CN106296901A - A kind of electronic lock system based on hand identification - Google Patents

A kind of electronic lock system based on hand identification Download PDF

Info

Publication number
CN106296901A
CN106296901A CN201610621796.1A CN201610621796A CN106296901A CN 106296901 A CN106296901 A CN 106296901A CN 201610621796 A CN201610621796 A CN 201610621796A CN 106296901 A CN106296901 A CN 106296901A
Authority
CN
China
Prior art keywords
image
palm
point
password
finger
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN201610621796.1A
Other languages
Chinese (zh)
Inventor
孟玲
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Individual
Original Assignee
Individual
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Individual filed Critical Individual
Priority to CN201610621796.1A priority Critical patent/CN106296901A/en
Publication of CN106296901A publication Critical patent/CN106296901A/en
Pending legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G07—CHECKING-DEVICES
    • G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
    • G07C9/00—Individual registration on entry or exit
    • G07C9/00174—Electronically operated locks; Circuits therefor; Nonmechanical keys therefor, e.g. passive or active electrical keys or other data carriers without mechanical keys
    • G07C9/00563—Electronically operated locks; Circuits therefor; Nonmechanical keys therefor, e.g. passive or active electrical keys or other data carriers without mechanical keys using personal physical data of the operator, e.g. finger prints, retinal images, voicepatterns
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/12—Fingerprints or palmprints
    • G06V40/1347—Preprocessing; Feature extraction
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/12—Fingerprints or palmprints
    • G06V40/1365—Matching; Classification
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/14—Vascular patterns

Abstract

The invention provides a kind of electronic lock system based on hand identification, including image password identification device, fingerprint recognition alarm device and safety control, described image password identification device is used for identifying image password, and unlock instruction when identifying successfully to the transmission of described safety control, described safety control, for the unblock instruction according to the transmission of described image password identification device, is unlocked；Described fingerprint recognition alarm device is for judging whether to report to the police according to the fingerprint of input.The present invention arranges image password identification device and fingerprint recognition alarm device, improves safety and the accuracy of electronic lock identification of electronic lock.

