CN106296905A - A kind of door lock being identified by palm - Google Patents

Abstract

The invention provides a kind of door lock being identified by palm, including door lock and the hand identification device that is connected with door lock, it is characterized in that, described door lock includes: door lock axle, power switch cabinet door leaf is extended in the front end of described door lock axle, it is provided with key hole in the leading section of described door lock axle, on described door lock axle, also twist-on has locking nut, described locking nut is positioned at the rear side of power switch cabinet door leaf, the first bolt it is socketed with successively on the door lock axle of described locking nut rear end, door lock catch, second bolt, described first bolt, door lock catch is fastened on door lock axle by the second bolt, described door lock catch end is additionally provided with support chip away from the side of power switch cabinet door leaf, the bottom of described support chip is tightened on door lock axle, and by the 3rd bolt fastening door lock shaft.The present invention improves the intensity of door lock catch, simple in construction, convenient installation, makes low cost, has a good application prospect.

Description

A kind of door lock being identified by palm

Technical field

The present invention relates to door lock field, be specifically related to a kind of door lock being identified by palm.

Background technology

Door lock greatly facilitates the life of people, but, the most existing door latch structure is complicated, installs inconvenience；Another The current door lock of aspect is many does not possess identity recognition function.

Along with the constantly maturation of the technology of identification and developing rapidly of computer technology, various lifes based on human body physiological characteristics Thing technology has gradually incorporated the every aspect in life.Staff is the mark of human evolution, and people usually goes impression and touching with hands The world.Hands, unlike the eyes of people, easily produces baffled worry and fear when in the face of strange instrument, when gathering hand-characteristic To the infringement brought on human psychological compared with gathering and being positioned at the feature of eye negligible.In hand-characteristic research, opponent Palm properties study is the most important research direction.

Summary of the invention

For solving the problems referred to above, it is desirable to provide a kind of door lock being identified by palm.

The purpose of the present invention realizes by the following technical solutions:

A kind of door lock being identified by palm, including door lock and the hand identification device that is connected with door lock, its feature Being that described door lock includes: door lock axle, power switch cabinet door leaf, the front end of described door lock axle are extended in the front end of described door lock axle Being provided with key hole in portion, on described door lock axle, also twist-on has locking nut, described locking nut to be positioned at power switch cabinet door leaf Rear side, the door lock axle of described locking nut rear end is socketed with the first bolt, door lock catch, the second bolt successively, described Door lock catch is fastened on door lock axle by one bolt, the second bolt, and described door lock catch end is away from power switch cabinet door leaf Side is additionally provided with support chip, and the bottom of described support chip is tightened on door lock axle, and by the 3rd bolt fastening door lock shaft.

Preferably, described door lock catch is elastic steel sheet.

Preferably, described door lock axle leading section is provided with end cap.

The invention have the benefit that employing door lock catch carries out door leaf locking, and be provided with at the rear side of door lock catch Blade, improves the intensity of door lock catch, simple in construction, convenient installation, makes low cost, have a good application prospect.

Accompanying drawing explanation

The invention will be further described to utilize accompanying drawing, but the embodiment in accompanying drawing does not constitute any limit to the present invention System, for those of ordinary skill in the art, on the premise of not paying creative work, it is also possible to obtain according to the following drawings Other accompanying drawing.

Fig. 1 is door lock schematic diagram of the present invention；

Fig. 2 is the structural representation of hand identification device of the present invention.

Reference:

Iris identification device 1, image password data base 21, palm image acquisition module 22, palm image pre-processing module 23, palm image characteristics extraction module 24, palm characteristics of image identification module 25, finger print acquisition module 31, fingerprint storage module 32, Fingerprint Processing Module 33.

Detailed description of the invention

The invention will be further described with the following Examples.

Application scenarios 1

See Fig. 1, Fig. 2, a kind of door lock being identified by palm of an embodiment in this application scene, including Door lock and the hand identification device being connected with door lock, is characterized in that, described door lock includes: door lock axle, the front end of described door lock axle Extending power switch cabinet door leaf, be provided with key hole in the leading section of described door lock axle, on described door lock axle, also twist-on has lock Jack panel, described locking nut is positioned at the rear side of power switch cabinet door leaf, the door lock axle of described locking nut rear end overlaps successively Being connected to the first bolt, door lock catch, the second bolt, door lock catch is fastened on door lock axle by described first bolt, the second bolt, Described door lock catch end is additionally provided with support chip away from the side of power switch cabinet door leaf, and the bottom of described support chip is tightened in door On lock shaft, and by the 3rd bolt fastening door lock shaft.

Preferably, described door lock catch is elastic steel sheet.

This preferred embodiment uses door lock catch to carry out door leaf locking, and is provided with support chip at the rear side of door lock catch, carries The high intensity of door lock catch, simple in construction, convenient install, make low cost, have a good application prospect.

Preferably, described door lock axle leading section is provided with end cap.

This preferred embodiment can effectively protect door lock.

Preferably, described iris identification device 1 includes image password data base 21, palm image acquisition module 22, palm Image pre-processing module 23, palm image characteristics extraction module 24 and palm characteristics of image identification module 25；Described image password Data base 21 is for prestoring the palm characteristics of image as image password that user sets；Described palm image acquisition module 22 for including palm palmmprint dominant line information by single collecting device collection and palm is quiet under 800nm near infrared light The palm image of arteries and veins information；Described palm image pre-processing module 23 is used for the palm image collected is carried out pretreatment, with Eliminate and gather the impact that in palm image process, palm rotates, translates, and position the effective coverage of palm image characteristics extraction；Institute State palm image characteristics extraction module 24 for extracting the palm characteristics of image to be identified of pretreated palm image, and by institute State palm characteristics of image to be identified to be transported in described palm characteristics of image identification module 25 carry out feature identification；Described palm figure As feature recognition module 25 using in described palm characteristics of image to be identified and image password data base 21 as image password Palm characteristics of image contrasts, it determines palm characteristics of image to be identified with the described palm characteristics of image as image password is No unanimously.

This preferred embodiment is perfect iris identification device 1, uses palm characteristics of image as image password, the peace of system Full property is higher.

Preferably, the described palm image to collecting carries out pretreatment, including:

(1) palm image is carried out medium filtering process, after removing the system noise of palm image, build palm image Grey value histograms, palm image is carried out by the local minimum choosing predetermined gray value threshold range according to grey value histograms Binary conversion treatment；

(2) build four finger profile diagrams, extract forefinger and middle finger, nameless and little thumb in the palm image after binary conversion treatment Refer to anchor point at two, according to two anchor points, the palm image after binary conversion treatment is done rotation processing, to correct palm figure image position Put；At described two, anchor point is set as on forefinger lower boundary and the point of interface of middle finger coboundary and nameless lower boundary and little finger The point of interface on border, coordinate is followed successively by (v₁,μ₁)、(v₂,μ₂)；According to the anchor point calculating anglec of rotation:

$\mathrm{\θ}=\mathrm{\γ}arctan\frac{v_2-v_1}{{\mathrm{\μ}}_2-{\mathrm{\μ}}_1}$

In formula, γ is the Dynamic gene set, and span is set as [0.98,1.02]；

During θ ＞ 0, the palm image after binary conversion treatment is turned clockwise by the anglec of rotation calculated, during θ ＜ 0, Palm image after binary conversion treatment is rotated, during θ=0, not to binary conversion treatment counterclockwise by the anglec of rotation calculated After palm image do any rotation.

(3) from the palm image after correction, extract suitable centre of the palm reference point, set up a reference frame, location The effective coverage of palm image characteristics extraction；Select near remaining four border circular areas referring to root referred in addition to thumb as fixed The effective coverage of position palm image characteristics extraction, selects the center of circle of described border circular areas as centre of the palm reference point；Described circle Territory is carried out really by the finger root point referring to root point, middle finger and the third finger and the nameless finger root point with little finger of forefinger with middle finger Fixed, particularly as follows:

1) palm contours extract is carried out: using pixel each in palm image as central pixel point, calculate center respectively Pixel and the gray scale difference of 8 neighborhood territory pixel points, when central pixel point is positioned on palm profile, it is positioned at vertical palm profile Point outer on direction will be for maximum, by the pole of pixel gray scale difference each in judging regional area with central pixel point gray scale difference Big value finds the real palm profile point in palm image, so that it is determined that palm profile；

2) fingertip location of forefinger, middle finger, the third finger and little finger is determined: finger tip direction is defined as the side of palm To, Fingers to the right, determines the fingertip location of forefinger, middle finger, the third finger and little finger, the fingertip location position of wherein said middle finger Low order end in whole profile；

3) forefinger is extracted with middle finger, middle finger with the nameless and nameless finger root point with little finger: set up objective contour Parametrization equation: for given objective contour L (t), its arc length parameterized equation is expressed as L (t)=(x (t), y (t)), Wherein x (t) and y (t) represents the coordinate of profile point respectively, and t represents the parameter of contour curve equation, and t ∈ [0,1]；

Calculate curvature k (t) of contour curve, from middle fingertip, extend to both sides, first extended to forefinger direction The point that individual Curvature varying is big, is designated as S₁, it is the seam points of forefinger and middle finger；First curvature extended to nameless direction becomes Change big point, be designated as W₁, it is middle finger and nameless seam points；Continue to extend and obtain second big point of Curvature varying, note For W₂, it is the nameless seam points with little finger；The point that described Curvature varying is big, refers to its curvature value and previous curvature value difference Point more than 2；

From a S₁Set out, it is assumed that webs line any pixel point P₁, find its and and P vertical with webs direction₁Two pictures of distance 2 P that element is wide₂And P₃, calculate P respectively₁With P₂、P₃Grad, using two Grad and SUM as evaluate P₁Vertically Graded amount on webs direction, when SUM changes greatly, former point is forefinger and refers to root point Q with middle finger₁；In like manner, middle finger and nothing Name refers to root point Q₂, nameless refer to root point Q with little finger₃；Described SUM changes greatly, refers to that its changing value is more than 2；

4) extraction refers to that root is round: junction point Q₁And Q₂, Q₂And Q₃, cross Q respectively₁ Q₂And Q₂Q₃Make perpendicular bisector, intersect at (m n), is the center of circle of required border circular areas, O point and Q to some O₁Distance is the radius R of required border circular areas.

This preferred embodiment carries out medium filtering process to palm image, it is to avoid the noise spot of palm image causes image fixed Position inaccurate, then carries out binary conversion treatment to palm image, so that the palm area in palm image and background area Preferably separate；The position of palm image is carried out rotation correction process, decreases the rotation of introducing in image acquisition process, put down The impact of the factors such as shifting, proportional zoom；By extracting suitable reference point, set up new reference frame, position palm figure Effective coverage as feature extraction, it is possible to reduce the difficulty of palm characteristics of image identification, improve the robust of match cognization algorithm Property.

Preferably, the palm characteristics of image to be identified of described extraction pretreated palm image, including:

(1) using the bifurcation of the palm vein in pretreated palm image and palmmprint main line as palm figure to be identified Each characteristic point F as feature_i(x, y), i=1,2 ... N, wherein N is characterized a number；By characteristic point to described border circular areas The ratio of the diameter of the distance in the center of circle and described border circular areas is as fisrt feature:

$Y_i=\frac{\sqrt{{(x_i-m)}^2+{(y_i-n)}^2}}{2R}$

In formula, Y_iRepresent the fisrt feature of ith feature point, (x_i,y_i) represent ith feature point coordinate；

The center of circle of described border circular areas is referred to root point Q with middle finger and the third finger₂Line as datum line, datum line direction Be 0 degree, the line in characteristic point and the center of circle clockwise to the angle folded by datum line as second feature；

In formula, E_iRepresent the second feature of ith feature point, E_iSpan be 0 to 360 degree, (x_i,y_i) represent i-th The coordinate of individual characteristic point；

(2) using the fisrt feature of characteristic point as abscissa, second feature, as vertical coordinate, constructs coordinate system, by described Palm vein and palmmprint main line bifurcation project in coordinate system, and the two-dimensional feature vector setting up pretreated palm image is empty Between.

This preferred embodiment selects palm vein and palmmprint main line bifurcation as each spy of palm characteristics of image to be identified Levy a little, both considered the memory space of iris identification device 1 and the restriction of the speed of service, reflect again palm vein and palmmprint Change, the palm characteristics of image degree of accuracy to be identified of extraction is high, and extraction rate is fast.

Preferably, described palm characteristics of image identification module 25 is by described palm characteristics of image to be identified and image password number When contrasting according to the palm characteristics of image as image password in storehouse 21, by the two dimensional character of palm characteristics of image to be identified Vector space and the described distribution as the characteristic point in the two-dimensional feature vector space in the palm characteristics of image of image password Carry out similarity comparison, particularly as follows: set the characteristic point in the two-dimensional feature vector space contrasting palm characteristics of image to be identified as treating Identifying characteristic point, described is standard as the characteristic point in the two-dimensional feature vector space in the palm characteristics of image of image password Characteristic point, carries out overlapping by palm image to be identified with the palm image in image password data base 21, and described as figure The standard feature point corresponding to characteristic point to be identified is determined in the two-dimensional feature vector space in the palm characteristics of image of password, Judge that characteristic point to be identified is less than predeterminable range threshold value and true according to judged result with the distance of corresponding standard feature point Fixed palm characteristics of image to be identified is the most consistent with the described palm characteristics of image as image password.

This preferred embodiment sets palm characteristics of image identification module 25 and is identified palm characteristics of image to be identified Time concrete operations, practical convenient.

This application scene Dynamic gene γ value to setting is as 0.98, and the accuracy of identification of door lock improves 5% relatively, knows Other speed improves 8% relatively.

Application scenarios 2

See Fig. 1, Fig. 2, a kind of door lock being identified by palm of an embodiment in this application scene, including Door lock and the hand identification device being connected with door lock, is characterized in that, described door lock includes: door lock axle, the front end of described door lock axle Extending power switch cabinet door leaf, be provided with key hole in the leading section of described door lock axle, on described door lock axle, also twist-on has lock Jack panel, described locking nut is positioned at the rear side of power switch cabinet door leaf, the door lock axle of described locking nut rear end overlaps successively Being connected to the first bolt, door lock catch, the second bolt, door lock catch is fastened on door lock axle by described first bolt, the second bolt, Described door lock catch end is additionally provided with support chip away from the side of power switch cabinet door leaf, and the bottom of described support chip is tightened in door On lock shaft, and by the 3rd bolt fastening door lock shaft.

Preferably, described door lock catch is elastic steel sheet.

This preferred embodiment uses door lock catch to carry out door leaf locking, and is provided with support chip at the rear side of door lock catch, carries The high intensity of door lock catch, simple in construction, convenient install, make low cost, have a good application prospect.

Preferably, described door lock axle leading section is provided with end cap.

This preferred embodiment can effectively protect door lock.

Preferably, described iris identification device 1 includes image password data base 21, palm image acquisition module 22, palm Image pre-processing module 23, palm image characteristics extraction module 24 and palm characteristics of image identification module 25；Described image password Data base 21 is for prestoring the palm characteristics of image as image password that user sets；Described palm image acquisition module 22 for including palm palmmprint dominant line information by single collecting device collection and palm is quiet under 800nm near infrared light The palm image of arteries and veins information；Described palm image pre-processing module 23 is used for the palm image collected is carried out pretreatment, with Eliminate and gather the impact that in palm image process, palm rotates, translates, and position the effective coverage of palm image characteristics extraction；Institute State palm image characteristics extraction module 24 for extracting the palm characteristics of image to be identified of pretreated palm image, and by institute State palm characteristics of image to be identified to be transported in described palm characteristics of image identification module 25 carry out feature identification；Described palm figure As feature recognition module 25 using in described palm characteristics of image to be identified and image password data base 21 as image password Palm characteristics of image contrasts, it determines palm characteristics of image to be identified with the described palm characteristics of image as image password is No unanimously.

This preferred embodiment is perfect iris identification device 1, uses palm characteristics of image as image password, the peace of system Full property is higher.

Preferably, the described palm image to collecting carries out pretreatment, including:

(1) palm image is carried out medium filtering process, after removing the system noise of palm image, build palm image Grey value histograms, palm image is carried out by the local minimum choosing predetermined gray value threshold range according to grey value histograms Binary conversion treatment；

(2) build four finger profile diagrams, extract forefinger and middle finger, nameless and little thumb in the palm image after binary conversion treatment Refer to anchor point at two, according to two anchor points, the palm image after binary conversion treatment is done rotation processing, to correct palm figure image position Put；At described two, anchor point is set as on forefinger lower boundary and the point of interface of middle finger coboundary and nameless lower boundary and little finger The point of interface on border, coordinate is followed successively by (v₁,μ₁)、(v₂,μ₂)；According to the anchor point calculating anglec of rotation:

$\mathrm{\θ}=\mathrm{\γ}arctan\frac{v_2-v_1}{{\mathrm{\μ}}_2-{\mathrm{\μ}}_1}$

In formula, γ is the Dynamic gene set, and span is set as [0.98,1.02]；

During θ ＞ 0, the palm image after binary conversion treatment is turned clockwise by the anglec of rotation calculated, during θ ＜ 0, Palm image after binary conversion treatment is rotated, during θ=0, not to binary conversion treatment counterclockwise by the anglec of rotation calculated After palm image do any rotation.

(3) from the palm image after correction, extract suitable centre of the palm reference point, set up a reference frame, location The effective coverage of palm image characteristics extraction；Select near remaining four border circular areas referring to root referred in addition to thumb as fixed The effective coverage of position palm image characteristics extraction, selects the center of circle of described border circular areas as centre of the palm reference point；Described circle Territory is carried out really by the finger root point referring to root point, middle finger and the third finger and the nameless finger root point with little finger of forefinger with middle finger Fixed, particularly as follows:

1) palm contours extract is carried out: using pixel each in palm image as central pixel point, calculate center respectively Pixel and the gray scale difference of 8 neighborhood territory pixel points, when central pixel point is positioned on palm profile, it is positioned at vertical palm profile Point outer on direction will be for maximum, by the pole of pixel gray scale difference each in judging regional area with central pixel point gray scale difference Big value finds the real palm profile point in palm image, so that it is determined that palm profile；

2) fingertip location of forefinger, middle finger, the third finger and little finger is determined: finger tip direction is defined as the side of palm To, Fingers to the right, determines the fingertip location of forefinger, middle finger, the third finger and little finger, the fingertip location position of wherein said middle finger Low order end in whole profile；

3) forefinger is extracted with middle finger, middle finger with the nameless and nameless finger root point with little finger: set up objective contour Parametrization equation: for given objective contour L (t), its arc length parameterized equation is expressed as L (t)=(x (t), y (t)), Wherein x (t) and y (t) represents the coordinate of profile point respectively, and t represents the parameter of contour curve equation, and t ∈ [0,1]；

Calculate curvature k (t) of contour curve, from middle fingertip, extend to both sides, first extended to forefinger direction The point that individual Curvature varying is big, is designated as S₁, it is the seam points of forefinger and middle finger；First curvature extended to nameless direction becomes Change big point, be designated as W₁, it is middle finger and nameless seam points；Continue to extend and obtain second big point of Curvature varying, note For W₂, it is the nameless seam points with little finger；The point that described Curvature varying is big, refers to its curvature value and previous curvature value difference Point more than 2；

From a S₁Set out, it is assumed that webs line any pixel point P₁, find its and and P vertical with webs direction₁Two pictures of distance 2 P that element is wide₂And P₃, calculate P respectively₁With P₂、P₃Grad, using two Grad and SUM as evaluate P₁Vertically Graded amount on webs direction, when SUM changes greatly, former point is forefinger and refers to root point Q with middle finger₁；In like manner, middle finger and nothing Name refers to root point Q₂, nameless refer to root point Q with little finger₃；Described SUM changes greatly, refers to that its changing value is more than 2；

4) extraction refers to that root is round: junction point Q₁And Q₂, Q₂And Q₃, cross Q respectively₁ Q₂And Q₂Q₃Make perpendicular bisector, intersect at (m n), is the center of circle of required border circular areas, O point and Q to some O₁Distance is the radius R of required border circular areas.

This preferred embodiment carries out medium filtering process to palm image, it is to avoid the noise spot of palm image causes image fixed Position inaccurate, then carries out binary conversion treatment to palm image, so that the palm area in palm image and background area Preferably separate；The position of palm image is carried out rotation correction process, decreases the rotation of introducing in image acquisition process, put down The impact of the factors such as shifting, proportional zoom；By extracting suitable reference point, set up new reference frame, position palm figure Effective coverage as feature extraction, it is possible to reduce the difficulty of palm characteristics of image identification, improve the robust of match cognization algorithm Property.

