hand hand image is calculatedGray scale 2=(AThe left palm 2+AThe right palm 2)/2；
C. it in hand image, on the basis of finger shape and length, determines to make with the image of finger shortest in hand image
For the corresponding image of thumb, determine that the image of secondary short finger as the corresponding image of little finger of toe, determines that the image close to thumb is made
For the corresponding image of forefinger, determine that the image close to little finger of toe as nameless corresponding image, determines remaining finger-shaped image
As the corresponding image of middle finger；
D. determine that finger root crotch position is finger root bifurcation in hand image；
E. left hand hand image is handled as follows：By each finger root bifurcation carry out line, and by middle finger with it is unknown
The extended line of the line of the two crotches of the finger root bifurcation and the third finger with the finger root bifurcation of little finger of toe of finger
With metacarpus in hand image close to the profile of little finger of toe intersection point as first point, by the finger root bifurcation of middle finger and forefinger with
And in the extended line and hand image of the line of forefinger and the finger root bifurcation of thumb the two crotches metacarpus close to thumb
The intersection point of the profile of finger is as second point；According to each finger root bifurcation of left hand hand image and first point and second
Point removes left-hand palm image in left hand hand image, obtains left-hand finger image；
F. right hand hand image is handled as follows：By each finger root bifurcation carry out line, and by middle finger with it is unknown
The extended line of the line of the two crotches of the finger root bifurcation and the third finger with the finger root bifurcation of little finger of toe of finger
With metacarpus in hand image close to the profile of little finger of toe intersection point as thirdly, by the finger root bifurcation of middle finger and forefinger with
And in the extended line and hand image of the line of forefinger and the finger root bifurcation of thumb the two crotches metacarpus close to thumb
The intersection point of the profile of finger is as the 4th point；According to each finger root bifurcation of right hand hand image and first point and second
Point removes right hand palm image in right hand hand image, obtains right finger image；
G. calculate respectively first point, second point, thirdly, centered on the 4th point, R be radius neighborhood territory pixel gray average,
1 × 4 matrix M is formed with this 4 gray averages；
It h., will be in right hand hand image using the image at tip in left hand hand image as the corresponding image of each finger tip of left hand
The image at tip is calculated as the corresponding image of each finger tip of the right hand with finger tip position in the corresponding image of each finger tip
Centered on, R be radius neighborhood gray average, formed with this 10 gray averages 10 × 1 matrix N；
I. the characteristic value A " i.e. of the matrix feature vector b that N × M is obtained are calculated；
J. using second point as origin, the plane right-angle coordinate of left-hand finger image is established, first point of coordinate is faAnd fb, with
It is thirdly origin, establishes the plane right-angle coordinate of right finger image, the 4th point of coordinate is f 'aAnd f 'b；
K. intersection correction coefficient alpha=A " × (1-A of each pixel in left-hand finger image and right finger image is calculatedGray scale 2×(1-x
× lg (f ' a/fa))/(1-y × lg (fb/f ' b))), the left hand after gray correction and right finger image, wherein x are obtained, y divides
It is not horizontal stroke, ordinate value of each pixel in the coordinate system of left hand and the right hand.
5. online fingerprint collecting method as described in claim 1, described (4) step include the following steps：
For some finger, along finger tip to finger and palm junction direction, according to vertical with each finger extending direction
The fineness of lines searches a most thin lines, using this lines as line of demarcation, obtains the line of demarcation to corresponding finger tip
Region, the second intermediate image as the corresponding finger.
6. online fingerprint collecting method as described in claim 1, the step (5) include：
A. the boundary of left-hand palm area B 1 and right hand palm area B2 in calculating first frame, palm and finger is with reference to the hand of each hand
Refer to root bifurcation line；
B. left-hand palm area B ' 1 and right hand palm area B ' 2 in the second frame are calculated, the boundary of palm and finger is with reference to each hand
Finger root bifurcation line；
C. to the finger of left hand and the right hand, the face of add up respectively each first intermediate image area and the second intermediate image
Product, and then obtain the area of the first intermediate image and the area and C2 of C1 and the second intermediate image；
D. calculating matrix a × b obtains matrix E；
E. the palm area factor of left hand and the right hand is calculated respectively：pLeft hand is slapped=ln (r × (B1/ (2 × B ' 1))), pThe right hand is slapped=ln (R
×(B2/(2×B’2)))；
F. image noise filter is constructed, filtering factor β is：
G. according to the picture noise wave filter that filtering factor is β, first intermediate image and the second intermediate image are referred to
Number filtering, wherein filtering parameter i.e. filtering factor β.