Description

A kind of electronic lock system based on hand identification
Technical field
The present invention relates to smart lock field, be specifically related to a kind of electronic lock system based on hand identification.
Background technology
The electronic password lock with anti-theft alarm function replaces traditional mechanical code lock, overcomes mechanical code lock Number of password is few, the shortcoming of poor safety performance, makes coded lock technically or is all greatly improved a step in performance.Relevant In technology, biological characteristic formula electronic lock is relative to other electronic locks, and intelligent high, it is by the human body biological characteristics such as sound, fingerprint As Password Input, computer carry out pattern recognition and control to unblank.
Biological characteristic formula electronic lock many employings sound, fingerprint or iris are as Password Input, but based on sound or iris As Password Input, easily receive the emotion influence of people itself, thus reduce the accuracy of electronic lock identification, and use based on During the biological characteristic formula electronic lock of fingerprint, a big defect is exactly that fingerprint is easily replicated, so being that seat belt is great hidden Suffer from.Additionally, when user faces a danger and is forced to input electronic lock password, there is no the most hidden type of alarm.
Summary of the invention
For solving the problems referred to above, it is desirable to provide a kind of electronic lock system based on hand identification.
The purpose of the present invention realizes by the following technical solutions:
A kind of electronic lock system based on hand identification, including image password identification device, fingerprint recognition alarm device and Safety control, described image password identification device is used for identifying image password, and when identifying successfully to described safety Controlling device transmission and unlock instruction, described safety control is for referring to according to the unblock of described image password identification device transmission Order, is unlocked；Described fingerprint recognition alarm device is for judging whether to report to the police according to the fingerprint of input.
Preferably, described image password is the palm characteristics of image that user sets.
The invention have the benefit that and image password identification device and fingerprint recognition alarm device are set, improve electronics The safety of lock and the accuracy of electronic lock identification, solve above-mentioned technical problem.
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 the principle schematic of the present invention；
Fig. 2 is the structural representation of image password identification device 1 of the present invention.
Reference:
Image password identification device 1, safety control 2, fingerprint recognition alarm device 3, image password data base 21, hands The palm image capture 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
Seeing Fig. 1, Fig. 2, the electronic lock system based on hand identification of an embodiment in this application scene, including figure As apparatus for security code recognition 1, fingerprint recognition alarm device 3 and safety control 2, described image password identification device 1 is used for knowing Other image password, and unlock instruction when identifying successfully to the transmission of described safety control 2；Described safety control 2 For the unblock instruction transmitted according to described image password identification device 1, it is unlocked；Described fingerprint recognition alarm device 3 is used In judging whether to report to the police according to the fingerprint of input.
Preferably, described image password is the palm characteristics of image that user sets.
The above embodiment of the present invention arranges image password identification device 1 and fingerprint recognition alarm device 3, improves electronics The safety of lock and the accuracy of electronic lock identification, solve above-mentioned technical problem.
Preferably, after the fingerprint of input is successfully identified by described fingerprint recognition alarm device 3, it is judged that described user In the hole, send warning message to user nominator；Described fingerprint recognition alarm device 3 includes finger print acquisition module 31, fingerprint storage module 32 and Fingerprint Processing Module 33, described finger print acquisition module 31 is for gathering the to be identified of user's input Finger print information；Described Fingerprint Processing Module 33 is for storing described finger print information to be identified and described fingerprint storage module 32 Warning finger print information contrasts, if described finger print information to be identified is consistent with described warning finger print information, it is judged that institute State user in the hole, send warning message to user nominator.
The fingerprint recognition alarm device 3 of this preferred embodiment is relatively simple, and facing a danger user is forced to input electronic lock During password, can be reported to the police by input fingerprint, type of alarm is the most hidden, and safety is high.
Preferably, described image password identification device 1 include 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 database 21 is for prestoring the palm characteristics of image as image password that user sets；Described palm image acquisition Module 22 is for including palm palmmprint dominant line information and hands by single collecting device collection under 800nm near infrared light The palm image of vena metacarpea information；Described palm image pre-processing module 23 is for carrying out pre-place to the palm image collected Reason, gathers, to eliminate, the impact that in palm image process, palm rotates, translates, and positions effective district of palm image characteristics extraction Territory；Described palm image characteristics extraction module 24 is used for extracting the palm characteristics of image to be identified of pretreated palm image, And be transported in described palm characteristics of image identification module 25 carry out feature identification by described palm characteristics of image to be identified；Described Palm characteristics of image identification module 25 using in described palm characteristics of image to be identified and image password data base 21 as image The palm characteristics of image of password contrasts, it determines palm characteristics of image to be identified and the described palm image as image password Feature is the most consistent, if unanimously, sends to safety control 2 and unlocks instruction.
This preferred embodiment is perfect image password identification device 1, uses palm characteristics of image as image password, system Safety 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:
θ = γ a r c t a n v 2 - v 1 μ 2 - 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 featurei(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 = ( x i - m ) 2 + ( y i - n ) 2 2 R
In formula, YiRepresent the fisrt feature of ith feature point, (xi,yi) 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, EiRepresent the second feature of ith feature point, EiSpan be 0 to 360 degree, (xi,yi) 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 memory space and the restriction of the speed of service of image password identification device 1, reflected again palm vein and the palm The change of stricture of vagina, 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 electronic lock improves 5% relatively, Recognition speed improves 8% relatively.
Application scenarios 2
Seeing Fig. 1, Fig. 2, the electronic lock system based on hand identification of an embodiment in this application scene, including figure As apparatus for security code recognition 1, fingerprint recognition alarm device 3 and safety control 2, described image password identification device 1 is used for knowing Other image password, and unlock instruction when identifying successfully to the transmission of described safety control 2；Described safety control 2 For the unblock instruction transmitted according to described image password identification device 1, it is unlocked；Described fingerprint recognition alarm device 3 is used In judging whether to report to the police according to the fingerprint of input.
Preferably, described image password is the palm characteristics of image that user sets.
The above embodiment of the present invention arranges image password identification device 1 and fingerprint recognition alarm device 3, improves electronics The safety of lock and the accuracy of electronic lock identification, solve above-mentioned technical problem.
Preferably, described fingerprint recognition alarm device 3 includes at finger print acquisition module 31, fingerprint storage module 32 and fingerprint Reason module 33, described finger print acquisition module 31 is for gathering the finger print information to be identified of user's input；Described Fingerprint Processing Module 33 contrast for the warning finger print information storing described finger print information to be identified and described fingerprint storage module 32, if Described finger print information to be identified is consistent with described warning finger print information, it is judged that described user is in the hole, to user Nominator sends warning message.
The fingerprint recognition alarm device 3 of this preferred embodiment is relatively simple, and facing a danger user is forced to input electronic lock During password, can be reported to the police by input fingerprint, type of alarm is the most hidden, and safety is high.
Preferably, described image password identification device 1 include 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 database 21 is for prestoring the palm characteristics of image as image password that user sets；Described palm image acquisition Module 22 is for including palm palmmprint dominant line information and hands by single collecting device collection under 800nm near infrared light The palm image of vena metacarpea information；Described palm image pre-processing module 23 is for carrying out pre-place to the palm image collected Reason, gathers, to eliminate, the impact that in palm image process, palm rotates, translates, and positions effective district of palm image characteristics extraction Territory；Described palm image characteristics extraction module 24 is used for extracting the palm characteristics of image to be identified of pretreated palm image, And be transported in described palm characteristics of image identification module 25 carry out feature identification by described palm characteristics of image to be identified；Described Palm characteristics of image identification module 25 using in described palm characteristics of image to be identified and image password data base 21 as image The palm characteristics of image of password contrasts, it determines palm characteristics of image to be identified and the described palm image as image password Feature is the most consistent, if unanimously, sends to safety control 2 and unlocks instruction.
This preferred embodiment is perfect image password identification device 1, uses palm characteristics of image as image password, system Safety 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:
θ = γ a r c t a n v 2 - v 1 μ 2 - 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 featurei(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 = ( x i - m ) 2 + ( y i - n ) 2 2 R
In formula, YiRepresent the fisrt feature of ith feature point, (xi,yi) 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, EiRepresent the second feature of ith feature point, EiSpan be 0 to 360 degree, (xi,yi) 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 memory space and the restriction of the speed of service of image password identification device 1, reflected again palm vein and the palm The change of stricture of vagina, 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 electronic lock improves relatively 4.5%, recognition speed improves 7.6% relatively.
Application scenarios 3
Seeing Fig. 1, Fig. 2, the electronic lock system based on hand identification of an embodiment in this application scene, including figure As apparatus for security code recognition 1, fingerprint recognition alarm device 3 and safety control 2, described image password identification device 1 is used for knowing Other image password, and unlock instruction when identifying successfully to the transmission of described safety control 2；Described safety control 2 For the unblock instruction transmitted according to described image password identification device 1, it is unlocked；Described fingerprint recognition alarm device 3 is used In judging whether to report to the police according to the fingerprint of input.
Preferably, described image password is the palm characteristics of image that user sets.
The above embodiment of the present invention arranges image password identification device 1 and fingerprint recognition alarm device 3, improves electronics The safety of lock and the accuracy of electronic lock identification, solve above-mentioned technical problem.