Preferably, the palm characteristics of image to be identified of described extraction pretreated palm image, including:

(1) using the bifurcation of the palm vein in pretreated palm image and palmmprint main line as palm figure to be identified Each characteristic point F as feature_i(x, y), i=1,2 ... N, wherein N is characterized a number；By characteristic point to described border circular areas The ratio of the diameter of the distance in the center of circle and described border circular areas is as fisrt feature:

$Y_i=\frac{\sqrt{{(x_i-m)}^2+{(y_i-n)}^2}}{2R}$

In formula, Y_iRepresent the fisrt feature of ith feature point, (x_i,y_i) represent ith feature point coordinate；

The center of circle of described border circular areas is referred to root point Q with middle finger and the third finger₂Line as datum line, datum line direction Be 0 degree, the line in characteristic point and the center of circle clockwise to the angle folded by datum line as second feature；

In formula, E_iRepresent the second feature of ith feature point, E_iSpan be 0 to 360 degree, (x_i,y_i) represent i-th The coordinate of individual characteristic point；

(2) using the fisrt feature of characteristic point as abscissa, second feature, as vertical coordinate, constructs coordinate system, by described Palm vein and palmmprint main line bifurcation project in coordinate system, and the two-dimensional feature vector setting up pretreated palm image is empty Between.

This preferred embodiment selects palm vein and palmmprint main line bifurcation as each spy of palm characteristics of image to be identified Levy a little, both considered the memory space of iris identification device 1 and the restriction of the speed of service, reflect again palm vein and palmmprint Change, the palm characteristics of image degree of accuracy to be identified of extraction is high, and extraction rate is fast.

Preferably, described palm characteristics of image identification module 25 is by described palm characteristics of image to be identified and image password number When contrasting according to the palm characteristics of image as image password in storehouse 21, by the two dimensional character of palm characteristics of image to be identified Vector space and the described distribution as the characteristic point in the two-dimensional feature vector space in the palm characteristics of image of image password Carry out similarity comparison, particularly as follows: set the characteristic point in the two-dimensional feature vector space contrasting palm characteristics of image to be identified as treating Identifying characteristic point, described is standard as the characteristic point in the two-dimensional feature vector space in the palm characteristics of image of image password Characteristic point, carries out overlapping by palm image to be identified with the palm image in image password data base 21, and described as figure The standard feature point corresponding to characteristic point to be identified is determined in the two-dimensional feature vector space in the palm characteristics of image of password, Judge that characteristic point to be identified is less than predeterminable range threshold value and true according to judged result with the distance of corresponding standard feature point Fixed palm characteristics of image to be identified is the most consistent with the described palm characteristics of image as image password.

This preferred embodiment sets palm characteristics of image identification module 25 and is identified palm characteristics of image to be identified Time concrete operations, practical convenient.

This application scene Dynamic gene γ value to setting is as 0.99, and the accuracy of identification of door lock improves 4.5% relatively, Recognition speed improves 7.6% relatively.

Application scenarios 3

See Fig. 1, Fig. 2, a kind of door lock being identified by palm of an embodiment in this application scene, including Door lock and the hand identification device being connected with door lock, is characterized in that, described door lock includes: door lock axle, the front end of described door lock axle Extending power switch cabinet door leaf, be provided with key hole in the leading section of described door lock axle, on described door lock axle, also twist-on has lock Jack panel, described locking nut is positioned at the rear side of power switch cabinet door leaf, the door lock axle of described locking nut rear end overlaps successively Being connected to the first bolt, door lock catch, the second bolt, door lock catch is fastened on door lock axle by described first bolt, the second bolt, Described door lock catch end is additionally provided with support chip away from the side of power switch cabinet door leaf, and the bottom of described support chip is tightened in door On lock shaft, and by the 3rd bolt fastening door lock shaft.

Preferably, described door lock catch is elastic steel sheet.

This preferred embodiment uses door lock catch to carry out door leaf locking, and is provided with support chip at the rear side of door lock catch, carries The high intensity of door lock catch, simple in construction, convenient install, make low cost, have a good application prospect.

Preferably, described door lock axle leading section is provided with end cap.

This preferred embodiment can effectively protect door lock.

Preferably, described iris identification device 1 includes image password data base 21, palm image acquisition module 22, palm Image pre-processing module 23, palm image characteristics extraction module 24 and palm characteristics of image identification module 25；Described image password Data base 21 is for prestoring the palm characteristics of image as image password that user sets；Described palm image acquisition module 22 for including palm palmmprint dominant line information by single collecting device collection and palm is quiet under 800nm near infrared light The palm image of arteries and veins information；Described palm image pre-processing module 23 is used for the palm image collected is carried out pretreatment, with Eliminate and gather the impact that in palm image process, palm rotates, translates, and position the effective coverage of palm image characteristics extraction；Institute State palm image characteristics extraction module 24 for extracting the palm characteristics of image to be identified of pretreated palm image, and by institute State palm characteristics of image to be identified to be transported in described palm characteristics of image identification module 25 carry out feature identification；Described palm figure As feature recognition module 25 using in described palm characteristics of image to be identified and image password data base 21 as image password Palm characteristics of image contrasts, it determines palm characteristics of image to be identified with the described palm characteristics of image as image password is No unanimously.

This preferred embodiment is perfect iris identification device 1, uses palm characteristics of image as image password, the peace of system Full property is higher.

Preferably, the described palm image to collecting carries out pretreatment, including:

(1) palm image is carried out medium filtering process, after removing the system noise of palm image, build palm image Grey value histograms, palm image is carried out by the local minimum choosing predetermined gray value threshold range according to grey value histograms Binary conversion treatment；

(2) build four finger profile diagrams, extract forefinger and middle finger, nameless and little thumb in the palm image after binary conversion treatment Refer to anchor point at two, according to two anchor points, the palm image after binary conversion treatment is done rotation processing, to correct palm figure image position Put；At described two, anchor point is set as on forefinger lower boundary and the point of interface of middle finger coboundary and nameless lower boundary and little finger The point of interface on border, coordinate is followed successively by (v₁,μ₁)、(v₂,μ₂)；According to the anchor point calculating anglec of rotation:

$\mathrm{\θ}=\mathrm{\γ}arctan\frac{v_2-v_1}{{\mathrm{\μ}}_2-{\mathrm{\μ}}_1}$

In formula, γ is the Dynamic gene set, and span is set as [0.98,1.02]；

During θ ＞ 0, the palm image after binary conversion treatment is turned clockwise by the anglec of rotation calculated, during θ ＜ 0, Palm image after binary conversion treatment is rotated, during θ=0, not to binary conversion treatment counterclockwise by the anglec of rotation calculated After palm image do any rotation.

(3) from the palm image after correction, extract suitable centre of the palm reference point, set up a reference frame, location The effective coverage of palm image characteristics extraction；Select near remaining four border circular areas referring to root referred in addition to thumb as fixed The effective coverage of position palm image characteristics extraction, selects the center of circle of described border circular areas as centre of the palm reference point；Described circle Territory is carried out really by the finger root point referring to root point, middle finger and the third finger and the nameless finger root point with little finger of forefinger with middle finger Fixed, particularly as follows:

1) palm contours extract is carried out: using pixel each in palm image as central pixel point, calculate center respectively Pixel and the gray scale difference of 8 neighborhood territory pixel points, when central pixel point is positioned on palm profile, it is positioned at vertical palm profile Point outer on direction will be for maximum, by the pole of pixel gray scale difference each in judging regional area with central pixel point gray scale difference Big value finds the real palm profile point in palm image, so that it is determined that palm profile；

2) fingertip location of forefinger, middle finger, the third finger and little finger is determined: finger tip direction is defined as the side of palm To, Fingers to the right, determines the fingertip location of forefinger, middle finger, the third finger and little finger, the fingertip location position of wherein said middle finger Low order end in whole profile；

3) forefinger is extracted with middle finger, middle finger with the nameless and nameless finger root point with little finger: set up objective contour Parametrization equation: for given objective contour L (t), its arc length parameterized equation is expressed as L (t)=(x (t), y (t)), Wherein x (t) and y (t) represents the coordinate of profile point respectively, and t represents the parameter of contour curve equation, and t ∈ [0,1]；

Calculate curvature k (t) of contour curve, from middle fingertip, extend to both sides, first extended to forefinger direction The point that individual Curvature varying is big, is designated as S₁, it is the seam points of forefinger and middle finger；First curvature extended to nameless direction becomes Change big point, be designated as W₁, it is middle finger and nameless seam points；Continue to extend and obtain second big point of Curvature varying, note For W₂, it is the nameless seam points with little finger；The point that described Curvature varying is big, refers to its curvature value and previous curvature value difference Point more than 2；

From a S₁Set out, it is assumed that webs line any pixel point P₁, find its and and P vertical with webs direction₁Two pictures of distance 2 P that element is wide₂And P₃, calculate P respectively₁With P₂、P₃Grad, using two Grad and SUM as evaluate P₁Vertically Graded amount on webs direction, when SUM changes greatly, former point is forefinger and refers to root point Q with middle finger₁；In like manner, middle finger and nothing Name refers to root point Q₂, nameless refer to root point Q with little finger₃；Described SUM changes greatly, refers to that its changing value is more than 2；

4) extraction refers to that root is round: junction point Q₁And Q₂, Q₂And Q₃, cross Q respectively₁ Q₂And Q₂Q₃Make perpendicular bisector, intersect at (m n), is the center of circle of required border circular areas, O point and Q to some O₁Distance is the radius R of required border circular areas.

This preferred embodiment carries out medium filtering process to palm image, it is to avoid the noise spot of palm image causes image fixed Position inaccurate, then carries out binary conversion treatment to palm image, so that the palm area in palm image and background area Preferably separate；The position of palm image is carried out rotation correction process, decreases the rotation of introducing in image acquisition process, put down The impact of the factors such as shifting, proportional zoom；By extracting suitable reference point, set up new reference frame, position palm figure Effective coverage as feature extraction, it is possible to reduce the difficulty of palm characteristics of image identification, improve the robust of match cognization algorithm Property.

Preferably, the palm characteristics of image to be identified of described extraction pretreated palm image, including:

(1) using the bifurcation of the palm vein in pretreated palm image and palmmprint main line as palm figure to be identified Each characteristic point F as feature_i(x, y), i=1,2 ... N, wherein N is characterized a number；By characteristic point to described border circular areas The ratio of the diameter of the distance in the center of circle and described border circular areas is as fisrt feature:

$Y_i=\frac{\sqrt{{(x_i-m)}^2+{(y_i-n)}^2}}{2R}$

In formula, Y_iRepresent the fisrt feature of ith feature point, (x_i,y_i) represent ith feature point coordinate；

The center of circle of described border circular areas is referred to root point Q with middle finger and the third finger₂Line as datum line, datum line direction Be 0 degree, the line in characteristic point and the center of circle clockwise to the angle folded by datum line as second feature；

In formula, E_iRepresent the second feature of ith feature point, E_iSpan be 0 to 360 degree, (x_i,y_i) represent i-th The coordinate of individual characteristic point；

(2) using the fisrt feature of characteristic point as abscissa, second feature, as vertical coordinate, constructs coordinate system, by described Palm vein and palmmprint main line bifurcation project in coordinate system, and the two-dimensional feature vector setting up pretreated palm image is empty Between.

This preferred embodiment selects palm vein and palmmprint main line bifurcation as each spy of palm characteristics of image to be identified Levy a little, both considered the memory space of iris identification device 1 and the restriction of the speed of service, reflect again palm vein and palmmprint Change, the palm characteristics of image degree of accuracy to be identified of extraction is high, and extraction rate is fast.

Preferably, described palm characteristics of image identification module 25 is by described palm characteristics of image to be identified and image password number When contrasting according to the palm characteristics of image as image password in storehouse 21, by the two dimensional character of palm characteristics of image to be identified Vector space and the described distribution as the characteristic point in the two-dimensional feature vector space in the palm characteristics of image of image password Carry out similarity comparison, particularly as follows: set the characteristic point in the two-dimensional feature vector space contrasting palm characteristics of image to be identified as treating Identifying characteristic point, described is standard as the characteristic point in the two-dimensional feature vector space in the palm characteristics of image of image password Characteristic point, carries out overlapping by palm image to be identified with the palm image in image password data base 21, and described as figure The standard feature point corresponding to characteristic point to be identified is determined in the two-dimensional feature vector space in the palm characteristics of image of password, Judge that characteristic point to be identified is less than predeterminable range threshold value and true according to judged result with the distance of corresponding standard feature point Fixed palm characteristics of image to be identified is the most consistent with the described palm characteristics of image as image password.

This preferred embodiment sets palm characteristics of image identification module 25 and is identified palm characteristics of image to be identified Time concrete operations, practical convenient.

This application scene Dynamic gene γ value to setting is as 1.00, and the accuracy of identification of door lock improves 6% relatively, knows Other speed improves 8.5% relatively.

Application scenarios 4

See Fig. 1, Fig. 2, a kind of door lock being identified by palm of an embodiment in this application scene, including Door lock and the hand identification device being connected with door lock, is characterized in that, described door lock includes: door lock axle, the front end of described door lock axle Extending power switch cabinet door leaf, be provided with key hole in the leading section of described door lock axle, on described door lock axle, also twist-on has lock Jack panel, described locking nut is positioned at the rear side of power switch cabinet door leaf, the door lock axle of described locking nut rear end overlaps successively Being connected to the first bolt, door lock catch, the second bolt, door lock catch is fastened on door lock axle by described first bolt, the second bolt, Described door lock catch end is additionally provided with support chip away from the side of power switch cabinet door leaf, and the bottom of described support chip is tightened in door On lock shaft, and by the 3rd bolt fastening door lock shaft.