7. online fingerprint collecting method as described in claim 1, the r value ranges be 0.02~0.1, R be 0.08~
0.3。
8. online fingerprint collecting method as described in claim 1, the R is 3 times of r.
9. online fingerprint collecting method as described in claim 1, the initial gray is RGB (255,255,255).
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810069330.4A CN108268851B (en) | 2018-01-24 | 2018-01-24 | Online fingerprint acquisition method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810069330.4A CN108268851B (en) | 2018-01-24 | 2018-01-24 | Online fingerprint acquisition method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108268851A true CN108268851A (en) | 2018-07-10 |
| CN108268851B CN108268851B (en) | 2021-09-14 |
Family
ID=62776576
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810069330.4A Active CN108268851B (en) | 2018-01-24 | 2018-01-24 | Online fingerprint acquisition method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108268851B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102073858A (en) * | 2011-01-24 | 2011-05-25 | 合肥迈智机电科技有限责任公司 | Fingerprint and palmprint acquisition instrument and acquisition method thereof |
| CN102739856A (en) * | 2012-05-31 | 2012-10-17 | 西安电子科技大学 | Mobile phone unlocking system and method based on palm image information |
| CN104123537A (en) * | 2014-07-04 | 2014-10-29 | 西安理工大学 | Rapid authentication method based on handshape and palmprint recognition |
| CN104284011A (en) * | 2013-07-12 | 2015-01-14 | 联想(北京)有限公司 | Information processing method and electronic device |
-
2018
- 2018-01-24 CN CN201810069330.4A patent/CN108268851B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102073858A (en) * | 2011-01-24 | 2011-05-25 | 合肥迈智机电科技有限责任公司 | Fingerprint and palmprint acquisition instrument and acquisition method thereof |
| CN102739856A (en) * | 2012-05-31 | 2012-10-17 | 西安电子科技大学 | Mobile phone unlocking system and method based on palm image information |
| CN104284011A (en) * | 2013-07-12 | 2015-01-14 | 联想(北京)有限公司 | Information processing method and electronic device |
| CN104123537A (en) * | 2014-07-04 | 2014-10-29 | 西安理工大学 | Rapid authentication method based on handshape and palmprint recognition |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108268851B (en) | 2021-09-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2016023264A1 (en) | Fingerprint identification method and fingerprint identification device | |
| CN106469302A (en) | A kind of face skin quality detection method based on artificial neural network | |
| Frucci et al. | WIRE: Watershed based iris recognition | |
| Hong et al. | Robust palmprint recognition based on the fast variation Vese–Osher model | |
| CN101162503A (en) | Method for extracting and recognizing human ear characteristic by improved Hausdorff distance | |
| CN109426789A (en) | Hand and image detecting method and system, hand dividing method, storage medium and equipment | |
| CN110796101A (en) | Face recognition method and system of embedded platform | |
| CN113128376B (en) | Wrinkle identification method and device based on image processing and terminal equipment | |
| CN109829354B (en) | Face recognition method based on deep learning | |
| CN117689655B (en) | Metal button surface defect detection method based on computer vision | |
| CN111860196B (en) | Hand operation action scoring device, method and computer readable storage medium | |
| CN111126143A (en) | Deep learning-based exercise judgment guidance method and system | |
| EP4083937A1 (en) | System and method for hair analysis of user | |
| CN113011253A (en) | Face expression recognition method, device, equipment and storage medium based on ResNeXt network | |
| CN106096527A (en) | A kind of recognition methods of real-time high-precision online bank note face amount | |
| Liu et al. | Illumination compensation and feedback of illumination feature in face detection | |
| CN108268851A (en) | Online fingerprint collecting method | |
| CN105678795B (en) | A kind of field shoe watermark image method of inspection | |
| CN109509194B (en) | Front human body image segmentation method and device under complex background | |
| CN107967469A (en) | With reference to the fingerprint method of sampling of vena metacarpea | |
| CN108073916A (en) | Palm print information collecting device | |
| CN108154141A (en) | Utilize the biological parameter identification system for referring to vein | |
| CN108256528A (en) | Fingers and palms line safety-protection system | |
| CN108280428A (en) | Compound fingers and palms line verifies system | |
| KR101058719B1 (en) | Method of input control based on hand posture recognization |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20210818 Address after: 510663 Room 201, 3rd & 4th floor, 2nd floor, No. 15, Ruan Road, Tianhe District, Guangzhou City, Guangdong Province Applicant after: GUANGDONG TECSUN TECHNOLOGY Co.,Ltd. Address before: 610000 No. 10, floor 20, building 3, No. 88, Jitai fifth road, high tech Zone, Chengdu, Sichuan Applicant before: SICHUAN ZHENG'ANTONG TECHNOLOGY Co.,Ltd. |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |