CN109190554A - It is a kind of based on fingerprint and to refer to the 3D identifying system and method for vein - Google Patents
It is a kind of based on fingerprint and to refer to the 3D identifying system and method for vein Download PDFInfo
- Publication number
- CN109190554A CN109190554A CN201811004097.8A CN201811004097A CN109190554A CN 109190554 A CN109190554 A CN 109190554A CN 201811004097 A CN201811004097 A CN 201811004097A CN 109190554 A CN109190554 A CN 109190554A
- Authority
- CN
- China
- Prior art keywords
- fingerprint
- image
- finger
- light source
- vein
- 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
- G06V40/1312—Sensors therefor direct reading, e.g. contactless acquisition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/10—Image acquisition
- G06V10/12—Details of acquisition arrangements; Constructional details thereof
- G06V10/14—Optical characteristics of the device performing the acquisition or on the illumination arrangements
- G06V10/143—Sensing or illuminating at different wavelengths
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/64—Three-dimensional objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
-
- 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
- G06V40/1359—Extracting features related to ridge properties; Determining the fingerprint type, e.g. whorl or loop
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/12—Fingerprints or palmprints
- G06V40/1365—Matching; Classification
-
- 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
- G06V40/14—Vascular patterns
Abstract
The present invention, which provides, a kind of based on fingerprint and refers to the 3D identifying system and method for vein, the 3D identifying system includes light source and imaging device, the light source includes first light source and near-infrared light source, the first light source is set to the two sides of finger plate placement, and the near-infrared light source is set on the finger plate placement；The imaging device includes at least two cameras, and there are center angles between every two camera, and the elongated central line of all cameras intersects on the finger plate placement.Fingerprint image and finger vein image of the present invention in the different directions of acquisition of same time user, the complete finger-image from finger left end to finger right end can be taken, utilize the fingerprint image reconfiguration 3D fingerprint image of different directions, and refer to vein image using the finger vein image of different directions building 3D, and then user identity can be matched and identified by its fingerprint characteristic and finger vein pattern, In vivo detection ability is increased, anti-counterfeit capability is improved.
Description
Technical field
The present invention relates to a kind of method for identifying ID more particularly to a kind of 3D based on fingerprint and finger vein to identify system
System, and be related to being applied to the 3D recognition methods based on fingerprint and the 3D identifying system for referring to vein.
Background technique
With the development of science and technology, the method for user identity identification is also more and more, application field is also increasingly wider；Now
Universal method for identifying ID is realized based on biometrics identification technology or fingerprint identification technology etc., but this
Prior art biological characteristic collected is relatively simple, and the prior art is the matching and certification of 2-D data, Bu Nengman mostly
Sufficient actual demand, there are some potential safety problems, anti-counterfeiting performance is also therefore limited.
Summary of the invention
The technical problem to be solved by the present invention is to need to provide one kind can be referred to by three-dimensional fingerprint recognition and three-dimensional it is quiet
Arteries and veins identification is common to realize user identity authentication, and then can be realized In vivo detection and anti-counterfeiting performance is high, security risk it is small based on
Fingerprint and the 3D identifying system for referring to vein, and further provide for being applied to described based on fingerprint and the 3D identifying system for referring to vein
3D recognition methods.
In this regard, the present invention provides a kind of 3D identifying system based on fingerprint and finger vein, including light source and imaging device, institute
Stating light source includes first light source and near-infrared light source, and the first light source is set to the two sides of finger plate placement, described close red
Outer light source is set on the finger plate placement；The imaging device include at least two cameras, every two camera it
Between there are center angles, and the elongated central line of all cameras intersects on the finger plate placement；At work, pass through
At least two camera shoots the fingerprint image when first light source is opened respectively, and passes through at least two camera
The finger vein image when near-infrared light source is opened is shot respectively, and then by the fingerprint image and refers to that vein image constructs 3D
Fingerprint image and 3D refer to vein image, to realize user identity identification.
A further improvement of the present invention is that the first light source includes left side light source and right side source, the left side light
Source and right side source are symmetrically arranged in the left and right sides of the finger plate placement, the left side light source and right side source point
It is not pre-determined distance with the distance between the finger plate placement.
A further improvement of the present invention is that the imaging device includes three cameras, between every two camera
Center angle is identical.
A further improvement of the present invention is that the center angle between the every two camera is 30 °.
The present invention also provides a kind of based on fingerprint and refers to the 3D recognition methods of vein, is applied to be based on fingerprint as described above
With refer to vein 3D identifying system, and the following steps are included:
Step S1 starts camera, acquisition fingerprint image and finger vein image；
Step S2 respectively pre-processes fingerprint image and finger vein image, the feature that takes the fingerprint and finger vein pattern；
Step S3 establishes 3D point cloud coordinate, constructs 3D fingerprint image and 3D refers to vein image；
Step S4, the fingerprint and 3D extracted in 3D fingerprint image refer to the finger veinprint in vein image；
Step S5 realizes In vivo detection, and carries out fingerprint to the data of In vivo detection and refer to the characteristic matching of veinprint,
With user identity identification.
