CN105426843A - Single-lens palm vein and palmprint image acquisition apparatus and image enhancement and segmentation method - Google Patents
Single-lens palm vein and palmprint image acquisition apparatus and image enhancement and segmentation method Download PDFInfo
- Publication number
- CN105426843A CN105426843A CN201510801840.2A CN201510801840A CN105426843A CN 105426843 A CN105426843 A CN 105426843A CN 201510801840 A CN201510801840 A CN 201510801840A CN 105426843 A CN105426843 A CN 105426843A
- Authority
- CN
- China
- Prior art keywords
- image
- palm vein
- palm
- light
- ccd sensor
- 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
- 210000003462 vein Anatomy 0.000 title claims abstract description 61
- 238000000034 method Methods 0.000 title claims abstract description 46
- 230000011218 segmentation Effects 0.000 title claims description 18
- 230000002708 enhancing effect Effects 0.000 claims abstract description 10
- 239000000463 material Substances 0.000 claims abstract description 7
- 230000008569 process Effects 0.000 claims description 20
- 238000001914 filtration Methods 0.000 claims description 18
- 230000000877 morphologic effect Effects 0.000 claims description 10
- 238000012545 processing Methods 0.000 claims description 9
- 238000005728 strengthening Methods 0.000 claims description 8
- 238000009499 grossing Methods 0.000 claims description 5
- 238000011946 reduction process Methods 0.000 claims description 5
- 238000005192 partition Methods 0.000 claims description 4
- 238000004064 recycling Methods 0.000 claims description 4
- 230000003595 spectral effect Effects 0.000 claims description 4
- 230000001186 cumulative effect Effects 0.000 claims description 3
- 230000010339 dilation Effects 0.000 claims description 3
- 230000003628 erosive effect Effects 0.000 claims description 3
- 238000012804 iterative process Methods 0.000 claims description 3
- 230000015572 biosynthetic process Effects 0.000 claims description 2
- 238000002834 transmittance Methods 0.000 claims description 2
- 230000000694 effects Effects 0.000 description 16
- 238000005516 engineering process Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 6
- 238000013461 design Methods 0.000 description 4
- 210000003491 skin Anatomy 0.000 description 4
- 230000008859 change Effects 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000005286 illumination Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 210000004204 blood vessel Anatomy 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000000052 comparative effect Effects 0.000 description 1
- 239000012141 concentrate Substances 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 210000002615 epidermis Anatomy 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000003709 image segmentation Methods 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 238000002310 reflectometry Methods 0.000 description 1
- 238000000638 solvent extraction Methods 0.000 description 1
- 238000007514 turning Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/12—Fingerprints or palmprints
- G06V40/13—Sensors therefor
-
- G06T5/70—
-
- G06T5/94—
-
- 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
- G06V40/1324—Sensors therefor by using geometrical optics, e.g. using prisms
Abstract
The invention discloses an apparatus capable of acquiring palm vein and palmprint images at the same time, and a method for enhancing and segmenting the palm vein and palmprint images obtained by adopting the apparatus. The apparatus comprises a housing, a lens, a near-infrared LED light source group, a visible white LED light source group, an annular light equalization material, a visible light CCD sensor, a near-infrared CCD sensor, a first semi-transmitting and semi-reflecting lens and a second semi-transmitting and semi-reflecting lens. According to the apparatus and the method, one lens is used for acquiring the palm vein and palmprint images at the same time, so that the regional consistency of the palm vein and palmprint images is ensured; the semi-transmitting and semi-reflecting lenses are used for separating light rays with different wavelengths in the same lens, and then the near-infrared CCD sensor and the visible light CCD sensor are used for acquiring the palm vein and palmprint images, so that the definition of the palm vein and palmprint images is ensured; and the acquired palm vein and palmprint images are enhanced and segmented, so that the phenomenon of non-uniform gray values of a palm region can be eliminated, and palm vein, palmprint and skin regions can be accurately distinguished.
Description
Technical field
The present invention relates to living things feature recognition field, be specially a kind of device using single camera lens simultaneously to gather palm vein image and palmprint image, the invention still further relates to enhancing and the dividing method of a kind of low contrast vena metacarpea and palmprint image.
Background
Current, comparative maturity and several biometrics identification technologies most with application prospect comprise fingerprint recognition, iris recognition, face recognition, speech recognition, the identification of palm type, signature identify.But the defect that above-mentioned biometrics identification technology has some common: the first is affected by environment larger; The second, can be replicated and usurp in theory.
Hand vein recognition technology is a kind of new biometrics identification technology proposed recent years, has uniqueness, stability, unforgeable, the advantage such as contactless.Hand vein recognition technology comprises palm vein, finger vena and Palm-dorsal vein recognition three kinds of forms.Wherein the advantage of palm vein recognition technology comprises 2 points: the first, and vena metacarpea is for finger vein, and its blood vessel is comparatively thick and under being positioned at epidermis, therefore easily capture vena metacarpea image; The second, vena metacarpea is for hand back vein structure, and its geometry is more complicated, can improve the accuracy of identification.But vena metacarpea structure is only be made up of several thicker vein blood vessels, cannot meet the application requirement of high security fields.The palmmprint structure of people can be used for identification as a kind of biological characteristic, if merge the feature of vena metacarpea and palmmprint, can improve the accuracy of identification undoubtedly.