Preferably, described door lock catch is elastic steel sheet.

This preferred embodiment uses door lock catch to carry out door leaf locking, and is provided with support chip at the rear side of door lock catch, carries The high intensity of door lock catch, simple in construction, convenient install, make low cost, have a good application prospect.

Preferably, described door lock axle leading section is provided with end cap.

This preferred embodiment can effectively protect door lock.

Preferably, described iris identification device 1 includes image password data base 21, palm image acquisition module 22, palm Image pre-processing module 23, palm image characteristics extraction module 24 and palm characteristics of image identification module 25；Described image password Data base 21 is for prestoring the palm characteristics of image as image password that user sets；Described palm image acquisition module 22 for including palm palmmprint dominant line information by single collecting device collection and palm is quiet under 800nm near infrared light The palm image of arteries and veins information；Described palm image pre-processing module 23 is used for the palm image collected is carried out pretreatment, with Eliminate and gather the impact that in palm image process, palm rotates, translates, and position the effective coverage of palm image characteristics extraction；Institute State palm image characteristics extraction module 24 for extracting the palm characteristics of image to be identified of pretreated palm image, and by institute State palm characteristics of image to be identified to be transported in described palm characteristics of image identification module 25 carry out feature identification；Described palm figure As feature recognition module 25 using in described palm characteristics of image to be identified and image password data base 21 as image password Palm characteristics of image contrasts, it determines palm characteristics of image to be identified with the described palm characteristics of image as image password is No unanimously.

This preferred embodiment is perfect iris identification device 1, uses palm characteristics of image as image password, the peace of system Full property is higher.

Preferably, the described palm image to collecting carries out pretreatment, including:

(1) palm image is carried out medium filtering process, after removing the system noise of palm image, build palm image Grey value histograms, palm image is carried out by the local minimum choosing predetermined gray value threshold range according to grey value histograms Binary conversion treatment；

(2) build four finger profile diagrams, extract forefinger and middle finger, nameless and little thumb in the palm image after binary conversion treatment Refer to anchor point at two, according to two anchor points, the palm image after binary conversion treatment is done rotation processing, to correct palm figure image position Put；At described two, anchor point is set as on forefinger lower boundary and the point of interface of middle finger coboundary and nameless lower boundary and little finger The point of interface on border, coordinate is followed successively by (v₁,μ1)、(v₂,μ2)；According to the anchor point calculating anglec of rotation:

$\mathrm{\θ}=\mathrm{\γ}arctan\frac{v_2-v_1}{{\mathrm{\μ}}_2-{\mathrm{\μ}}_1}$

In formula, γ is the Dynamic gene set, and span is set as [0.98,1.02]；

During θ ＞ 0, the palm image after binary conversion treatment is turned clockwise by the anglec of rotation calculated, during θ ＜ 0, Palm image after binary conversion treatment is rotated, during θ=0, not to binary conversion treatment counterclockwise by the anglec of rotation calculated After palm image do any rotation.

(3) from the palm image after correction, extract suitable centre of the palm reference point, set up a reference frame, location The effective coverage of palm image characteristics extraction；Select near remaining four border circular areas referring to root referred in addition to thumb as fixed The effective coverage of position palm image characteristics extraction, selects the center of circle of described border circular areas as centre of the palm reference point；Described circle Territory is carried out really by the finger root point referring to root point, middle finger and the third finger and the nameless finger root point with little finger of forefinger with middle finger Fixed, particularly as follows:

1) palm contours extract is carried out: using pixel each in palm image as central pixel point, calculate center respectively Pixel and the gray scale difference of 8 neighborhood territory pixel points, when central pixel point is positioned on palm profile, it is positioned at vertical palm profile Point outer on direction will be for maximum, by the pole of pixel gray scale difference each in judging regional area with central pixel point gray scale difference Big value finds the real palm profile point in palm image, so that it is determined that palm profile；

2) fingertip location of forefinger, middle finger, the third finger and little finger is determined: finger tip direction is defined as the side of palm To, Fingers to the right, determines the fingertip location of forefinger, middle finger, the third finger and little finger, the fingertip location position of wherein said middle finger Low order end in whole profile；

3) forefinger is extracted with middle finger, middle finger with the nameless and nameless finger root point with little finger: set up objective contour Parametrization equation: for given objective contour L (t), its arc length parameterized equation is expressed as L (t)=(x (t), y (t)), Wherein x (t) and y (t) represents the coordinate of profile point respectively, and t represents the parameter of contour curve equation, and t ∈ [0,1]；

Calculate curvature k (t) of contour curve, from middle fingertip, extend to both sides, first extended to forefinger direction The point that individual Curvature varying is big, is designated as S₁, it is the seam points of forefinger and middle finger；First curvature extended to nameless direction becomes Change big point, be designated as W₁, it is middle finger and nameless seam points；Continue to extend and obtain second big point of Curvature varying, note For W₂, it is the nameless seam points with little finger；The point that described Curvature varying is big, refers to its curvature value and previous curvature value difference Point more than 2；

From a S₁Set out, it is assumed that webs line any pixel point P₁, find its and and P vertical with webs direction₁Two pictures of distance 2 P that element is wide₂And P₃, calculate P respectively₁With P₂、P₃Grad, using two Grad and SUM as evaluate P₁Vertically Graded amount on webs direction, when SUM changes greatly, former point is forefinger and refers to root point Q with middle finger₁；In like manner, middle finger and nothing Name refers to root point Q₂, nameless refer to root point Q with little finger₃；Described SUM changes greatly, refers to that its changing value is more than 2；

4) extraction refers to that root is round: junction point Q₁And Q₂, Q₂And Q₃, cross Q respectively₁ Q₂And Q₂Q₃Make perpendicular bisector, intersect at (m n), is the center of circle of required border circular areas, O point and Q to some O₁Distance is the radius R of required border circular areas.

This preferred embodiment carries out medium filtering process to palm image, it is to avoid the noise spot of palm image causes image fixed Position inaccurate, then carries out binary conversion treatment to palm image, so that the palm area in palm image and background area Preferably separate；The position of palm image is carried out rotation correction process, decreases the rotation of introducing in image acquisition process, put down The impact of the factors such as shifting, proportional zoom；By extracting suitable reference point, set up new reference frame, position palm figure Effective coverage as feature extraction, it is possible to reduce the difficulty of palm characteristics of image identification, improve the robust of match cognization algorithm Property.

Preferably, the palm characteristics of image to be identified of described extraction pretreated palm image, including:

(1) using the bifurcation of the palm vein in pretreated palm image and palmmprint main line as palm figure to be identified Each characteristic point F as feature_i(x, y), i=1,2 ... N, wherein N is characterized a number；By characteristic point to described border circular areas The ratio of the diameter of the distance in the center of circle and described border circular areas is as fisrt feature:

$Y_i=\frac{\sqrt{{(x_i-m)}^2+{(y_i-n)}^2}}{2R}$

In formula, Y_iRepresent the fisrt feature of ith feature point, (x_i,y_i) represent ith feature point coordinate；

The center of circle of described border circular areas is referred to root point Q with middle finger and the third finger₂Line as datum line, datum line direction Be 0 degree, the line in characteristic point and the center of circle clockwise to the angle folded by datum line as second feature；

In formula, E_iRepresent the second feature of ith feature point, E_iSpan be 0 to 360 degree, (x_i,y_i) represent i-th The coordinate of individual characteristic point；

(2) using the fisrt feature of characteristic point as abscissa, second feature, as vertical coordinate, constructs coordinate system, by described Palm vein and palmmprint main line bifurcation project in coordinate system, and the two-dimensional feature vector setting up pretreated palm image is empty Between.

This preferred embodiment selects palm vein and palmmprint main line bifurcation as each spy of palm characteristics of image to be identified Levy a little, both considered the memory space of iris identification device 1 and the restriction of the speed of service, reflect again palm vein and palmmprint Change, the palm characteristics of image degree of accuracy to be identified of extraction is high, and extraction rate is fast.

Preferably, described palm characteristics of image identification module 25 is by described palm characteristics of image to be identified and image password number When contrasting according to the palm characteristics of image as image password in storehouse 21, by the two dimensional character of palm characteristics of image to be identified Vector space and the described distribution as the characteristic point in the two-dimensional feature vector space in the palm characteristics of image of image password Carry out similarity comparison, particularly as follows: set the characteristic point in the two-dimensional feature vector space contrasting palm characteristics of image to be identified as treating Identifying characteristic point, described is standard as the characteristic point in the two-dimensional feature vector space in the palm characteristics of image of image password Characteristic point, carries out overlapping by palm image to be identified with the palm image in image password data base 21, and described as figure The standard feature point corresponding to characteristic point to be identified is determined in the two-dimensional feature vector space in the palm characteristics of image of password, Judge that characteristic point to be identified is less than predeterminable range threshold value and true according to judged result with the distance of corresponding standard feature point Fixed palm characteristics of image to be identified is the most consistent with the described palm characteristics of image as image password.

This preferred embodiment sets palm characteristics of image identification module 25 and is identified palm characteristics of image to be identified Time concrete operations, practical convenient.

This application scene Dynamic gene γ value to setting is as 1.01, and the accuracy of identification of door lock improves 4.8% relatively, Recognition speed improves 7.5% relatively.

Application scenarios 5

See Fig. 1, Fig. 2, a kind of door lock being identified by palm of an embodiment in this application scene, including Door lock and the hand identification device being connected with door lock, is characterized in that, described door lock includes: door lock axle, the front end of described door lock axle Extending power switch cabinet door leaf, be provided with key hole in the leading section of described door lock axle, on described door lock axle, also twist-on has lock Jack panel, described locking nut is positioned at the rear side of power switch cabinet door leaf, the door lock axle of described locking nut rear end overlaps successively Being connected to the first bolt, door lock catch, the second bolt, door lock catch is fastened on door lock axle by described first bolt, the second bolt, Described door lock catch end is additionally provided with support chip away from the side of power switch cabinet door leaf, and the bottom of described support chip is tightened in door On lock shaft, and by the 3rd bolt fastening door lock shaft.

Preferably, described door lock catch is elastic steel sheet.

This preferred embodiment uses door lock catch to carry out door leaf locking, and is provided with support chip at the rear side of door lock catch, carries The high intensity of door lock catch, simple in construction, convenient install, make low cost, have a good application prospect.

Preferably, described door lock axle leading section is provided with end cap.

This preferred embodiment can effectively protect door lock.

Preferably, described iris identification device 1 includes image password data base 21, palm image acquisition module 22, palm Image pre-processing module 23, palm image characteristics extraction module 24 and palm characteristics of image identification module 25；Described image password Data base 21 is for prestoring the palm characteristics of image as image password that user sets；Described palm image acquisition module 22 for including palm palmmprint dominant line information by single collecting device collection and palm is quiet under 800nm near infrared light The palm image of arteries and veins information；Described palm image pre-processing module 23 is used for the palm image collected is carried out pretreatment, with Eliminate and gather the impact that in palm image process, palm rotates, translates, and position the effective coverage of palm image characteristics extraction；Institute State palm image characteristics extraction module 24 for extracting the palm characteristics of image to be identified of pretreated palm image, and by institute State palm characteristics of image to be identified to be transported in described palm characteristics of image identification module 25 carry out feature identification；Described palm figure As feature recognition module 25 using in described palm characteristics of image to be identified and image password data base 21 as image password Palm characteristics of image contrasts, it determines palm characteristics of image to be identified with the described palm characteristics of image as image password is No unanimously.

This preferred embodiment is perfect iris identification device 1, uses palm characteristics of image as image password, the peace of system Full property is higher.

Preferably, the described palm image to collecting carries out pretreatment, including:

(1) palm image is carried out medium filtering process, after removing the system noise of palm image, build palm image Grey value histograms, palm image is carried out by the local minimum choosing predetermined gray value threshold range according to grey value histograms Binary conversion treatment；

(2) build four finger profile diagrams, extract forefinger and middle finger, nameless and little thumb in the palm image after binary conversion treatment Refer to anchor point at two, according to two anchor points, the palm image after binary conversion treatment is done rotation processing, to correct palm figure image position Put；At described two, anchor point is set as on forefinger lower boundary and the point of interface of middle finger coboundary and nameless lower boundary and little finger The point of interface on border, coordinate is followed successively by (v₁,μ₁)、(v₂,μ₂)；According to the anchor point calculating anglec of rotation:

$\mathrm{\θ}=\mathrm{\γ}arctan\frac{v_2-v_1}{{\mathrm{\μ}}_2-{\mathrm{\μ}}_1}$

In formula, γ is the Dynamic gene set, and span is set as [0.98,1.02]；

During θ ＞ 0, the palm image after binary conversion treatment is turned clockwise by the anglec of rotation calculated, during θ ＜ 0, Palm image after binary conversion treatment is rotated, during θ=0, not to binary conversion treatment counterclockwise by the anglec of rotation calculated After palm image do any rotation.

(3) from the palm image after correction, extract suitable centre of the palm reference point, set up a reference frame, location The effective coverage of palm image characteristics extraction；Select near remaining four border circular areas referring to root referred in addition to thumb as fixed The effective coverage of position palm image characteristics extraction, selects the center of circle of described border circular areas as centre of the palm reference point；Described circle Territory is carried out really by the finger root point referring to root point, middle finger and the third finger and the nameless finger root point with little finger of forefinger with middle finger Fixed, particularly as follows:

1) palm contours extract is carried out: using pixel each in palm image as central pixel point, calculate center respectively Pixel and the gray scale difference of 8 neighborhood territory pixel points, when central pixel point is positioned on palm profile, it is positioned at vertical palm profile Point outer on direction will be for maximum, by the pole of pixel gray scale difference each in judging regional area with central pixel point gray scale difference Big value finds the real palm profile point in palm image, so that it is determined that palm profile；

2) fingertip location of forefinger, middle finger, the third finger and little finger is determined: finger tip direction is defined as the side of palm To, Fingers to the right, determines the fingertip location of forefinger, middle finger, the third finger and little finger, the fingertip location position of wherein said middle finger Low order end in whole profile；

3) forefinger is extracted with middle finger, middle finger with the nameless and nameless finger root point with little finger: set up objective contour Parametrization equation: for given objective contour L (t), its arc length parameterized equation is expressed as L (t)=(x (t), y (t)), Wherein x (t) and y (t) represents the coordinate of profile point respectively, and t represents the parameter of contour curve equation, and t ∈ [0,1]；

Calculate curvature k (t) of contour curve, from middle fingertip, extend to both sides, first extended to forefinger direction The point that individual Curvature varying is big, is designated as S₁, it is the seam points of forefinger and middle finger；First curvature extended to nameless direction becomes Change big point, be designated as W₁, it is middle finger and nameless seam points；Continue to extend and obtain second big point of Curvature varying, note For W₂, it is the nameless seam points with little finger；The point that described Curvature varying is big, refers to its curvature value and previous curvature value difference Point more than 2；

From a S₁Set out, it is assumed that webs line any pixel point P₁, find its and and P vertical with webs direction₁Two pictures of distance 2 P that element is wide₂And P₃, calculate P respectively₁With P₂、P₃Grad, using two Grad and SUM as evaluate P₁Vertically Graded amount on webs direction, when SUM changes greatly, former point is forefinger and refers to root point Q with middle finger₁；In like manner, middle finger and nothing Name refers to root point Q₂, nameless refer to root point Q with little finger₃；Described SUM changes greatly, refers to that its changing value is more than 2；

4) extraction refers to that root is round: junction point Q₁And Q₂, Q₂And Q₃, cross Q respectively₁ Q₂And Q₂Q₃Make perpendicular bisector, intersect at (m n), is the center of circle of required border circular areas, O point and Q to some O₁Distance is the radius R of required border circular areas.

This preferred embodiment carries out medium filtering process to palm image, it is to avoid the noise spot of palm image causes image fixed Position inaccurate, then carries out binary conversion treatment to palm image, so that the palm area in palm image and background area Preferably separate；The position of palm image is carried out rotation correction process, decreases the rotation of introducing in image acquisition process, put down The impact of the factors such as shifting, proportional zoom；By extracting suitable reference point, set up new reference frame, position palm figure Effective coverage as feature extraction, it is possible to reduce the difficulty of palm characteristics of image identification, improve the robust of match cognization algorithm Property.

Preferably, the palm characteristics of image to be identified of described extraction pretreated palm image, including:

(1) using the bifurcation of the palm vein in pretreated palm image and palmmprint main line as palm figure to be identified Each characteristic point F as feature_i(x, y), i=1,2 ... N, wherein N is characterized a number；By characteristic point to described border circular areas The ratio of the diameter of the distance in the center of circle and described border circular areas is as fisrt feature:

$Y_i=\frac{\sqrt{{(x_i-m)}^2+{(y_i-n)}^2}}{2R}$

In formula, Y_iRepresent the fisrt feature of ith feature point, (x_i,y_i) represent ith feature point coordinate；

The center of circle of described border circular areas is referred to root point Q with middle finger and the third finger₂Line as datum line, datum line direction Be 0 degree, the line in characteristic point and the center of circle clockwise to the angle folded by datum line as second feature；

In formula, E_iRepresent the second feature of ith feature point, E_iSpan be 0 to 360 degree, (x_i,y_i) represent i-th The coordinate of individual characteristic point；

(2) using the fisrt feature of characteristic point as abscissa, second feature, as vertical coordinate, constructs coordinate system, by described Palm vein and palmmprint main line bifurcation project in coordinate system, and the two-dimensional feature vector setting up pretreated palm image is empty Between.

This preferred embodiment selects palm vein and palmmprint main line bifurcation as each spy of palm characteristics of image to be identified Levy a little, both considered the memory space of iris identification device 1 and the restriction of the speed of service, reflect again palm vein and palmmprint Change, the palm characteristics of image degree of accuracy to be identified of extraction is high, and extraction rate is fast.

Preferably, described palm characteristics of image identification module 25 is by described palm characteristics of image to be identified and image password number When contrasting according to the palm characteristics of image as image password in storehouse 21, by the two dimensional character of palm characteristics of image to be identified Vector space and the described distribution as the characteristic point in the two-dimensional feature vector space in the palm characteristics of image of image password Carry out similarity comparison, particularly as follows: set the characteristic point in the two-dimensional feature vector space contrasting palm characteristics of image to be identified as treating Identifying characteristic point, described is standard as the characteristic point in the two-dimensional feature vector space in the palm characteristics of image of image password Characteristic point, carries out overlapping by palm image to be identified with the palm image in image password data base 21, and described as figure The standard feature point corresponding to characteristic point to be identified is determined in the two-dimensional feature vector space in the palm characteristics of image of password, Judge that characteristic point to be identified is less than predeterminable range threshold value and true according to judged result with the distance of corresponding standard feature point Fixed palm characteristics of image to be identified is the most consistent with the described palm characteristics of image as image password.

This preferred embodiment sets palm characteristics of image identification module 25 and is identified palm characteristics of image to be identified Time concrete operations, practical convenient.

This application scene Dynamic gene γ value to setting is as 1.02, and the accuracy of identification of door lock improves 5.2% relatively, Recognition speed improves 7% relatively.

Last it should be noted that, above example is only in order to illustrate technical scheme, rather than the present invention is protected Protecting the restriction of scope, although having made to explain to the present invention with reference to preferred embodiment, those of ordinary skill in the art should Work as understanding, technical scheme can be modified or equivalent, without deviating from the reality of technical solution of the present invention Matter and scope.

Claims (3)

1. the door lock being identified by palm, including door lock and the hand identification device that is connected with door lock, be is characterized in that, Described door lock includes: door lock axle, and power switch cabinet door leaf is extended in the front end of described door lock axle, in the leading section of described door lock axle Being provided with key hole, on described door lock axle, also twist-on has locking nut, after described locking nut is positioned at power switch cabinet door leaf Side, the door lock axle of described locking nut rear end is socketed with the first bolt, door lock catch, the second bolt, described first spiral shell successively Door lock catch is fastened on door lock axle by bolt, the second bolt, and described door lock catch end is away from the side of power switch cabinet door leaf Being additionally provided with support chip, the bottom of described support chip is tightened on door lock axle, and by the 3rd bolt fastening door lock shaft.

A kind of door lock being identified by palm the most according to claim 1, is characterized in that, described door lock catch is bullet Property steel disc.

A kind of door lock being identified by palm the most according to claim 2, be is characterized in that, described door lock axle leading section It is provided with end cap.