A further improvement of the present invention is that including following sub-step in the step S1:
Step S101 starts camera；
Step S102 opens the first light source, acquires the fingerprint image simultaneously by least two cameras；
Step S103, automatically switches to open the near-infrared light source, acquires the finger simultaneously by least two cameras
Vein image；
Or, step S101, starts camera；
Step S102 ' opens the near-infrared light source, acquires the finger vein figure simultaneously by least two cameras
Picture；
Step S103 ', automatically switches to open the first light source, acquires the fingerprint simultaneously by least two cameras
Image.
A further improvement of the present invention is that the step S2 includes following sub-step:
Step S201, the fingerprint image acquired simultaneously at least two cameras carry out including binaryzation and Gauss respectively
The pretreatment of filtering；
Step S202 carries out crestal line feature, lines endpoint and lines bifurcation to each fingerprint image after pretreatment
Extraction, obtain fingerprint characteristic；
Step S203 carries out the finger vein image that at least two cameras acquire simultaneously to include image rectification, inclination
Any one or a few pretreatment in angle calculation, image background removal, edge processing and image enhancement；
Step S204 refer to each finger vein image after pretreatment the topological structure and ridge orientation of vein
It extracts, obtains referring to vein pattern.
A further improvement of the present invention is that in the step S3, fingerprint image captured by the camera to different directions
The point of the same position of picture, using preset finger cylinder model as the external form of three-dimensionalreconstruction, by the hand of each fingerprint image
Refer to that upper two-dimensional coordinate is calculated and projected in three-dimensional point coordinate corresponding to finger cylinder model, and then constructs 3D fingerprint
Image.
A further improvement of the present invention is that in the step S3, finger vein captured by the camera to different directions
The point of the same position of image projects in three-dimensional space as two-dimensional points coordinate, by the two-dimensional points coordinate according to camera parameters
It constructs 3D and refers to vein image.
A further improvement of the present invention is that carrying out fingerprint in the step S5 to the data of In vivo detection and referring to vein
The characteristic matching of lines is determined as that living body is examined when the Hamming distance of fingerprint characteristic and finger vein pattern is respectively less than preset threshold
The user identity authentication success of survey.
Compared with prior art, the beneficial effects of the present invention are: the same time acquisition user different directions finger
Print image and finger vein image, can take the complete finger-image from finger left end to finger right end, utilize difference
The fingerprint image reconfiguration 3D fingerprint image in direction, then on the basis of this, can also be obtained under near-infrared light source and clearly refer to vein
Image refers to vein image using the finger vein image building 3D of different directions, and then can be referred to by 3D fingerprint image and 3D quiet
Fingerprint characteristic corresponding to arteries and veins image matches and identifies user identity with vein pattern is referred to, increases In vivo detection ability, mentions
Anti-counterfeit capability is risen.
Detailed description of the invention
Fig. 1 is the system structure diagram of an embodiment of the present invention；
Fig. 2 is the workflow schematic diagram of an embodiment of the present invention.
Specific embodiment
With reference to the accompanying drawing, preferably embodiment of the invention is described in further detail.
As shown in Figure 1, this example provides a kind of 3D identifying system based on fingerprint and finger vein, including light source and imaging dress
It sets, the light source includes first light source and near-infrared light source 2, and the first light source is set to the two sides of finger plate placement 4, institute
Near-infrared light source 2 is stated to be set on the finger plate placement 4；The imaging device includes at least two cameras 5, every two
There are center angles between camera 5, and the elongated central line of all cameras 5 intersects on the finger plate placement 4；?
When work, the fingerprint image when first light source is opened is shot by least two camera 5 respectively, and described in extremely
Few two cameras 5 shoot the finger vein image when near-infrared light source 2 is opened respectively, and then by the fingerprint image and refer to
Vein image building 3D fingerprint image and 3D refer to vein image, to realize user identity identification.
Preferably, the 3D identifying system based on fingerprint and finger vein described in this example is directly arranged at the shell 6 of smart machine
On, it further include light source converter, for controlling the automatic conversion between first light source and near-infrared light source 2；More preferably, such as
Shown in Fig. 1, this example further includes USB 3.0Hub 8 and energy supply control module 9, is respectively used to realize grafting and the power supply of USB interface
Control.
As shown in Figure 1, first light source described in this example includes left side light source 3 and right side source 1, the left side light source 3 and the right side
Side light source 1 is symmetrically arranged in the left and right sides of the finger plate placement 4, and the left side light source 3 and right side source 1 are distinguished
The distance between described finger plate placement 4 is pre-determined distance.The pre-determined distance is preferably 2cm.The near-infrared light source 2
It is preferred that the LED light bar of the near infrared light using 840nm, the finger that the LED light bar of the near infrared light is installed at placement finger is put
It sets above panel 4, is close to finger back, can prevent near infrared light from leaking hunting.
Left side light source 3 and right side source 1 described in this example are mounted on the two sides of finger plate placement 4, and light can be impinged upon uniformly
On finger, three cameras 5 can shoot clearly and covering surface without departing from half fingerprint image；Near-infrared light source 2
It is mounted on above finger plate placement 4, is close to finger back, prevents light from finger two sides light leakage, such near infrared light can be worn
Finger is crossed, finger vein is transmitted.
As shown in Figure 1, imaging device described in this example preferably includes three cameras 5, the center between every two camera 5
Angle is identical, and the center angle between the every two camera 5 is preferably 30 °.This example shoots finger from three directions, can
The right end of finger is covered from the left end of finger, the center angle of every two camera 2 is 30 °, and intermediate camera 5 is clapped
What is taken the photograph is the direct picture of finger, and then three-dimensional is reconstructed in the fingerprint image in three directions that can be shot according to the same time
Finger-image similarly can also refer to vein image according to the finger vein image reconstruct three-dimensional in three directions.
3D identifying system described in this example is opened, user's registration acquires the finger-image of user, can be, be first turned on first
Light source, first light source are ordinary light source, and three cameras shoot fingerprint image, then automatically switch near-infrared light source 2, shooting refers to
Vein image, the speed of toggle lights quickly, can guarantee that six width images of acquisition are just that the same time is collected in this way, save
In the database.
As shown in Fig. 2, this example also provides a kind of 3D recognition methods based on fingerprint and finger vein, it is applied to as described above
3D identifying system based on fingerprint and finger vein, and the following steps are included:
Step S1 starts camera 5, acquisition fingerprint image and finger vein image；
Step S2 respectively pre-processes fingerprint image and finger vein image, the feature that takes the fingerprint and finger vein pattern；
Step S3 establishes 3D point cloud coordinate, constructs 3D fingerprint image and 3D refers to vein image；
Step S4, the fingerprint and 3D extracted in 3D fingerprint image refer to the finger veinprint in vein image；
Step S5 realizes In vivo detection, and carries out fingerprint to the data of In vivo detection and refer to the characteristic matching of veinprint,
With user identity identification.
As shown in Fig. 2, user needs first to register when using for the first time.It is preferably included in step S1 described in this example following
Sub-step:
Step S101 starts camera 5；
Step S102 opens the first light source, acquires the fingerprint image simultaneously by least two cameras 5；
Step S103 automatically switches to open the near-infrared light source 2, by described at least two acquisitions simultaneously of camera 5
Refer to vein image；
Or, step S101, starts camera 5；
Step S102 ' opens the near-infrared light source 2, acquires the finger vein figure simultaneously by least two cameras 5
Picture；
Step S103 ' automatically switches to open the first light source, acquires the finger simultaneously by least two cameras 5
Print image.
The quantity of camera 5 described in this example is preferably 3, and then refers to the component of vein image for 3D fingerprint image and 3D
It is the most advantageous, and will not be excessively complicated.In practical applications, fingerprint image can be first acquired, can also first acquire and refer to vein figure
Picture；Preferably, this example preferential collection fingerprint image, then switches again and opens near-infrared light source 2, and shooting refers to vein image, such as Fig. 2
It is shown.
Step S2 described in this example includes following sub-step:
Step S201, the fingerprint image at least two acquisitions simultaneously of camera 5 includes binaryzation and gaussian filtering
Pretreatment；For example, carrying out picture smooth treatment, image binaryzation and image thinning respectively to the fingerprint image of acquisition simultaneously, scheme
As smoothing processing eliminates noise using time-domain filtering method, using Gabor filtering for ridge part, paddy part and edge (overall situation)
Characteristic is enhanced；Image binaryzation utilizes Otsu method (method between maximum kind), presets a threshold value, divides the image into two
After point, by iterative calculation, threshold value when class variance between two parts image to reach to maximum is as global threshold, before separate picture
Scape and background；Image thinning is to obtain clearly single pixel wide skeleton structure, repeats screening using iterative algorithm and meets condition
Pixel finally obtains single pixel wide skeleton.
Step S202 carries out crestal line feature, lines endpoint and lines bifurcation to each fingerprint image after pretreatment
Extraction, obtain fingerprint characteristic；
Step S203 carries out including image rectification, inclination to the finger vein image of at least two acquisitions simultaneously of camera 5
Any one or a few pretreatment in angle calculation, image background removal, edge processing and image enhancement；
Step S204 refer to each finger vein image after pretreatment the topological structure and ridge orientation of vein
It extracts, obtains referring to vein pattern.
Step S3 described in this example can convert pixel according to world coordinate system and sit according to the inside and outside parameter of the camera of calibration
The conversion formula of mark system coordinate:
Its three-dimensional coordinate is solved to the pixel of fingerprint image, and then establishes three-dimensional point cloud coordinate, while similar hand is added
The cylinder model of finger-type shape is modified and demarcates, i.e., preferably can be used as three using with the approximate finger cylinder model of finger size
The external form for tieing up reconstruct projects two-dimensional coordinate calculating on finger in the corresponding three-dimensional point coordinate of finger cylinder model.
Wherein, the inside and outside parameter of the camera of calibration is also referred to as camera calibration: world coordinate system (xw,yw,zw) it is a three-dimensional
Rectangular coordinate system describes the spatial position of object on the basis of it；Camera coordinates system (xc,yc,zc) it is also that a three-dimensional right angle is sat
Mark system, origin is located at camera lens optical center, and x, y-axis are parallel with the both sides practised physiognomy respectively, z-axis for camera lens optical axis with as plane it is vertical；
World coordinate system is converted to camera coordinates system and passes through Formula of Coordinate System TransformationIt realizes, R is the rotation of 3*3
Matrix, t are the translation vector of 3*1；Pixel coordinate system uov is a two-dimensional Cartesian coordinate system, is reflected in camera CMOS chip
The arranging situation of pixel, origin o are located at the upper left corner of image, and u axis, v axis are parallel respectively at the both sides of image planes；Image coordinate system
XOY, origin are camera optical axis and the intersection point practised physiognomy, i.e. the central point of image, X-axis, Y-axis is parallel with u axis, v axis respectively；Image is sat
Mark system is converted to pixel coordinate systemPin-hole imaging principle, perspective projectionS is scale factor (adjustable and default), and f is effective focal length, and dX and dY are respectively picture
Physical size of the element in X-axis and Y direction, u0And v0The respectively image origin coordinate of the u axis of pixel coordinate system and v axis,It is homogeneous coordinates of the spatial point P in camera coordinates system oxyz,It is spatial point p homogeneous in image coordinate system OXY
Coordinate；World coordinate system is converted to the Formula of Coordinate System Transformation of pixel coordinate system are as follows:
The referred to as scale factor of u, v axis, M1The referred to as inner parameter matrix of camera, M2The referred to as external parameter square of camera
Battle array, XwFor the homogeneous coordinates of world coordinate system.The camera of this example is also referred to as camera.
This example preferably extracts its crestal line feature, SIFT feature and minutiae feature to the fingerprint image of three width different directions,
Wherein, the extraction process of the crestal line feature include eliminate noise, be partitioned into fingerprint area-of-interest, by Gabor filtering
Enhancing, binaryzation and the smothing filtering of device progress streakline；The extraction process of the SIFT feature (Scale invariant features transform)
Are as follows: building scale space, detection extreme point obtain scale invariability, and characteristic point filters and be accurately positioned, and are characterized a little minute
With direction value, takes the field of 16*16 as sampling window using centered on characteristic point, the relative direction of sampled point and characteristic point is led to
It is included into after crossing Gauss weighting comprising 8 direction histograms, generates Feature Descriptor；The extraction of the minutiae feature includes to line
The extraction of terminal point and bifurcation, lines endpoint and bifurcation are most important fingerprint details.
This example is by the determination of the grain distribution of fingerprint ridge line and valley line and extracting ridges feature, and determination refers in crestal line feature
The line field of direction determines the core of fingerprint, the shape and tendency of peripheral envelope and crestal line；Each feature in SIFT feature
Descriptor of the Main way as rotational invariance of point, determines 4 attributes of SIFT feature: space coordinate, scale, direction and
Feature point description symbol, and then obtain SIFT feature；According to the fingerprint characteristic of extraction, i.e., to the same of the image of multiple groups different directions
The point of position converts the conversion formula of pixel coordinate system coordinate according to world coordinate system:
Three-dimensional coordinate is solved to the pixel of fingerprint image, and then establishes three-dimensional coordinate, is reconstructed according to finger cylinder model
Three-dimensional fingerprint out.
That is, in step S3 described in this example, the same position of fingerprint image captured by the camera 5 to different directions
The point set will be two-dimensional on the finger of each fingerprint image using preset finger cylinder model as the external form of three-dimensionalreconstruction
Point coordinate is calculated and is projected in three-dimensional point coordinate corresponding to finger cylinder model, and then constructs 3D fingerprint image.
This example refers to that vein image pre-processes to three width, preprocessing process include: image correction, calculate finger incline
Rake angle, correction original image, image background remove, refer to vein area-of-interest, normalizing using Morphological scale-space edge, extraction
Change any one or a few in processing and Gabor image enhancement；Wherein, the process for referring to vein area-of-interest is extracted are as follows: first
First finger vein image carries out mean filter, removes noise, then carries out outer edge detection, the edge thinning detected is arrived
Single pixel point takes the minimum value of the difference of the pixel on same level direction as the width of rectangular area, and interception refers to vein image
Area-of-interest (can carry out customized be set or adjusted according to user demand).The process of normalized are as follows: double by gray scale
Linear interpolation method carries out size normalized to image, according to the gray value of four adjoint points around coordinate points come interpolation calculation
The value of the point out；Then to the processing of its gray scale normalization, the gray value of image pixel is transformed into [0-255] range.Gabor
The process of image enhancement are as follows: image enhancement processing is carried out using the local histogram equalization algorithm of contrast-limited, it is quiet according to referring to
Any point in arteries and veins image chooses the certain rectangular window of size, calculates local histogram equalization processing, mobile rectangular window
Mouthful, repeat complete image；The frequency spectrum of image is improved using Gabor filtering in frequency domain.Then finger vein image is carried out
Calibration, establishes three-dimensional point cloud coordinate, that is, to the two-dimensional points of the same position of the finger vein image of the camera shooting of different directions
Coordinate calculates the coordinate of projection in three dimensions by camera parameters, using Formula of Coordinate System Transformation to the picture of fingerprint image
Vegetarian refreshments solves three-dimensional coordinate, and then calculates three-dimensional point cloud coordinate.
That is, finger vein image is same captured by the camera 5 to different directions in step S3 described in this example
The point of position, which is projected as two-dimensional points coordinate, by the two-dimensional points coordinate according to camera parameters, to be constructed 3D and refers in three-dimensional space
Vein image.
Preferably, this example is described thin to the finger vein image texture feature extraction and minutiae feature of three width different directions
Node diagnostic includes lines endpoint and bifurcation, determines the topological structure and ridge orientation for referring to vein, establishes three-dimensional coordinate reconstruct
3D refers to vein out.
As shown in Fig. 2, carrying out fingerprint in step S5 described in this example to the data of In vivo detection and referring to the feature of veinprint
Matching is determined as user's body of In vivo detection when the Hamming distance of fingerprint characteristic and finger vein pattern is respectively less than preset threshold
Part authenticates successfully, is otherwise determined as the user identity authentication failure of In vivo detection.
In conclusion this example the different directions of acquisition of same time user fingerprint image and refer to vein image, can be with
The complete finger-image from finger left end to finger right end is taken, the fingerprint image reconfiguration 3D fingerprint of different directions is utilized
Image, then on the basis of this, can also be obtained under near-infrared light source 2 and clearly refer to vein image, it is quiet using the finger of different directions
Arteries and veins picture construction 3D refers to vein image, so can be referred to by 3D fingerprint image and 3D fingerprint characteristic corresponding to vein image and
Refer to vein pattern to match and identify user identity, increases In vivo detection ability, improve anti-counterfeit capability.
This example refers to that vein realizes the 3D identification to user identity using 3D fingerprint and 3D, can not be by finger broken skin, spot
And the epidermises environment such as dry and wet influences, and can also accomplish the function of preventing the false fingerprint such as fingerprint sleeve and fingerprint film, enhance fingerprint recognition
Safety.
The above content is a further detailed description of the present invention in conjunction with specific preferred embodiments, and it cannot be said that
Specific implementation of the invention is only limited to these instructions.For those of ordinary skill in the art to which the present invention belongs, exist
Under the premise of not departing from present inventive concept, a number of simple deductions or replacements can also be made, all shall be regarded as belonging to of the invention
Protection scope.
Claims (10)
1. a kind of 3D identifying system based on fingerprint and finger vein, which is characterized in that including light source and imaging device, the light source
Including first light source and near-infrared light source, the first light source is set to the two sides of finger plate placement, the near-infrared light source
It is set on the finger plate placement；The imaging device includes at least two cameras, is existed between every two camera
Center angle, and the elongated central line of all cameras intersects on the finger plate placement；At work, by it is described extremely
Few two cameras shoot the fingerprint image when first light source is opened respectively, and are clapped respectively by least two camera
The finger vein image when near-infrared light source is opened is taken the photograph, and then by the fingerprint image and refers to that vein image constructs 3D fingerprint image
Picture and 3D refer to vein image, to realize user identity identification.
2. the 3D identifying system according to claim 1 based on fingerprint and finger vein, which is characterized in that the first light source
Including left side light source and right side source, the left side light source and right side source are symmetrically arranged in the finger plate placement
The left and right sides, the left side light source and right side source are respectively pre-determined distance with the distance between the finger plate placement.
3. the 3D identifying system according to claim 1 or 2 based on fingerprint and finger vein, which is characterized in that the imaging
Device includes three cameras, and the center angle between every two camera is identical.
4. the 3D identifying system according to claim 3 based on fingerprint and finger vein, which is characterized in that the every two is taken the photograph
As the center angle between head is 30 °.
5. a kind of 3D recognition methods based on fingerprint and finger vein, which is characterized in that be applied to as Claims 1-4 is any one
The 3D identifying system based on fingerprint and finger vein described in, and the following steps are included:
Step S1 starts camera, acquisition fingerprint image and finger vein image；
Step S2 respectively pre-processes fingerprint image and finger vein image, the feature that takes the fingerprint and finger vein pattern；
Step S3 establishes 3D point cloud coordinate, constructs 3D fingerprint image and 3D refers to vein image；
Step S4, the fingerprint and 3D extracted in 3D fingerprint image refer to the finger veinprint in vein image；
Step S5, realize In vivo detection, and to the data of In vivo detection carry out fingerprint and refer to veinprint characteristic matching, with
Family identification.
6. the 3D recognition methods according to claim 5 based on fingerprint and finger vein, which is characterized in that in the step S1
Including following sub-step:
Step S101 starts camera；
Step S102 opens the first light source, acquires the fingerprint image simultaneously by least two cameras；
Step S103, automatically switches to open the near-infrared light source, acquires the finger vein simultaneously by least two cameras
Image；
Or, step S101, starts camera；
Step S102 ' opens the near-infrared light source, acquires the finger vein image simultaneously by least two cameras；
Step S103 ', automatically switches to open the first light source, acquires the fingerprint image simultaneously by least two cameras
Picture.
7. the 3D recognition methods according to claim 5 based on fingerprint and finger vein, which is characterized in that the step S2 packet
Include following sub-step:
Step S201, the fingerprint image acquired simultaneously at least two cameras carry out including binaryzation and gaussian filtering respectively
Pretreatment；
Step S202 carries out mentioning for crestal line feature, lines endpoint and lines bifurcation to each fingerprint image after pretreatment
It takes, obtains fingerprint characteristic；
Step S203, the finger vein image acquired simultaneously at least two cameras carry out including image rectification, tilt angle
It calculates, any one or a few pretreatment in image background removal, edge processing and image enhancement；
Step S204 carries out each finger vein image after pretreatment to refer to the topological structure of vein and proposing for ridge orientation
It takes, obtains referring to vein pattern.
8. the 3D recognition methods according to claim 7 based on fingerprint and finger vein, which is characterized in that the step S3
In, the point of the same position of fingerprint image captured by the camera to different directions, using preset finger cylinder model as
Two-dimensional coordinate on the finger of each fingerprint image is calculated and projects finger cylinder model institute by the external form of three-dimensionalreconstruction
In corresponding three-dimensional point coordinate, and then construct 3D fingerprint image.
9. the 3D recognition methods according to claim 7 based on fingerprint and finger vein, which is characterized in that the step S3
In, refer to the point of the same position of vein image captured by the camera to different directions as two-dimensional points coordinate, by the two dimension
Point coordinate is projected according to camera parameters to be constructed 3D and refers to vein image in three-dimensional space.
10. the 3D recognition methods according to claim 5 based on fingerprint and finger vein, which is characterized in that the step S5
In, fingerprint is carried out to the data of In vivo detection and refers to the characteristic matching of veinprint, when the Chinese of fingerprint characteristic and finger vein pattern
When prescribed distance is respectively less than preset threshold, it is determined as the user identity authentication success of In vivo detection.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811004097.8A CN109190554A (en) | 2018-08-30 | 2018-08-30 | It is a kind of based on fingerprint and to refer to the 3D identifying system and method for vein |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811004097.8A CN109190554A (en) | 2018-08-30 | 2018-08-30 | It is a kind of based on fingerprint and to refer to the 3D identifying system and method for vein |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109190554A true CN109190554A (en) | 2019-01-11 |
Family
ID=64916900
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811004097.8A Pending CN109190554A (en) | 2018-08-30 | 2018-08-30 | It is a kind of based on fingerprint and to refer to the 3D identifying system and method for vein |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109190554A (en) |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109700435A (en) * | 2019-01-28 | 2019-05-03 | 上海得舟信息科技有限公司 | A kind of projection intravenous angiography device and its image processing method |
| CN110008931A (en) * | 2019-04-16 | 2019-07-12 | 上海应用技术大学 | In conjunction with the mixing recognition methods of fingerprint and finger venous information |
| CN110008852A (en) * | 2019-03-15 | 2019-07-12 | 深圳北斗通信科技有限公司 | Fingerprint collecting method, system and storage medium |
| CN110443217A (en) * | 2019-08-13 | 2019-11-12 | 深圳大学 | One kind being based on multispectral fingerprint method for anti-counterfeit and system |
| CN110945524A (en) * | 2019-10-21 | 2020-03-31 | 深圳市汇顶科技股份有限公司 | Fingerprint identification method, fingerprint identification device and electronic equipment |
| CN111046807A (en) * | 2019-12-16 | 2020-04-21 | 上海芯灵科技有限公司 | Finger vein knuckle line coincidence recognition system |
| WO2020181465A1 (en) | 2019-03-11 | 2020-09-17 | Moqi Technology (beijing) Co., Ltd. | Device and method for contactless fingerprint acquisition |
| CN112084840A (en) * | 2020-07-24 | 2020-12-15 | 浙江工业大学 | Finger vein identification method based on three-dimensional NMI |
| CN112101332A (en) * | 2020-11-23 | 2020-12-18 | 北京圣点云信息技术有限公司 | Feature extraction and comparison method and device based on 3D finger veins |
| CN113076921A (en) * | 2021-04-21 | 2021-07-06 | 华南理工大学 | Multispectral texture synchronous mapping method of three-dimensional finger biological feature model |
| CN113378604A (en) * | 2020-03-10 | 2021-09-10 | 浙江宇视科技有限公司 | Finger vein recognition device and biological recognition system |
| CN110532751B (en) * | 2019-09-02 | 2022-05-31 | 联想(北京)有限公司 | Information processing method, electronic device, and readable storage medium |
| CN114973338A (en) * | 2022-06-16 | 2022-08-30 | 慧之安信息技术股份有限公司 | Sentinel position confirmation method based on fingerprint identification |
| CN111753656B (en) * | 2020-05-18 | 2024-04-26 | 深圳大学 | Feature extraction method, device, equipment and computer readable storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20060104485A1 (en) * | 2004-11-16 | 2006-05-18 | Imageware Systems, Inc. | Multimodal biometric platform |
| CN104361315A (en) * | 2014-10-27 | 2015-02-18 | 浙江工业大学 | 3D (three-dimensional) fingerprint recognition device based on monocular and multi-view stereoscopic machine vision |
| CN106919941A (en) * | 2017-04-26 | 2017-07-04 | 华南理工大学 | A kind of three-dimensional finger vein identification method and system |
-
2018
- 2018-08-30 CN CN201811004097.8A patent/CN109190554A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20060104485A1 (en) * | 2004-11-16 | 2006-05-18 | Imageware Systems, Inc. | Multimodal biometric platform |
| CN104361315A (en) * | 2014-10-27 | 2015-02-18 | 浙江工业大学 | 3D (three-dimensional) fingerprint recognition device based on monocular and multi-view stereoscopic machine vision |
| CN106919941A (en) * | 2017-04-26 | 2017-07-04 | 华南理工大学 | A kind of three-dimensional finger vein identification method and system |
Non-Patent Citations (1)
| Title |
|---|
| 吉紫娟: "指纹与静脉复合识别系统的图像采集", 《湖北第二师范学院学报》 * |
Cited By (22)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109700435A (en) * | 2019-01-28 | 2019-05-03 | 上海得舟信息科技有限公司 | A kind of projection intravenous angiography device and its image processing method |
| WO2020181465A1 (en) | 2019-03-11 | 2020-09-17 | Moqi Technology (beijing) Co., Ltd. | Device and method for contactless fingerprint acquisition |
| EP3895063A4 (en) * | 2019-03-11 | 2021-12-29 | MOQI Technology (Beijing) Co., Ltd. | Device and method for contactless fingerprint acquisition |
| US11734948B2 (en) | 2019-03-11 | 2023-08-22 | Moqi Technology (beijing) Co., Ltd. | Device and method for contactless fingerprint acquisition |
| CN110008852A (en) * | 2019-03-15 | 2019-07-12 | 深圳北斗通信科技有限公司 | Fingerprint collecting method, system and storage medium |
| CN110008931A (en) * | 2019-04-16 | 2019-07-12 | 上海应用技术大学 | In conjunction with the mixing recognition methods of fingerprint and finger venous information |
| CN110443217A (en) * | 2019-08-13 | 2019-11-12 | 深圳大学 | One kind being based on multispectral fingerprint method for anti-counterfeit and system |
| CN110443217B (en) * | 2019-08-13 | 2022-09-02 | 深圳大学 | Multispectral-based fingerprint anti-counterfeiting method and system |
| CN110532751B (en) * | 2019-09-02 | 2022-05-31 | 联想(北京)有限公司 | Information processing method, electronic device, and readable storage medium |
| KR102610600B1 (en) * | 2019-10-21 | 2023-12-05 | 선전 구딕스 테크놀로지 컴퍼니, 리미티드 | Fingerprint recognition method, fingerprint recognition device and electronic device |
| WO2021077259A1 (en) * | 2019-10-21 | 2021-04-29 | 深圳市汇顶科技股份有限公司 | Fingerprint recognition method, fingerprint recognition device and electronic apparatus |
| US11455826B2 (en) | 2019-10-21 | 2022-09-27 | Shenzhen GOODIX Technology Co., Ltd. | Method for identifying fingerprint, fingerprint identification apparatus and electronic device |
| KR20210096202A (en) * | 2019-10-21 | 2021-08-04 | 선전 구딕스 테크놀로지 컴퍼니, 리미티드 | Fingerprint recognition method, fingerprint recognition device and electronic device |
| CN110945524A (en) * | 2019-10-21 | 2020-03-31 | 深圳市汇顶科技股份有限公司 | Fingerprint identification method, fingerprint identification device and electronic equipment |
| CN111046807A (en) * | 2019-12-16 | 2020-04-21 | 上海芯灵科技有限公司 | Finger vein knuckle line coincidence recognition system |
| CN113378604B (en) * | 2020-03-10 | 2022-07-12 | 浙江宇视科技有限公司 | Finger vein recognition device and biological recognition system |
| CN113378604A (en) * | 2020-03-10 | 2021-09-10 | 浙江宇视科技有限公司 | Finger vein recognition device and biological recognition system |
| CN111753656B (en) * | 2020-05-18 | 2024-04-26 | 深圳大学 | Feature extraction method, device, equipment and computer readable storage medium |
| CN112084840A (en) * | 2020-07-24 | 2020-12-15 | 浙江工业大学 | Finger vein identification method based on three-dimensional NMI |
| CN112101332A (en) * | 2020-11-23 | 2020-12-18 | 北京圣点云信息技术有限公司 | Feature extraction and comparison method and device based on 3D finger veins |
| CN113076921A (en) * | 2021-04-21 | 2021-07-06 | 华南理工大学 | Multispectral texture synchronous mapping method of three-dimensional finger biological feature model |
| CN114973338A (en) * | 2022-06-16 | 2022-08-30 | 慧之安信息技术股份有限公司 | Sentinel position confirmation method based on fingerprint identification |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109190554A (en) | It is a kind of based on fingerprint and to refer to the 3D identifying system and method for vein | |
| US11017205B2 (en) | Three-dimensional finger vein recognition method and system | |
| JP6650946B2 (en) | System and method for performing fingerprint-based user authentication using images captured with a mobile device | |
| Syarif et al. | Enhanced maximum curvature descriptors for finger vein verification | |
| Hao et al. | Multispectral palm image fusion for accurate contact-free palmprint recognition | |
| WO2017059591A1 (en) | Finger vein identification method and device | |
| CN105760841B (en) | Identity recognition method and system | |
| CN104933432B (en) | Processing method of finger abdomen crease and finger vein image | |
| CN108960068A (en) | For acquiring the light source brightness adjusting device and method of finger venous image | |
| CN102184387A (en) | Finger vein authentication system | |
| CN107832739A (en) | A kind of palm vein identification system and method based on ORB feature extractions | |
| CN111462379A (en) | Access control management method, system and medium containing palm vein and face recognition | |
| CN107239772A (en) | Palm print and palm vein image collecting device and clearance gate | |
| TW200905577A (en) | Iris recognition system | |
| CN105426843A (en) | Single-lens palm vein and palmprint image acquisition apparatus and image enhancement and segmentation method | |
| CN104778445A (en) | Living body recognizing device and method based on three-dimensional characteristics of finger venas | |
| CN106845449A (en) | A kind of image processing apparatus, method and face identification system | |
| Sun et al. | A DSP-based finger vein authentication system | |
| Parziale et al. | Advanced technologies for touchless fingerprint recognition | |
| Kumar et al. | Online biometric authentication using hand vein patterns | |
| Soni et al. | A new vein pattern-based verification system | |
| Wang et al. | Cross-device hand vein recognition based on improved SIFT | |
| CN110866235B (en) | Identity recognition method and device for simultaneously capturing human pulse and vein images | |
| Kumar et al. | Biometric authentication based on infrared thermal hand vein patterns | |
| KR101450247B1 (en) | Method for authenticating based on finger vein using SIFT keypoint |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190111 |