Disclosure of the invention number is the patent of CN101833647B: " the acquisition equipment of palmprint image and palmprint image disposal route ", disclose a kind of device and the recognition methods that gather palmprint image, but palmmprint is relatively simple for structure, only relies on palmmprint structure to carry out identification and there is certain potential safety hazard.
Disclosure of the invention number is the patent of CN101196987B: " online palmprint, palm vein image personal identification method and special-purpose collection instrument thereof ".Disclose a kind of device that can gather palmmprint and vena metacarpea, but its gatherer process is for alternately to open visible LED and near-infrared LED, thus obtains palmmprint and vena metacarpea image respectively.Owing to taking alternately, the method cannot capture the on all four palmmprint in region and vena metacarpea image simultaneously; Due to the process need regular hour of video camera imaging when light source switches, result in and identify that T.T. increases; In addition, near infrared palm vein image contrast is lower, and the method does not study effective image enchancing method.
Summary of the invention
In order to overcome problems of the prior art, the object of this invention is to provide a kind of device that simultaneously can gather palm vein and palmprint image, and adopt said apparatus acquisition palm vein and palmprint image to carry out strengthening and dividing method.
To achieve these goals, the present invention by the following technical solutions: a kind of single-lens lower device simultaneously gathering palm vein and palmprint image, described device comprises:
Housing, four face closures, anterior perforate is for installing camera lens;
Camera lens, through housing, can simultaneously through luminous ray and near infrared light, for gathering palm image;
Light source group, surrounding lens, light directive camera lens dead ahead, for throwing light on and light filling to palm;
The equal luminescent material of ring-type, is arranged on light source group dead ahead, and size can shelter from light source group, completely for the formation of uniform light;
Ccd sensor group, is arranged in housing, for gathering the image through camera lens;
Lens set, is arranged in housing, for sending the image through camera lens to ccd sensor group;
Control store PC, connecting ccd sensor group, for the palm vein received and palmprint image being carried out strengthening and dividing processing, and storing.
Described light source group comprises near-infrared LED light source group and visible white light LED light source group, and described near-infrared LED light source group is 8 850nm near-infrared LED lamps, and visible white light LED light source group is 8 visible white light LED.
Described ccd sensor group comprises Visible-light CCD sensor and Near Infrared CCD sensor; Described Visible-light CCD sensor setting is in the dead astern of camera lens, and the central shaft of the two point-blank, for gathering the light of visible white light LED light source group transmitting after palmar, through the visible ray palmprint image of camera lens; Described Near Infrared CCD sensor, is arranged on the top in housing, and it is just facing to being 225 degree with horizontal plane angle, for gathering the light of near-infrared LED light source group transmitting after palmar, through the near infrared palm vein image of camera lens.
Described lens set comprises two semi-transparent semi-reflecting eyeglasses, first semi-transparent semi-reflecting eyeglass is arranged in the middle of camera lens and Visible-light CCD sensor, the angle of the first semi-transparent semi-reflecting eyeglass and surface level is 67.5 degree, for transmitting the luminous ray through camera lens, the semi-transparent semi-reflecting eyeglass of near infrared light to the second of reflectance-transmittance camera lens simultaneously, the second semi-transparent semi-reflecting eyeglass reflect near infrared light line is to Near Infrared CCD sensor.
Described device also comprises palm placing rack and middle finger fixed card slot, described palm placing rack is for being arranged on housing front portion, camera lens outside, for limiting the distance between palm and camera lens, middle finger fixed card slot is arranged on palm placing rack, for keeping the consistance gathering palm vein and palmprint image.
Gather a method for palm vein and palmprint image simultaneously, comprise the following steps:
(1) palm is placed on 15cm before camera lens, obtains palm vein and palmprint image by Visible-light CCD sensor and Near Infrared CCD sensor;
(2) palm vein collected and palmprint image are split;
(3) based on Retinex iterative filtering, palm vein and palmprint image are strengthened;
(4) binarization segmentation is carried out to the palm vein after enhancing and palmprint image;
(5) authenticity judgement is carried out to the palm vein in the image after binaryzation and palmmprint structure, remove noise and false structure.
Described step 2 adopt delete gather each 50 pixels of image surrounding.
Described step 3 comprises the following steps:
(1) use the mean filter of 3*3 to the palm vein after segmentation and the smoothing filtering and noise reduction process of palmprint image, adopt following formula:
Wherein I
0(x, y) is palm vein after region of interest regional partition and palmprint image, and I (x, y) is the image after smothing filtering denoising;
(2) Retinex algorithm improved is adopted to strengthen palm vein and palmprint image:
The intensity of variation d (x, y) of A, each neighborhood of pixel points pixel of employing following formula computed image:
d(x,y)＝|I(x,y+1)-I(x,y-1)|+|I(x+1,y)-I(x-1,y)|
Wherein I (x, y) is the image of video camera shooting, d (x, y) be each pixel left and right pixel value difference and up and down picture element interpolation absolute value and;
B, employing following formula calculate dynamic filter window function:
w(x,y)＝(1+0.5d
2(x,y))
-1
C, use dynamic filter window function w (x, y) each element to image I (x, y) carry out iterative filtering 20 times, computing environment light component L (x, y):
L
t+1(x,y)＝max(L′
t+1(x,y),L
t(x,y))
Wherein: L
0(x, y)=I (x, y)
Wherein I (x, y) is original input picture, and L (x, y) is the ambient light component of trying to achieve.Said process is iterative process, initial L
0(x, y)=I (x, y), N (x, y) are the cumulative sums of the 3*3 neighborhood of spectral window w (x, y);
D, employing Retinex algorithm, calculate the image R (x, y) after strengthening, and normalize to [0,1];
R(x,y)＝logI(x,y)-logL(x,y)
R
0(x,y)＝(R(x,y)-min(R))/(max(R)-min(R))
R
0(x, y) is balanced and palm vein after strengthening and palmprint image;
(3) contrast stretching process is carried out to palm vein and palmprint image:
A, R
0(x, y) is if=0 R
0(x, y) <0.6
R
0(x, y)=2*R
0(x, y) is if-1 R
0(x, y)>=0.6
B, the cosine transform of use gray scale carry out gray scale stretch processing to image, obtain R
1(x, y), computing formula is as follows:
R
1(x,y)＝1-cos(0.5*π*R
0(x,y))
The Gaussian filter of C, use 3*3 is to R
1(x, y) carries out filtering and noise reduction process.
Use the method opponent palmmprint of overall binaryzation and palm vein image to split in described step 4, the optimum segmentation threshold value of palm line is 0.45, and the optimum segmentation threshold value of palm vein picture is 0.55.
Described step 5 comprises the following steps:
(1) utilize morphological operation to process the picture after segmentation, first carry out morphological dilations and eliminate small holes, connect little gap simultaneously, recycling morphological erosion recovers the width of original vena metacarpea and palmmprint;
(2) the medium and small black patches noise of binary image is removed;
(3) false vena metacarpea and palmmprint structure is removed.
The invention has the beneficial effects as follows: (1) the present invention uses a camera lens to gather vena metacarpea and palmmprint picture simultaneously, has ensured the region consistency of vena metacarpea picture and palmmprint picture; (2) semi-transparent semi-reflecting eyeglass is used, the light of different wave length under same camera lens is separated, recycling Near Infrared CCD sensor and Visible-light CCD sensor collect the picture of vena metacarpea and palmmprint respectively, have ensured the sharpness of vena metacarpea and palmmprint picture; (3) vena metacarpea of the present invention and palmprint image strengthen and partitioning algorithm can overcome the gray-scale value uneven phenomenon of palm area, distinguish vena metacarpea accurately, palmmprint and skin area, and the computation complexity of the method is less, on the computing machine of corei7-3770,3.4GHz, 4G internal memory, 0.1s is about to the vena metacarpea of 160*120 size and the mean value in the processing time of palmmprint picture, meets the requirement calculated in real time.
Accompanying drawing explanation
Fig. 1 is the sectional view of embodiment vena metacarpea and palmprint image collecting device.
Fig. 2 is the external structure of embodiment vena metacarpea and palmprint image collecting device.
Fig. 3 is embodiment vena metacarpea and palm-print image capture, strengthens and segmentation process flow diagram.
Fig. 4 is embodiment vena metacarpea (a) and palmmprint (b) picture area-of-interest segmentation result figure.
Fig. 5 is that embodiment vena metacarpea (a) and palmmprint (b) picture strengthen design sketch.
Fig. 6 is embodiment vena metacarpea (a) and palmmprint (b) picture contrast drawing effect figure.
Fig. 7 is embodiment vena metacarpea (a) and palmmprint (b) picture segmentation design sketch.
Fig. 8 is embodiment vena metacarpea (a) and palmmprint (b) picture Morphological scale-space design sketch.
Fig. 9 is embodiment vena metacarpea (a) and palmmprint (b) picture denoising effect figure.
Figure 10 is that false structure design sketch removed by embodiment vena metacarpea (a) and palmmprint (b) picture.
Embodiment
Below in conjunction with specific embodiments and the drawings, the present invention is further illustrated.
Vena metacarpea and palmprint image collecting device under a kind of single camera lens, as shown in Figure 1, its external structure as shown in Figure 2 for its sectional view.
As shown in Figure 1, device comprises: housing 1, camera lens 2, near-infrared LED light source group 3, visible white light LED light source group 4, the equal luminescent material of ring-type 5, Visible-light CCD sensor 6, Near Infrared CCD sensor 7, first semi-transparent semi-reflecting eyeglass 8 and the second semi-transparent semi-reflecting eyeglass 9.
As shown in Figure 2, device also comprises palm placing rack 10 and middle finger fixed card slot 11.
Housing effect is immobilising device, and avoid the light in environment to affect, require opaque, do not have particular/special requirement to material, four face closures, anterior perforate is for installing camera lens simultaneously.Camera lens is common visible ray and the general camera lens of near infrared light, can simultaneously through luminous ray and near infrared light.850nm near-infrared LED group has LED 8, is looped around around camera lens, light directive camera lens dead ahead, as the light source of shooting vena metacarpea image.Visible white light LED group has LED 8, is looped around around near-infrared LED group, light directive camera lens dead ahead, as the light source of shooting palmprint image.Annular all luminescent material is placed on the dead ahead of two groups of light sources, and size can shelter from two groups of light sources completely, and its effect forms uniform near infrared and luminous ray, thus collect balanced vena metacarpea and palmprint image.
Visible-light CCD sensor is placed on the dead astern of camera lens, and the central shaft of the two is point-blank, and its effect is: the light gathering the transmitting of visible white light LED group after palmar, through the visible ray palmprint image of camera lens.Near Infrared CCD sensor is positioned at the top of enclosure interior, and it is just facing to being 225 degree with horizontal plane angle, and its effect is: the near infrared light gathering second semi-transparent semi-reflecting eyeglass reflection, thus shooting near infrared palm vein image.
Semi-transparent semi-reflecting eyeglass has 2, can through luminous ray, reflect near IR light simultaneously.First semi-transparent semi-reflecting eyeglass is placed in the middle of camera lens and Visible-light CCD sensor, the angle of eyeglass and surface level is 67.5 degree, its effect is: the luminous ray transmitted through camera lens, such visible LED can capture palmprint image, simultaneously near infrared light to a second semi-transparent semi-reflecting eyeglass of reflection lens.Second semi-transparent semi-reflecting eyeglass is placed on the top of left side housing, and eyeglass is perpendicular to surface level, and its effect is: the near infrared light of the semi-transparent semi-reflecting eyeglass reflection of secondary reflection first is again to Near Infrared CCD sensor.
The palm vein that Visible-light CCD sensor and Near Infrared CCD sensor receive and palmprint image send control store PC to, strengthen and dividing processing, and store image.
Palm placing rack for being arranged on housing front portion, camera lens is outside, for limiting the distance between palm and camera lens, height 15 centimetres.Middle finger fixed card slot is arranged on palm placing rack, and effect is the position of fixing middle finger and palm intersection, for keeping the consistance gathering palm vein and palmprint image.
Vena metacarpea and palm-print image capture, strengthen and split process flow diagram and see Fig. 3, the palmmprint adopting palm vein and palmprint image collecting device to photograph and vena metacarpea picture contrast lower, if be directly used for identifying, be difficult to obtain higher discrimination, therefore need to carry out image enhaucament and dividing processing, step is as follows:
Step 1: palm is placed on 15cm before camera lens, obtains palm vein and palmprint image by Visible-light CCD sensor and Near Infrared CCD sensor.
Step 2: carry out " region of interest regional partition " the original image photographed, obtains " standard palmmprint and vena metacarpea image ".
Embodiment for: delete the original vena metacarpea that gathers and each 50 pixels of palmprint image surrounding, hand edge vena metacarpea and the less region of palmmprint structure are removed in its effect, thus obtaining the abundant critical area of structural information, the region of interest area image of acquisition is as Fig. 4.
Step 3: based on vena metacarpea and the palmprint image enhancing of Retinex iterative filtering.
Embodiment is:
1, smothing filtering denoising.
With the mean filter of 3*3 to the vena metacarpea collected and the smoothing filtering process of palmprint image.Because the original vena metacarpea that photographs and palmprint image contain certain noise, therefore first use the smoothing filter of a 3*3 to the smoothing filtering of image, as shown in the formula:
Wherein I
0(x, y) is vena metacarpea after region of interest regional partition and palmprint image, and I (x, y) is the image of smothing filtering denoising.
2, the Retinex algorithm improved strengthens vena metacarpea and palmprint image.
Although harvester employs annular all luminescent material disperse light, define more uniform light, the gray-scale value of the image collected is still not too even; In addition, because collected picture contrast is lower, research illumination equilibrium and structure is therefore needed to strengthen algorithm.
Retinex theory is a set of color theory that EdwinLand proposes, and can be applied in image processing field through research in recent years.The core concept of Retinex theory is: human eye is to the perception of an object color, still can accurately judge when ambient light change or body surface uneven illumination, be because the vision system of the mankind can carry out certain process, eliminate the disturbing factors such as the intensity of light source.Irradiation light can be removed from the image photographed by Retinex theory, thus the reflectivity properties that acquisition object has.Although near-infrared image does not have color, the gray scale uneven phenomenon that Retinex theory eliminates vena metacarpea and palmprint image can be applied equally.
Retinex theory is defined as follows:
R(x,y)＝logI(x,y)-logL(x,y)
Wherein I (x, y) is the image of video camera shooting, and L (x, y) is ambient light component, and R (x, y) is gray balance and the image after strengthening; Carry out simulated environment light component L (x, y) by carrying out gaussian filtering to former figure in standard Retinex theory, ambient light component L (x, y) computation process of the present invention is as follows:
(1) the intensity of variation d (x, y) of each neighborhood of pixel points pixel of computed image, as shown in the formula:
d(x,y)＝|I(x,y+1)-I(x,y-1)|+|I(x+1,y)-I(x-1,y)|
Easily find from formula, d (x, y) represent each pixel left and right pixel value difference and up and down picture element interpolation absolute value and, the severe degree of this local neighborhood change can be represented.
(2) calculating dynamic filter window function w (x, y) is a function successively decreased with the increase of certain pixel vegetarian refreshments gradient, as shown in the formula:
w(x,y)＝(1+0.5d
2(x,y))
-1
Easily find from formula, neighborhood of pixel points intensity of variation is higher, and the value of this spectral window function is less.That is: when d (x, y) comparatively large (grey scale change is comparatively large, may be edge), smoothly weaken, otherwise strengthen smooth effect.Like this, while smoothed image flat site, marginal information is remained.
(3) dynamic filter window function w (x, y) each element to image I (x, y) is used to carry out iterative filtering 20 times, computing environment light component L (x, y):
L
t+1(x,y)＝max(L′
t+1(x,y),L
t(x,y))
Wherein:
L
0(x,y)＝I(x,y)
Wherein I (x, y) is original input picture, and L (x, y) is the ambient light component of trying to achieve.Said process is iterative process, initial L
0(x, y)=I (x, y), N (x, y) are the cumulative sums of the 3*3 neighborhood of spectral window w (x, y), and its effect is the consistance of the interval value ensureing pixel before and after iteration.The actual effect solving the higher value of the pixel before and after iteration is, adds the overall brightness of skin area, strengthens the contrast of picture.
(4) solve the image after enhancing, and normalize to [0,1].
After solving ambient light component, the formula of Retinex algorithm can be utilized, directly calculate the vena metacarpea after balanced also enhancing and palmmprint picture;
R(x,y)＝logI(x,y)-logL(x,y)
Now pixel value is not interval in [0,1], therefore needs to utilize following formula that pixel value is normalized to [0,1] scope.
R
0(x,y)＝(R(x,y)-min(R))/(max(R)-min(R))
So far, the vena metacarpea after can being enhanced and palmmprint picture R
0(x, y), as shown in Figure 5.
3, contrast stretching process.
After above-mentioned calculating, the gray-scale value of picture is general higher, and contrast is lower, therefore needs to do contrast stretching process further, and detailed process is:
(1) R
0(x, y) is if=0 R
0(x, y) <0.6
R
0(x, y)=2*R
0(x, y) is if-1 R
0(x, y)>=0.6
Vena metacarpea after enhancing and palmmprint picture R
0the gray-scale value of (x, y) mainly concentrates in the scope of [0.6,1], therefore utilizes this conversion, can stretch between its gray area, increases contrast.
(2) re-use gray scale cosine transform and gray scale stretch processing is carried out to image, obtain R
1(x, y), increase the grey value difference of vena metacarpea, palmmprint and skin further, computing formula is as follows:
R
1(x,y)＝1-cos(0.5*π*R
0(x,y))
(3) finally use the Gaussian filter of 3*3 to R
1(x, y) carries out filtering and noise reduction process, and the vena metacarpea after enhancing and palmprint image are as shown in Figure 6.
Step 4: binarization segmentation is carried out to the vena metacarpea after enhancing and palmprint image.
Vena metacarpea after step 2 processes and the gray-scale value of palmmprint picture more balanced, and vena metacarpea, contrast between palmmprint and skin are larger, therefore the method for overall binaryzation can be used palmmprint and vena metacarpea Image Segmentation Using, the optimum segmentation threshold value of palmmprint is 0.45, the optimum segmentation threshold value of vena metacarpea picture is 0.55, and treatment effect is as Fig. 7.
Step 5: carry out authenticity judgement to the vena metacarpea in the image after binaryzation and palmmprint structure, removes noise and false structure.
Embodiment is as follows:
(1) utilize morphological operation to process the picture after segmentation, first carry out morphological dilations and eliminate small holes, connect little gap simultaneously, recycling morphological erosion recovers the width of original vena metacarpea and palmmprint; Treatment effect is as Fig. 8.
(2) remove the medium and small black patch noise of binary image, if the grey scale pixel value namely having five or more in 5 × 5 neighborhoods of a pixel is 0, is then set to 0, otherwise is set to 1; Treatment effect is as Fig. 9.
(3) false vena metacarpea and palmmprint structure is removed, method is as follows: mark black block in binary image, calculate every block area (pixel count), the length determining the boundary rectangle of every block and width (image size 160*120), then process according to following situation:
● if black patch area is less than 150, then delete this black patch.Palmmprint and vena metacarpea structure have continuity, and the pixel number had is more, and the black patch of zonule is generally noise, stain or small opacities.
● if black patch area, between 150 to 600, judges the fold differences D of its length and width, if D is less than 5, then deletes this black patch.Be analyzed as follows: for the black patch of area in 150-600 scope, be generally wall scroll vena metacarpea or palmmprint, there is single direction, now the length of black patch and wide difference general larger, through a large amount of statistical experiment, the length and width difference value of wall scroll vena metacarpea and palmmprint structure is greater than 5.This larger false black patch generally produces the shaded side at four turnings at image.