Preferably, described fingerprint recognition alarm device 3 includes at finger print acquisition module 31, fingerprint storage module 32 and fingerprint Reason module 33, described finger print acquisition module 31 is for gathering the finger print information to be identified of user's input；Described Fingerprint Processing Module 33 contrast for the warning finger print information storing described finger print information to be identified and described fingerprint storage module 32, if Described finger print information to be identified is consistent with described warning finger print information, it is judged that described user is in the hole, to user Nominator sends warning message.
The fingerprint recognition alarm device 3 of this preferred embodiment is relatively simple, and facing a danger user is forced to input electronic lock During password, can be reported to the police by input fingerprint, type of alarm is the most hidden, and safety is high.
Preferably, described image password identification device 1 include 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 database 21 is for prestoring the palm characteristics of image as image password that user sets；Described palm image acquisition Module 22 is for including palm palmmprint dominant line information and hands by single collecting device collection under 800nm near infrared light The palm image of vena metacarpea information；Described palm image pre-processing module 23 is for carrying out pre-place to the palm image collected Reason, gathers, to eliminate, the impact that in palm image process, palm rotates, translates, and positions effective district of palm image characteristics extraction Territory；Described palm image characteristics extraction module 24 is used for extracting the palm characteristics of image to be identified of pretreated palm image, And be transported in described palm characteristics of image identification module 25 carry out feature identification by described palm characteristics of image to be identified；Described Palm characteristics of image identification module 25 using in described palm characteristics of image to be identified and image password data base 21 as image The palm characteristics of image of password contrasts, it determines palm characteristics of image to be identified and the described palm image as image password Feature is the most consistent, if unanimously, sends to safety control 2 and unlocks instruction.
This preferred embodiment is perfect image password identification device 1, uses palm characteristics of image as image password, system Safety 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:
θ = γ a r c t a n v 2 - v 1 μ 2 - 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 featurei(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 = ( x i - m ) 2 + ( y i - n ) 2 2 R
In formula, YiRepresent the fisrt feature of ith feature point, (xi,yi) 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, EiRepresent the second feature of ith feature point, EiSpan be 0 to 360 degree, (xi,yi) 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 memory space and the restriction of the speed of service of image password identification device 1, reflected again palm vein and the palm The change of stricture of vagina, 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 electronic lock improves 6% relatively, Recognition speed improves 8.5% relatively.
Application scenarios 4
Seeing Fig. 1, Fig. 2, the electronic lock system based on hand identification of an embodiment in this application scene, including figure As apparatus for security code recognition 1, fingerprint recognition alarm device 3 and safety control 2, described image password identification device 1 is used for knowing Other image password, and unlock instruction when identifying successfully to the transmission of described safety control 2；Described safety control 2 For the unblock instruction transmitted according to described image password identification device 1, it is unlocked；Described fingerprint recognition alarm device 3 is used In judging whether to report to the police according to the fingerprint of input.
Preferably, described image password is the palm characteristics of image that user sets.
The above embodiment of the present invention arranges image password identification device 1 and fingerprint recognition alarm device 3, improves electronics The safety of lock and the accuracy of electronic lock identification, solve above-mentioned technical problem.
Preferably, described fingerprint recognition alarm device 3 includes at finger print acquisition module 31, fingerprint storage module 32 and fingerprint Reason module 33, described finger print acquisition module 31 is for gathering the finger print information to be identified of user's input；Described Fingerprint Processing Module 33 contrast for the warning finger print information storing described finger print information to be identified and described fingerprint storage module 32, if Described finger print information to be identified is consistent with described warning finger print information, it is judged that described user is in the hole, to user Nominator sends warning message.
The fingerprint recognition alarm device 3 of this preferred embodiment is relatively simple, and facing a danger user is forced to input electronic lock During password, can be reported to the police by input fingerprint, type of alarm is the most hidden, and safety is high.
Preferably, described image password identification device 1 include 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 database 21 is for prestoring the palm characteristics of image as image password that user sets；Described palm image acquisition Module 22 is for including palm palmmprint dominant line information and hands by single collecting device collection under 800nm near infrared light The palm image of vena metacarpea information；Described palm image pre-processing module 23 is for carrying out pre-place to the palm image collected Reason, gathers, to eliminate, the impact that in palm image process, palm rotates, translates, and positions effective district of palm image characteristics extraction Territory；Described palm image characteristics extraction module 24 is used for extracting the palm characteristics of image to be identified of pretreated palm image, And be transported in described palm characteristics of image identification module 25 carry out feature identification by described palm characteristics of image to be identified；Described Palm characteristics of image identification module 25 using in described palm characteristics of image to be identified and image password data base 21 as image The palm characteristics of image of password contrasts, it determines palm characteristics of image to be identified and the described palm image as image password Feature is the most consistent, if unanimously, sends to safety control 2 and unlocks instruction.
This preferred embodiment is perfect image password identification device 1, uses palm characteristics of image as image password, system Safety 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:
θ = γ a r c t a n v 2 - v 1 μ 2 - 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 featurei(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 = ( x i - m ) 2 + ( y i - n ) 2 2 R
In formula, YiRepresent the fisrt feature of ith feature point, (xi,yi) 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, EiRepresent the second feature of ith feature point, EiSpan be 0 to 360 degree, (xi,yi) 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 memory space and the restriction of the speed of service of image password identification device 1, reflected again palm vein and the palm The change of stricture of vagina, 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 electronic lock improves relatively 4.8%, recognition speed improves 7.5% relatively.
Application scenarios 5
Seeing Fig. 1, Fig. 2, the electronic lock system based on hand identification of an embodiment in this application scene, including figure As apparatus for security code recognition 1, fingerprint recognition alarm device 3 and safety control 2, described image password identification device 1 is used for knowing Other image password, and unlock instruction when identifying successfully to the transmission of described safety control 2；Described safety control 2 For the unblock instruction transmitted according to described image password identification device 1, it is unlocked；Described fingerprint recognition alarm device 3 is used In judging whether to report to the police according to the fingerprint of input.
Preferably, described image password is the palm characteristics of image that user sets.
The above embodiment of the present invention arranges image password identification device 1 and fingerprint recognition alarm device 3, improves electronics The safety of lock and the accuracy of electronic lock identification, solve above-mentioned technical problem.
Preferably, described fingerprint recognition alarm device 3 includes at finger print acquisition module 31, fingerprint storage module 32 and fingerprint Reason module 33, described finger print acquisition module 31 is for gathering the finger print information to be identified of user's input；Described Fingerprint Processing Module 33 contrast for the warning finger print information storing described finger print information to be identified and described fingerprint storage module 32, if Described finger print information to be identified is consistent with described warning finger print information, it is judged that described user is in the hole, to user Nominator sends warning message.
The fingerprint recognition alarm device 3 of this preferred embodiment is relatively simple, and facing a danger user is forced to input electronic lock During password, can be reported to the police by input fingerprint, type of alarm is the most hidden, and safety is high.
Preferably, described image password identification device 1 include 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 database 21 is for prestoring the palm characteristics of image as image password that user sets；Described palm image acquisition Module 22 is for including palm palmmprint dominant line information and hands by single collecting device collection under 800nm near infrared light The palm image of vena metacarpea information；Described palm image pre-processing module 23 is for carrying out pre-place to the palm image collected Reason, gathers, to eliminate, the impact that in palm image process, palm rotates, translates, and positions effective district of palm image characteristics extraction Territory；Described palm image characteristics extraction module 24 is used for extracting the palm characteristics of image to be identified of pretreated palm image, And be transported in described palm characteristics of image identification module 25 carry out feature identification by described palm characteristics of image to be identified；Described Palm characteristics of image identification module 25 using in described palm characteristics of image to be identified and image password data base 21 as image The palm characteristics of image of password contrasts, it determines palm characteristics of image to be identified and the described palm image as image password Feature is the most consistent, if unanimously, sends to safety control 2 and unlocks instruction.
This preferred embodiment is perfect image password identification device 1, uses palm characteristics of image as image password, system Safety 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:
θ = γ a r c t a n v 2 - v 1 μ 2 - 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 featurei(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 = ( x i - m ) 2 + ( y i - n ) 2 2 R
In formula, YiRepresent the fisrt feature of ith feature point, (xi,yi) 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, EiRepresent the second feature of ith feature point, EiSpan be 0 to 360 degree, (xi,yi) 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 memory space and the restriction of the speed of service of image password identification device 1, reflected again palm vein and the palm The change of stricture of vagina, 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 electronic lock improves relatively 5.2%, 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. an electronic lock system based on hand identification, is characterized in that, reports to the police including image password identification device, fingerprint recognition Device and safety control, described image password identification device is used for identifying image password, and when identifying successfully to institute Stating safety control transmission and unlock instruction, described safety control is for according to the transmission of described image password identification device Unlock instruction, be unlocked；Described fingerprint recognition alarm device is for judging whether to report to the police according to the fingerprint of input.
A kind of electronic lock system based on hand identification the most according to claim 1, is characterized in that, described image password is The palm characteristics of image that user sets.
A kind of electronic lock system based on hand identification the most according to claim 2, is characterized in that, described fingerprint recognition report After the fingerprint of input is successfully identified by alarm device, it is judged that described user is in the hole, send to user nominator Warning message.
CN201610621796.1A 2016-07-30 2016-07-30 A kind of electronic lock system based on hand identification Pending CN106296901A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201610621796.1A CN106296901A (en) 2016-07-30 2016-07-30 A kind of electronic lock system based on hand identification

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201610621796.1A CN106296901A (en) 2016-07-30 2016-07-30 A kind of electronic lock system based on hand identification

Publications (1)

Publication Number Publication Date
CN106296901A true CN106296901A (en) 2017-01-04

Family

ID=57663915

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201610621796.1A Pending CN106296901A (en) 2016-07-30 2016-07-30 A kind of electronic lock system based on hand identification

Country Status (1)

Country Link
CN (1) CN106296901A (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110457330A (en) * 2019-08-21 2019-11-15 北京远舢智能科技有限公司 A kind of time series data management platform
CN110718002A (en) * 2018-07-12 2020-01-21 河南森源重工有限公司 Vehicle door unlocking method and system

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101055618A (en) * 2007-06-21 2007-10-17 中国科学院合肥物质科学研究院 Palm grain identification method based on direction character
US20080226136A1 (en) * 2006-09-14 2008-09-18 Fujitsu Limited Living body guidance control method for a biometrics authentication device, and biometrics authentication device
CN102116113A (en) * 2010-12-27 2011-07-06 北京天公瑞丰科技有限公司 Security box unlocking system based on palm vein authentication and method thereof
CN201902075U (en) * 2010-12-27 2011-07-20 北京天公瑞丰科技有限公司 Security cabinet unlocking system based on palm vein identification
CN104123537A (en) * 2014-07-04 2014-10-29 西安理工大学 Rapid authentication method based on handshape and palmprint recognition
CN205068547U (en) * 2015-10-28 2016-03-02 西安科技大学 Remote fingerprint recognition access control system

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20080226136A1 (en) * 2006-09-14 2008-09-18 Fujitsu Limited Living body guidance control method for a biometrics authentication device, and biometrics authentication device
CN101055618A (en) * 2007-06-21 2007-10-17 中国科学院合肥物质科学研究院 Palm grain identification method based on direction character
CN102116113A (en) * 2010-12-27 2011-07-06 北京天公瑞丰科技有限公司 Security box unlocking system based on palm vein authentication and method thereof
CN201902075U (en) * 2010-12-27 2011-07-20 北京天公瑞丰科技有限公司 Security cabinet unlocking system based on palm vein identification
CN104123537A (en) * 2014-07-04 2014-10-29 西安理工大学 Rapid authentication method based on handshape and palmprint recognition
CN205068547U (en) * 2015-10-28 2016-03-02 西安科技大学 Remote fingerprint recognition access control system

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110718002A (en) * 2018-07-12 2020-01-21 河南森源重工有限公司 Vehicle door unlocking method and system
CN110457330A (en) * 2019-08-21 2019-11-15 北京远舢智能科技有限公司 A kind of time series data management platform
CN110457330B (en) * 2019-08-21 2022-09-13 北京远舢智能科技有限公司 Time sequence data management platform

Similar Documents

Publication Publication Date Title
CN103902977B (en) Face identification method and device based on Gabor binary patterns
CN110543822A (en) finger vein identification method based on convolutional neural network and supervised discrete hash algorithm
CN105528572A (en) Fingerprint identification method
CN103914676A (en) Method and apparatus for use in face recognition
CN101350063A (en) Method and apparatus for locating human face characteristic point
CN104580143A (en) Security authentication method based on gesture recognition, terminal, server and system
CN107169479A (en) Intelligent mobile equipment sensitive data means of defence based on fingerprint authentication
CN105912910A (en) Cellphone sensing based online signature identity authentication method and system
CN111476188B (en) Crowd counting method, system, medium and electronic equipment based on feature pyramid
CN103595538A (en) Identity verification method based on mobile phone acceleration sensor
CN108334875A (en) Vena characteristic extracting method based on adaptive multi-thresholding
CN109711416A (en) Target identification method, device, computer equipment and storage medium
CN102629320A (en) Ordinal measurement statistical description face recognition method based on feature level
CN103729625A (en) Face identification method
CN106682092A (en) Target retrieval method and terminal
CN102332084A (en) Identity identification method based on palm print and human face feature extraction
CN106296901A (en) A kind of electronic lock system based on hand identification
Boles et al. Personal identification using images of the human palm
CN105844265B (en) A kind of fingerprint image treating method and apparatus
CN104820828A (en) Identity authentication method based on multi-directional mixed features of dual inner phalangeal prints
Tian et al. The cooperative vehicle infrastructure system based on machine vision
Jain et al. Online signature verification using energy, angle and directional gradient feature with neural network
CN106303000A (en) A kind of mobile terminal unlocked based on hand identification
CN110427826A (en) A kind of hand identification method, apparatus, electronic equipment and storage medium
CN104766085B (en) A kind of multiple dimensioned pattern recognition method

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
RJ01 Rejection of invention patent application after publication
RJ01 Rejection of invention patent application after publication

Application publication date: 20170104