● if black patch area is greater than 600, retains this black patch, is true vena metacarpea and palmmprint structure.
Through above step, can be not high from contrast accurately, extract real structure, as Figure 10 in the not too uniform vena metacarpea of gray-scale value and palmmprint picture.Visible: originally distant vena metacarpea and palmmprint structure is now gem-pure shows.
The above is only preferred embodiment of the present invention, not does any type of restriction to the present invention.Every above embodiment is done according to techniques and methods essence of the present invention any simple modification, equivalent variations and modification, all still belong in the scope of techniques and methods scheme of the present invention.
Claims (10)
1. the single-lens lower device simultaneously gathering palm vein and palmprint image, is characterized in that; Described device comprises:
Housing, four face closures, anterior perforate is for installing camera lens;
Camera lens, through housing, can simultaneously through luminous ray and near infrared light, for gathering palm image;
Light source group, surrounding lens, light directive camera lens dead ahead, for throwing light on and light filling to palm;
The equal luminescent material of ring-type, is arranged on light source group dead ahead, and size can shelter from light source group, completely for the formation of uniform light;
Ccd sensor group, is arranged in housing, for gathering the image through camera lens;
Lens set, is arranged in housing, for sending the image through camera lens to ccd sensor group;
Control store PC, connecting ccd sensor group, for the palm vein received and palmprint image being carried out strengthening and dividing processing, and storing.
2. device according to claim 1, it is characterized in that: described light source group comprises near-infrared LED light source group and visible white light LED light source group, described near-infrared LED light source group is 8 850nm near-infrared LED lamps, and visible white light LED light source group is 8 visible white light LED.
3. device according to claim 2, is characterized in that: described ccd sensor group comprises Visible-light CCD sensor and Near Infrared CCD sensor; Described Visible-light CCD sensor setting is in the dead astern of camera lens, and the central shaft of the two point-blank, for gathering the light of visible white light LED light source group transmitting after palmar, through the visible ray palmprint image of camera lens; Described Near Infrared CCD sensor, is arranged on the top in housing, and it is just facing to being 225 degree with horizontal plane angle, for gathering the light of near-infrared LED light source group transmitting after palmar, through the near infrared palm vein image of camera lens.
4. device according to claim 3, it is characterized in that: described lens set comprises two semi-transparent semi-reflecting eyeglasses, first semi-transparent semi-reflecting eyeglass is arranged in the middle of camera lens and Visible-light CCD sensor, the angle of the first semi-transparent semi-reflecting eyeglass and surface level is 67.5 degree, for transmitting the luminous ray through camera lens, the semi-transparent semi-reflecting eyeglass of near infrared light to the second of reflectance-transmittance camera lens simultaneously, the second semi-transparent semi-reflecting eyeglass reflect near infrared light line is to Near Infrared CCD sensor.
5. device according to claim 1, it is characterized in that: described device also comprises palm placing rack and middle finger fixed card slot, described palm placing rack is for being arranged on housing front portion, camera lens outside, for limiting the distance between palm and camera lens, middle finger fixed card slot is arranged on palm placing rack, for keeping the consistance gathering palm vein and palmprint image.
6. gather a method for palm vein and palmprint image according to the arbitrary described device of claim 1 to 5 simultaneously, it is characterized in that comprising the following steps:
(1) palm is placed on 15cm before camera lens, obtains palm vein and palmprint image by Visible-light CCD sensor and Near Infrared CCD sensor;
(2) palm vein collected and palmprint image are split;
(3) based on Retinex iterative filtering, palm vein and palmprint image are strengthened;
(4) binarization segmentation is carried out to the palm vein after enhancing and palmprint image;
(5) authenticity judgement is carried out to the palm vein in the image after binaryzation and palmmprint structure, remove noise and false structure.
7. method according to claim 6, is characterized in that: described step 2 adopt delete gather each 50 pixels of image surrounding.
8. method according to claim 6, is characterized in that: described step 3 comprises the following steps:
(1) use the mean filter of 3*3 to the palm vein after segmentation and the smoothing filtering and noise reduction process of palmprint image, adopt following formula:
Wherein I
0(x, y) is palm vein after region of interest regional partition and palmprint image, and I (x, y) is the image after smothing filtering denoising;
(2) Retinex algorithm improved is adopted to strengthen palm vein and palmprint image:
The intensity of variation d (x, y) of A, each neighborhood of pixel points pixel of employing following formula computed image:
d(x,y)＝|I(x,y+1)-I(x,y-1)|+|I(x+1,y)-I(x-1,y)|
Wherein I (x, y) is the image of video camera shooting, d (x, y) be each pixel left and right pixel value difference and up and down picture element interpolation absolute value and;
B, employing following formula calculate dynamic filter window function:
w(x,y)＝(1+0.5d
2(x,y))
-1
C, use dynamic filter window function w (x, y) each element to image I (x, y) carry out iterative filtering 20 times, computing environment light component L (x, y):
L
t+1(x,y)＝max(L′
t+1(x,y),L
t(x,y))
Wherein: L
0(x, y)=I (x, y)
Wherein I (x, y) is original input picture, and L (x, y) is the ambient light component of trying to achieve.Said process is iterative process, initial L
0(x, y)=I (x, y), N (x, y) are the cumulative sums of the 3*3 neighborhood of spectral window w (x, y);
D, employing Retinex algorithm, calculate the image R (x, y) after strengthening, and normalize to [0,1];
R(x,y)＝logI(x,y)-logL(x,y)
R
0(x,y)＝(R(x,y)-min(R))/(max(R)-min(R))
R
0(x, y) is balanced and palm vein after strengthening and palmprint image;
(3) contrast stretching process is carried out to palm vein and palmprint image:
A, R
0(x, y) is if=0 R
0(x, y) <0.6
R
0(x, y)=2*R
0(x, y) is if-1 R
0(x, y)>=0.6
B, the cosine transform of use gray scale carry out gray scale stretch processing to image, obtain R
1(x, y), computing formula is as follows:
R
1(x,y)＝1-cos(0.5*π*R
0(x,y))
The Gaussian filter of C, use 3*3 is to R
1(x, y) carries out filtering and noise reduction process.
9. method according to claim 6, it is characterized in that: in described step 4, use the method opponent palmmprint of overall binaryzation and palm vein image to split, the optimum segmentation threshold value of palm line is 0.45, and the optimum segmentation threshold value of palm vein picture is 0.55.
10. method according to claim 6, is characterized in that: described step 5 comprises the following steps:
(1) utilize morphological operation to process the picture after segmentation, first carry out morphological dilations and eliminate small holes, connect little gap simultaneously, recycling morphological erosion recovers the width of original vena metacarpea and palmmprint;
(2) the medium and small black patches noise of binary image is removed;
(3) false vena metacarpea and palmmprint structure is removed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510801840.2A CN105426843B (en) | 2015-11-19 | 2015-11-19 | The single-lens lower vena metacarpea of one kind and palmprint image collecting device and image enhancement and dividing method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510801840.2A CN105426843B (en) | 2015-11-19 | 2015-11-19 | The single-lens lower vena metacarpea of one kind and palmprint image collecting device and image enhancement and dividing method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105426843A true CN105426843A (en) | 2016-03-23 |
| CN105426843B CN105426843B (en) | 2019-02-22 |
Family
ID=55505043
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510801840.2A Active CN105426843B (en) | 2015-11-19 | 2015-11-19 | The single-lens lower vena metacarpea of one kind and palmprint image collecting device and image enhancement and dividing method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105426843B (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106236016A (en) * | 2016-08-18 | 2016-12-21 | 皖江新兴产业技术发展中心 | A kind of in-situ projection method for vein displaying picture |
| CN107038445A (en) * | 2017-02-13 | 2017-08-11 | 上海大学 | A kind of binaryzation and dividing method for Chinese character identifying code |
| CN107977935A (en) * | 2017-11-15 | 2018-05-01 | 合肥中科奔巴科技有限公司 | A kind of vena metacarpea image texture filtering reinforcement method |
| CN109447052A (en) * | 2019-01-09 | 2019-03-08 | 东浓智能科技(上海)有限公司 | A kind of vena metacarpea identification device being accurately positioned palm position and its implementation |
| CN111738076A (en) * | 2020-05-18 | 2020-10-02 | 山东大学 | Non-contact palm print and palm vein identification method and device |
| CN112241721A (en) * | 2020-10-27 | 2021-01-19 | 上海掌腾信息科技有限公司 | Method for realizing complete palm vein image acquisition based on light irradiation of different wavelengths |
| CN112241720A (en) * | 2020-10-27 | 2021-01-19 | 上海掌腾信息科技有限公司 | Method for realizing palm vein image self-adaptive extraction processing of palm vein recognition device aiming at palm inclined condition |
| CN114155296A (en) * | 2021-11-19 | 2022-03-08 | 宁波芯然科技有限公司 | Method for determining central area of palm image |
| TWI781459B (en) * | 2020-10-08 | 2022-10-21 | 國立中興大學 | Palm vein feature identification system and method |
| CN117593341A (en) * | 2024-01-19 | 2024-02-23 | 深圳市超诺科技有限公司 | System and method for processing target object monitoring data based on hunting camera |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103116741A (en) * | 2013-01-28 | 2013-05-22 | 天津理工大学 | Capture and identification system for blending images of palm veins and palm prints |
| US20140019489A1 (en) * | 2012-07-10 | 2014-01-16 | Jinjun Wang | Constructing Incremental Tree Model for Vein Image Recognition and Authentication |
| CN104217195A (en) * | 2014-08-07 | 2014-12-17 | 中国矿业大学 | A stereo imaging and recognition system for hand veins |
-
2015
- 2015-11-19 CN CN201510801840.2A patent/CN105426843B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140019489A1 (en) * | 2012-07-10 | 2014-01-16 | Jinjun Wang | Constructing Incremental Tree Model for Vein Image Recognition and Authentication |
| CN103116741A (en) * | 2013-01-28 | 2013-05-22 | 天津理工大学 | Capture and identification system for blending images of palm veins and palm prints |
| CN104217195A (en) * | 2014-08-07 | 2014-12-17 | 中国矿业大学 | A stereo imaging and recognition system for hand veins |
Non-Patent Citations (3)
| Title |
|---|
| 王华彬等: "基于Retinex和小波分解的手背静脉识别方法", 《系统工程理论与实践》 * |
| 苑玮琦等: "手部三模态图像采集系统的设计与实现", 《传感器与微系统》 * |
| 陈芳: "基于近红外成像的手背静脉识别系统研究与实现", 《中国优秀硕士学位论文全文数据库》 * |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106236016A (en) * | 2016-08-18 | 2016-12-21 | 皖江新兴产业技术发展中心 | A kind of in-situ projection method for vein displaying picture |
| CN106236016B (en) * | 2016-08-18 | 2019-02-26 | 皖江新兴产业技术发展中心 | A kind of in-situ projection method for vein imaging |
| CN107038445A (en) * | 2017-02-13 | 2017-08-11 | 上海大学 | A kind of binaryzation and dividing method for Chinese character identifying code |
| CN107977935A (en) * | 2017-11-15 | 2018-05-01 | 合肥中科奔巴科技有限公司 | A kind of vena metacarpea image texture filtering reinforcement method |
| CN109447052A (en) * | 2019-01-09 | 2019-03-08 | 东浓智能科技(上海)有限公司 | A kind of vena metacarpea identification device being accurately positioned palm position and its implementation |
| CN111738076A (en) * | 2020-05-18 | 2020-10-02 | 山东大学 | Non-contact palm print and palm vein identification method and device |
| TWI781459B (en) * | 2020-10-08 | 2022-10-21 | 國立中興大學 | Palm vein feature identification system and method |
| CN112241721A (en) * | 2020-10-27 | 2021-01-19 | 上海掌腾信息科技有限公司 | Method for realizing complete palm vein image acquisition based on light irradiation of different wavelengths |
| CN112241720A (en) * | 2020-10-27 | 2021-01-19 | 上海掌腾信息科技有限公司 | Method for realizing palm vein image self-adaptive extraction processing of palm vein recognition device aiming at palm inclined condition |
| CN112241721B (en) * | 2020-10-27 | 2022-07-05 | 上海掌腾信息科技有限公司 | Method for realizing complete palm vein image acquisition based on light irradiation of different wavelengths |
| CN114155296A (en) * | 2021-11-19 | 2022-03-08 | 宁波芯然科技有限公司 | Method for determining central area of palm image |
| CN117593341A (en) * | 2024-01-19 | 2024-02-23 | 深圳市超诺科技有限公司 | System and method for processing target object monitoring data based on hunting camera |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105426843B (en) | 2019-02-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105426843A (en) | Single-lens palm vein and palmprint image acquisition apparatus and image enhancement and segmentation method | |
| CN106530279B (en) | A kind of image processing method and system | |
| Haindl et al. | Unsupervised detection of non-iris occlusions | |
| RU2431190C2 (en) | Facial prominence recognition method and device | |
| CN107423690A (en) | A kind of face identification method and device | |
| Puhan et al. | Efficient segmentation technique for noisy frontal view iris images using Fourier spectral density | |
| CN101999900A (en) | Living body detecting method and system applied to human face recognition | |
| WO2007080817A1 (en) | Method for localizing pixels representing an iris in an image acquired of an eye | |
| KR20090087895A (en) | Method and apparatus for extraction and matching of biometric detail | |
| JP2007188504A (en) | Method for filtering pixel intensity in image | |
| CN107273812B (en) | A kind of living body iris method for anti-counterfeit for authentication | |
| CN112464690A (en) | Living body identification method, living body identification device, electronic equipment and readable storage medium | |
| Das et al. | Multi-angle based lively sclera biometrics at a distance | |
| KR101174103B1 (en) | A face recognition method of Mathematics pattern analysis for muscloskeletal in basics | |
| Benziane et al. | Dorsal hand vein identification based on binary particle swarm optimization | |
| CN107145820B (en) | Binocular positioning method based on HOG characteristics and FAST algorithm | |
| Szczepański et al. | Pupil and iris detection algorithm for near-infrared capture devices | |
| KR101767051B1 (en) | Method and apparatus for extracting finger vein image based on fuzzy inference | |
| Hashim et al. | Fast Iris localization based on image algebra and morphological operations | |
| CN114565531A (en) | Image restoration method, device, equipment and medium | |
| Poornima et al. | Unconstrained iris authentication through fusion of RGB channel information | |
| CN112801034A (en) | Finger vein recognition device | |
| Al-Hameed et al. | Face detection based on skin color segmentation and eyes detection in the human face | |
| Marcon et al. | Sclera segmentation for gaze estimation and iris localization in unconstrained images. | |
| Rajabhushanam et al. | IRIS recognition using hough transform |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |