CN111310545A - Method for measuring handwriting simulation complexity in online handwriting authentication - Google Patents
Method for measuring handwriting simulation complexity in online handwriting authentication Download PDFInfo
- Publication number
- CN111310545A CN111310545A CN201911224765.2A CN201911224765A CN111310545A CN 111310545 A CN111310545 A CN 111310545A CN 201911224765 A CN201911224765 A CN 201911224765A CN 111310545 A CN111310545 A CN 111310545A
- Authority
- CN
- China
- Prior art keywords
- handwriting
- calculating
- complexity index
- complexity
- simulation
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000004088 simulation Methods 0.000 title claims abstract description 57
- 238000000034 method Methods 0.000 title claims abstract description 23
- 238000005070 sampling Methods 0.000 claims description 19
- 238000004422 calculation algorithm Methods 0.000 claims description 6
- 230000008859 change Effects 0.000 claims description 6
- 230000009191 jumping Effects 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 3
- 230000001419 dependent effect Effects 0.000 claims description 3
- 230000008569 process Effects 0.000 description 3
- 108010076504 Protein Sorting Signals Proteins 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 230000002776 aggregation Effects 0.000 description 1
- 238000004220 aggregation Methods 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000007635 classification algorithm Methods 0.000 description 1
- 210000000887 face Anatomy 0.000 description 1
- 238000004445 quantitative analysis Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
- G06V30/32—Digital ink
- G06V30/333—Preprocessing; Feature extraction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
- G06V30/32—Digital ink
- G06V30/36—Matching; Classification
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Character Discrimination (AREA)
- Collating Specific Patterns (AREA)
Abstract
The invention relates to the field of information security, and discloses a method for measuring handwriting simulation complexity in online handwriting authentication, which comprises the following steps: calculating the writing speed and the rotation angle information of the given handwriting, calculating a simulation complexity index related to attention, a simulation complexity index related to memory, a simulation complexity index related to hand-eye coordination and a simulation complexity index related to observation, and fusing the four calculated simulation complexity indexes to obtain the overall simulation complexity of the handwriting. The invention discloses a method for measuring handwriting imitation complexity in online handwriting authentication, which quantitatively measures the imitation complexity of handwriting from four capabilities such as attention, memory, eye coordination, observation and the like so as to achieve the purpose of further estimating the shortest exercise time required by successfully imitating the handwriting with the given imitation complexity and lay a foundation for improving the overall safety of an online handwriting authentication system.
Description
Technical Field
The invention relates to the field of information security, in particular to a method for measuring handwriting simulation complexity in online handwriting authentication.
Background
In the field of on-line signature handwriting authentication, a system judges whether templates and test handwriting come from the same writer or not by comparing the handwriting of the user with the handwriting of the user name. The template handwriting is online handwriting which is submitted by a user with known identity and is related to the name of the user in a registration stage; the test handwriting refers to online handwriting submitted by a user with unknown identity in a test stage; the online handwriting is a time sequence signal sequence obtained by adopting special data acquisition equipment to acquire the movement track of a pen point in the handwriting process in real time through a sensor, and information acquired by the sensor at each sampling moment comprises information such as two-dimensional position information of the pen point, forward pressure applied by the pen point on a writing plane and the like; the online signature handwriting specifically refers to a time sequence signal sequence acquired by data acquisition equipment in the process of writing own name characters by a user.
In the authentication process using signature handwriting, such a dilemma is often encountered: namely, because the signature of some users is too simple, the signature handwriting such as "wang-wai-xiao" is easy to copy, so that the system faces higher misjudgment risk. Analysis has found that the reason for this problem is not classification algorithms, but rather that the space for variation of features contained in the easily imitated signature script is too small. If the handwritten signature handwriting submitted by the user is measured according to the imitation complexity in the registration stage, registration applications which are easy to imitate are rejected, so that the overall security of the system is improved.
The daily life experience tells us that the difficulty degree of handwriting imitation is objective, and the difficulty degree of different handwriting imitation is obviously different; it is not obvious to give a quantitative measure of the ease of simulation. It has been found that the complexity of the simulation is the minimum effort required to overcome the limitations of the ability of the person to successfully simulate handwriting (e.g., observation, memory, coordination, attention, etc.), for example, to recite short texts. Each specific handwriting has a certain imitation complexity, for example, it requires the imitator to have a strong observation power to perceive the handwriting detail characteristics (pen-moving mode, pen power variation, proportion collocation relationship, etc.) as much as possible; strong memory to remember the information; strong hand-eye coordination ability to write handwriting with specified characteristics; strong attention is also required to inhibit self-power setting of writing. The combination of all of the above capabilities determines how easily the handwriting is to be copied. The more a given handwriting requires for the above capabilities, the higher the corresponding emulation complexity; conversely, the lower.
Disclosure of Invention
The invention aims to provide a method for measuring handwriting imitation complexity in online handwriting authentication, which carries out quantitative measurement on the imitation complexity of the handwriting from four capabilities of attention, memory, hand-eye coordination, observation and the like so as to achieve the purpose of further estimating the shortest exercise time required for successfully imitating the handwriting with the given imitation complexity and lay a foundation for improving the overall safety of an online handwriting authentication system.
In order to achieve the above object, the present invention provides a method for measuring handwriting simulation complexity in online handwriting authentication, comprising the following steps:
A) beginning: let W { (x)1,y1,f1),(x2,y2,f2),...,(xn,yn,fn) The method comprises the steps that (1) a time sequence of the handwriting to be measured, which is acquired by a sensor, is defined, wherein x and y represent two-dimensional position information of a pen point, which is acquired by the sensor, and f represents pen point pressure information, which is acquired by the sensor;
B) calculating writing speed information of handwriting W: is provided with LW={l1,l2,...,lnRepresents the writing speed time series of the handwriting W,representing the speed information of the pen point at the kth moment, wherein k is more than 1 and less than or equal to n, l1=0;
C) Calculating the rotation angle information of the handwriting W: let AW={a1,a2,...,anDenotes the time sequence of the rotation angle of the handwriting W, is setIndicates the k-th timeInformation of the angle of rotation of the pen tip, whereink,lk+1Represents the velocity of the nib, D, at time k, k +1k=dxk×dxk+1+dyk×dyk+1, dxk=xk-xk-1,dxk+1=xk+1-xk,dyk=yk-yk-1,dyk+1=yk+1-yk,1<k<n,b1=0, bnFinally, the direction of the rotation angle is determined, i.e. if the sampling point (x) is set to 0k+1,yk+1) Such that the equation of the line f (x, y) is greater than zero, then ak=bk(ii) a Otherwise, ak=-bk(ii) a Wherein f (x, y) represents the sum of the values of the slave point (x)k-1,yk-1) To (x)k,yk) Linear equation of vector definition of direction, -pi ≦ ak≤π,1≤k≤n;
D) Calculating a simulation complexity index related to attention: calculating to obtain a simulation complexity index P1 related to attention by taking the number of sampling points of the handwriting time sequence W as an input parameter;
E) calculating a memory-related simulation complexity index: using handwriting time sequence W { (x)1,y1,f1),(x2,y2,f2),...,(xn,yn,fn) And rotation angle time series AW={a1,a2,...,anCalculating to obtain a simulation complexity index P2 related to memory;
F) calculating a simulation complexity index related to the hand-eye coordination force and the observation force; using handwriting time sequence W { (x)1,y1,f1),(x2,y2,f2),...,(xn,yn,fn) And writing speed time series LW={l1,l2,...,lnInvoking a simulation complexity index calculation method related to the hand-eye coordination force and the observation force, which is disclosed in the patent document, as an input parameter; obtaining simulation complexity indexes P3 and P4 related to the hand-eye coordination force and the observation force;
G) calculating the imitation complexity index P of the handwriting W as P1 × P2 × P3 × P4;
H) finishing; and returning the copy complexity index P of the handwriting W.
Preferably, in the step D), the step of calculating the imitation complexity index related to attention comprises the following steps:
D1) starting; taking the number n of sampling points of the handwriting time sequence W as an input parameter;
D2) calculating a simulation complexity index related to attention:wherein x represents the time for writing the handwriting, and the unit is second; x is n/F, wherein n represents the number of sampling points in the handwriting W, and F represents the sampling frequency of the handwriting board for collecting the handwriting W;
D3) and (4) ending: returning the tracing complexity index P1 ═ c (x) of the handwriting W in relation to attention.
Preferably, in the step E), the step of calculating the memory-related simulation complexity index comprises the following steps:
E1) beginning: using handwriting time sequence W { (x)1,y1,f1),(x2,y2,f2),...,(xn,yn,fn) And rotation angle time series AW={a1,a2,...,anAs input parameters;
E2) segmenting the handwriting W according to strokes: extracting key points K ═ K in W0,k1,k2,...,km-1,kmIn which k isiI is more than or equal to 0 and less than or equal to m, k represents the serial number of the key point in the handwriting W0=1,km=n,ki<ki+1I is more than or equal to 0 and less than m, and the handwriting W is divided into m strokes by the key points; wherein the ith stroke is
E3) Initializing a loop variable x to 1;
E4) calculating the number of the intersection points of the x-th stroke and other strokes in the handwriting W: let cxRepresenting the number of intersection points of the x-th stroke and other strokes in the handwriting W;
E5) calculating the number of subsegments with the same rotation angle sign in the x-th stroke: the sub-segments with the same rotation angle sign indicate that the rotation angle signs of all sampling points in the sub-segments are all non-positive or all non-negative sub-segments, and d is setxThe number of the subsegments with the same rotation angle sign in the x-th stroke is represented;
E6) calculating the stroke complexity index P of the x-th segmentx=1+cx/2+dx;
E7) If x is equal to x +1 and is less than or equal to m, jumping to step E4), reading the stroke complexity index of the next segment, otherwise, jumping to step E8);
E8) calculating a memory-related simulation complexity index: weighted average of stroke complexity indices for all segmentsObtaining a stroke complexity index of the handwriting W;
E9) and (4) ending: returning the copy complexity index P2 of the handwriting W relative to memory.
Preferably, in the step F), calculating the simulation complexity index related to the hand-eye coordination force and the observation force comprises the following steps:
F1) beginning: using handwriting time sequence W { (x)1,y1,f1),(x2,y2,f2),...,(xn,yn,fn) And writing speed time series LW={l1,l2,...,lnAs input parameters;
F2) segmenting the handwriting W according to strokes: extracting key points K ═ K in W0,k1,k2,...,km-1,kmIn which k isiI is more than or equal to 0 and less than or equal to m, k represents the serial number of the key point in the handwriting W0=1,km=n,ki<ki+1I is more than or equal to 0 and less than m, and the handwriting W is divided into m strokes by the key points, wherein the ith stroke is
F3) Calculating the length of each strokeax=atan(dyx/dxx), Get L ═ L1,L2,...,Lm},A={a1,a2,...,amCalculating the mean and variance of the sets L and A respectively,
F4) calculating writing speed sequence LW={l1,l2,...,lnMaximum and minimum values of }: is provided withRespectively representing the writing speed maximum and minimum value set, respectively calculating the mean value and variance of the writing speed maximum and minimum value,
F5) calculating writing force sequence FW={f1,f2,...,fnMaximum and minimum values of }: is provided withRespectively representing the maximum and minimum value sets of the writing force, and respectively calculating the mean value and the variance of the maximum and minimum values of the writing force;
F6) calculating the intersection points between all strokes in the handwriting W: let C { (x)i,yj)|(xi,yj) Is the intersection point of the ith and j strokes, i is more than or equal to 1, j is less than or equal to m, represents the set of the intersection points between all strokes in the handwriting W, and B is { (x)i,yi) I belongs to K and represents the starting and stopping point set of all strokes, and D is C ∪ B;
F7) calculate the mean and variance of all intersection location information: the mean and variance over the x and y components of all sample points in the cross point set D are calculated,
F8) calculating a feature change complexity index: p1=DIVL/AVGL;P2=DIVA/AVGA,
F10) Clustering the intersection points in the handwriting: clustering all the cross points in the set C according to the position relation by adopting a clustering algorithm, and setting E { (d)1,r1),(d2,r2),...,(dk,rk) Expressing a clustering result returned by a clustering algorithm, wherein k expresses the number of obtained categories; di,riRepresenting the number of intersection points in the ith category and the intra-category distance of the ith category, wherein i is more than or equal to 1 and less than or equal to k;
F12) And (4) ending: returning the handwriting W a simulation complexity index P3 related to hand-eye coordination and a simulation complexity index P4 related to observation.
Compared with the prior art, the invention has the following advantages: the method carries out quantitative measurement on the tracing complexity of the handwriting from four capabilities of attention, memory, eye coordination, observation and the like so as to achieve the purpose of further estimating the shortest exercise time required by successfully tracing the handwriting with the given tracing complexity, and lays a foundation for improving the overall safety of an online handwriting authentication system.
Drawings
FIG. 1 is a flow chart of a method for measuring handwriting simulation complexity in online handwriting authentication according to the present invention;
FIG. 2 is a detailed flowchart of step D) in FIG. 1;
FIG. 3 is a detailed flowchart of step E) of FIG. 1;
FIG. 4 is a detailed flowchart of step F) in FIG. 1.
Detailed Description
The invention is described in further detail below with reference to the figures and the specific embodiments.
A method for extracting and authenticating stroke dynamic characteristics in online handwriting authentication is shown in figure 1 and comprises the following steps:
a method for measuring handwriting simulation complexity in online handwriting authentication is shown in FIG. 1, and includes the following steps:
A) beginning: let W { (x)1,y1,f1),(x2,y2,f2),...,(xn,yn,fn) The method comprises the steps that (1) a time sequence of the handwriting to be measured, which is acquired by a sensor, is defined, wherein x and y represent two-dimensional position information of a pen point, which is acquired by the sensor, and f represents pen point pressure information, which is acquired by the sensor;
B) calculating writing speed information of handwriting W: is provided with LW={l1,l2,...,lnRepresents the writing speed time series of the handwriting W,representing the speed information of the pen point at the kth moment, wherein k is more than 1 and less than or equal to n, l1=0;
C) Calculating the rotation angle information of the handwriting W: let AW={a1,a2,...,anDenotes the time sequence of the rotation angle of the handwriting W, is setIndicating the rotational angle information of the pen tip at the k-th time, wherek,lk+1Represents the velocity of the nib, D, at time k, k +1k=dxk×dxk+1+dyk×dyk+1,dxk=xk-xk-1,dxk+1=xk+1-xk,dyk=yk-yk-1,dyk+1=yk+1-yk,1<k<n,b1=0, bnFinally, the direction of the rotation angle is determined, i.e. if the sampling point (x) is set to 0k+1,yk+1) Such that the equation of the line f (x, y) is greater than zero, then ak=bk(ii) a Otherwise, ak=-bk(ii) a Wherein f (x, y) represents the sum of the values of the slave point (x)k-1,yk-1) To (x)k,yk) Linear equation of vector definition of direction, -pi ≦ ak≤π,1≤k≤n;
D) Calculating a simulation complexity index related to attention: taking the number of sampling points of the handwriting time sequence W as an input parameter, calculating to obtain a simulation complexity index P1 related to attention, as shown in fig. 2, the calculating of the simulation complexity index related to attention includes the following steps:
D1) starting; taking the number n of sampling points of the handwriting time sequence W as an input parameter;
D2) calculating a simulation complexity index related to attention:wherein x represents the time for writing the handwriting, and the unit is second; x is n/F, wherein n represents the number of sampling points in the handwriting W, and F represents the sampling frequency of the handwriting board for collecting the handwriting W;
D3) and (4) ending: returning the tracing complexity index P1 ═ C (x) of the handwriting W related to attention;
E) calculating a memory-related simulation complexity index: using handwriting time sequence W { (x)1,y1,f1),(x2,y2,f2),...,(xn,yn,fn) And rotation angle time series AW={a1,a2,...,anCalculating a memory-related simulation complexity index P2 as an input parameter, as shown in fig. 3, wherein the calculating of the memory-related simulation complexity index includes the following steps:
E1) beginning: using handwriting time sequence W { (x)1,y1,f1),(x2,y2,f2),...,(xn,yn,fn) And rotation angle time series AW={a1,a2,...,anAs input parameters;
E2) segmenting the handwriting W according to strokes: extracting key points K ═ K in W0,k1,k2,...,km-1,kmIn which k isiI is more than or equal to 0 and less than or equal to m, k represents the serial number of the key point in the handwriting W0=1,km=n,ki<ki+1I is more than or equal to 0 and less than m, and the handwriting W is divided into m strokes by the key points; wherein the ith stroke is
E3) Initializing a loop variable x to 1;
E4) calculating the number of intersection points of the x-th stroke and other strokes in the handwriting W: let cxRepresenting the number of intersection points of the x-th stroke and other strokes in the handwriting W;
E5) calculating the number of subsegments with the same rotation angle sign in the x-th stroke: the sub-segments with the same rotation angle sign indicate that the rotation angle signs of all sampling points in the sub-segments are all non-positive or all non-negative sub-segments, and d is setxThe number of the subsegments with the same rotation angle sign in the x-th stroke is represented;
E6) calculating the stroke complexity index P of the x-th segmentx=1+cx/2+dx;
E7) If x is equal to x +1 and is less than or equal to m, jumping to step E4), reading the stroke complexity index of the next segment, otherwise, jumping to step E8);
E8) calculating a memory-related simulation complexity index: weighted average of stroke complexity indices for all segmentsObtaining a stroke complexity index of the handwriting W;
E9) and (4) ending: returning a copy complexity index P2 of the handwriting W related to the memory;
F) calculating a simulation complexity index related to the hand-eye coordination force and the observation force; using handwriting time sequence W { (x)1,y1,f1),(x2,y2,f2),...,(xn,yn,fn) And writing speed time series LW={l1,l2,...,lnInvoking a simulation complexity index calculation method related to the hand-eye coordination force and the observation force, which is disclosed in the patent document, as an input parameter; obtaining the simulation complexity indexes P3 and P4 related to the hand-eye coordination power and the observation power, and calculating the simulation complexity indexes related to the hand-eye coordination power and the observation power as shown in FIG. 4 comprises the following steps:
F1) beginning: using handwriting time sequence W { (x)1,y1,f1),(x2,y2,f2),...,(xn,yn,fn) And writing speed time series LW={l1,l2,...,lnAs input parameters;
F2) segmenting the handwriting W according to strokes: extracting key points K ═ K in W0,k1,k2,...,km-1,kmIn which k isiI is more than or equal to 0 and less than or equal to m, k represents the serial number of the key point in the handwriting W0=1,km=n,ki<ki+1I is more than or equal to 0 and less than m, and the handwriting W is divided into m strokes by the key points, wherein the ith stroke is
F3) Calculating the length of each strokeax=atan(dyx/dxx), Get L ═ L1,L2,...,Lm},A={a1,a2,...,amCalculating the mean and variance of the sets L and A respectively,
F4) calculating writing speed sequence LW={l1,l2,...,lnMaximum and minimum values of }: is provided withRespectively representing the writing speed maximum and minimum value set, respectively calculating the mean value and variance of the writing speed maximum and minimum value,
F5) calculating writing force sequence FW={f1,f2,...,fnMaximum and minimum values of }: is provided withRespectively representing the maximum and minimum value sets of the writing force, and respectively calculating the mean value and the variance of the maximum and minimum values of the writing force;
F6) calculating the intersection points between all strokes in the handwriting W: let C { (x)i,yj)|(xi,yj) Is the intersection point of the ith and j strokes, i is more than or equal to 1, j is less than or equal to m, represents the set of the intersection points between all strokes in the handwriting W, and B is { (x)i,yi) I belongs to K and represents the starting and stopping point set of all strokes, and D is C ∪ B;
F7) calculate the mean and variance of all intersection location information: the mean and variance over the x and y components of all sample points in the cross point set D are calculated,
F8) calculating a feature change complexity index: p1=DIVLAVGL;P2=DIVAAVGA,
F10) Clustering the intersection points in the handwriting: clustering all the cross points in the set C according to the position relation by adopting a clustering algorithm, and setting E { (d)1,r1),(d2,r2),...,(dk,rk) Expressing a clustering result returned by a clustering algorithm, wherein k expresses the number of obtained categories; di,riRepresenting the number of intersection points in the ith category and the intra-category distance of the ith category, wherein i is more than or equal to 1 and less than or equal to k;
F12) And (4) ending: returning a simulation complexity index P3 related to hand-eye coordination of the handwriting W and a simulation complexity index P4 related to observation power;
G) calculating the imitation complexity index P of the handwriting W as P1 × P2 × P3 × P4;
H) finishing; and returning the copy complexity index P of the handwriting W.
In the present example, quantitative analysis was performed from the following four aspects:
A. memory power
Each stroke in the handwriting comprises information such as the position, the length, the azimuth angle, the shape and the like of a starting point and an ending point, and also comprises information such as arc length, rotated angle, direction and the like if the stroke is wound, so that the more the number of strokes is, the larger the information amount is, and the higher the requirement on the memory is.
B. Coordination of hand and eye
In unit time, the more strokes are, the more writing actions are, and the higher the requirement on the coordination force of hands and eyes is; if the stroke category number is more in a certain stroke sequence, the requirement on the coordination force of hands and eyes is higher.
C. Observation power
The shorter the stroke length in the handwriting, the less easy to attract attention; the higher the degree of stroke aggregation, e.g., crossing strokes, overlapping strokes, etc., the less likely it is to find features therein, and the more careful observation is required.
D. Attention to
It was found experimentally that the high concentration state of attention is not permanent and that after a certain increase in duration, e.g. 6 ± 2 seconds, attention will not be dispersed autonomously. Therefore, the longer the handwriting writing time, the higher the attention requirement.
The invention discloses a method for measuring handwriting imitation complexity in online handwriting authentication, which quantitatively measures the imitation complexity of handwriting from four capabilities such as attention, memory, eye coordination, observation and the like so as to achieve the purpose of further estimating the shortest exercise time required by successfully imitating the handwriting with the given imitation complexity and lay a foundation for improving the overall safety of an online handwriting authentication system.
Claims (4)
1. A method for measuring handwriting simulation complexity in online handwriting authentication is characterized by comprising the following steps: the method comprises the following steps:
A) beginning: let W { (x)1,y1,f1),(x2,y2,f2),...,(xn,yn,fn) The method comprises the steps that (1) a time sequence of the handwriting to be measured, which is acquired by a sensor, is defined, wherein x and y represent two-dimensional position information of a pen point, which is acquired by the sensor, and f represents pen point pressure information, which is acquired by the sensor;
B) calculating the writing speed of handwriting WInformation: is provided with LW={l1,l2,...,lnRepresents the writing speed time series of the handwriting W,representing the speed information of the pen point at the kth moment, wherein k is more than 1 and less than or equal to n, l1=0;
C) Calculating the rotation angle information of the handwriting W: let AW={a1,a2,...,anDenotes the time sequence of the rotation angle of the handwriting W, is setIndicating the rotational angle information of the pen tip at the k-th time, wherek,lk+1Represents the velocity of the nib, D, at time k, k +1k=dxk×dxk+1+dyk×dyk+1,dxk=xk-xk-1,dxk+1=xk+1-xk,dyk=yk-yk-1,dyk+1=yk+1-yk,1<k<n,b1=0,bnFinally, the direction of the rotation angle is determined, i.e. if the sampling point (x) is set to 0k+1,yk+1) Such that the equation of the line f (x, y) is greater than zero, then ak=bk(ii) a Otherwise, ak=-bk(ii) a Wherein f (x, y) represents the sum of the values of the slave point (x)k-1,yk-1) To (x)k,yk) Linear equation of vector definition of direction, -pi ≦ ak≤π,1≤k≤n;
D) Calculating a simulation complexity index related to attention: calculating to obtain a simulation complexity index P1 related to attention by taking the number of sampling points of the handwriting time sequence W as an input parameter;
E) calculating a memory-related simulation complexity index: using handwriting time sequence W { (x)1,y1,f1),(x2,y2,f2),...,(xn,yn,fn) And rotation angle time series AW={a1,a2,...,anAs inputCalculating parameters to obtain a copy complexity index P2 related to memory;
F) calculating a simulation complexity index related to the hand-eye coordination force and the observation force; using handwriting time sequence W { (x)1,y1,f1),(x2,y2,f2),...,(xn,yn,fn) And writing speed time series LW={l1,l2,...,lnInvoking a simulation complexity index calculation method related to the hand-eye coordination force and the observation force, which is disclosed in the patent document, as an input parameter; obtaining simulation complexity indexes P3 and P4 related to the hand-eye coordination force and the observation force;
G) calculating the imitation complexity index P of the handwriting W as P1 × P2 × P3 × P4;
H) finishing; and returning the copy complexity index P of the handwriting W.
2. The method for measuring the handwriting simulation complexity in the online handwriting authentication according to claim 1, wherein: in the step D), calculating the imitation complexity index related to attention comprises the following steps:
D1) starting; taking the number n of sampling points of the handwriting time sequence W as an input parameter;
D2) calculating a simulation complexity index related to attention:wherein x represents the time for writing the handwriting, and the unit is second; x is n/F, wherein n represents the number of sampling points in the handwriting W, and F represents the sampling frequency of the handwriting board for collecting the handwriting W;
D3) and (4) ending: returning the tracing complexity index P1 ═ c (x) of the handwriting W in relation to attention.
3. The method for measuring the handwriting simulation complexity in the online handwriting authentication according to claim 2, wherein: in the step E), the step of calculating the imitation complexity index related to the memory comprises the following steps:
E1) beginning: when writingThe sequence W { (x)1,y1,f1),(x2,y2,f2),...,(xn,yn,fn) And rotation angle time series AW={a1,a2,...,anAs input parameters;
E2) segmenting the handwriting W according to strokes: extracting key points K ═ K in W0,k1,k2,...,km-1,kmIn which k isiI is more than or equal to 0 and less than or equal to m, k represents the serial number of the key point in the handwriting W0=1,km=n,ki<ki+1I is more than or equal to 0 and less than m, and the handwriting W is divided into m strokes by the key points; wherein the ith stroke is
E3) Initializing a loop variable x to 1;
E4) calculating the number of intersection points of the x-th stroke and other strokes in the handwriting W: let cxRepresenting the number of intersection points of the x-th stroke and other strokes in the handwriting W;
E5) calculating the number of subsegments with the same rotation angle sign in the x-th stroke: the sub-segments with the same rotation angle sign indicate that the rotation angle signs of all sampling points in the sub-segments are all non-positive or all non-negative sub-segments, and d is setxThe number of the subsegments with the same rotation angle sign in the x-th stroke is represented;
E6) calculating the stroke complexity index P of the x-th segmentx=1+cx/2+dx;
E7) If x is equal to x +1 and is less than or equal to m, jumping to step E4), reading the stroke complexity index of the next segment, otherwise, jumping to step E8);
E8) calculating a memory-related simulation complexity index: weighted average of stroke complexity indices for all segmentsObtaining a stroke complexity index of the handwriting W;
E9) and (4) ending: returning the copy complexity index P2 of the handwriting W relative to memory.
4. A method for measuring handwriting simulation complexity in online handwriting authentication according to claim 3, wherein: in the step F), calculating the simulation complexity index related to the hand-eye coordination force and the observation force comprises the following steps:
F1) beginning: using handwriting time sequence W { (x)1,y1,f1),(x2,y2,f2),...,(xn,yn,fn) And writing speed time series LW={l1,l2,...,lnAs input parameters;
F2) segmenting the handwriting W according to strokes: extracting key points K ═ K in W0,k1,k2,...,km-1,kmIn which k isiI is more than or equal to 0 and less than or equal to m, k represents the serial number of the key point in the handwriting W0=1,km=n,ki<ki+1I is more than or equal to 0 and less than m, and the handwriting W is divided into m strokes by the key points, wherein the ith stroke is
F3) Calculating the length of each strokeax=a tan(dyx/dxx), X is more than or equal to 1 and less than m, and L is ═ L1,L2,...,Lm},A={a1,a2,...,amCalculating the mean and variance of the sets L and A respectively,
F4) calculating writing speed sequence LW={l1,l2,...,lnMaximum and minimum values of }: is provided withRespectively representing the writing speed maximum and minimum value set, respectively calculating the mean value and variance of the writing speed maximum and minimum value,
F5) calculating writing force sequence FW={f1,f2,...,fnMaximum and minimum values of }: is provided withRespectively representing the maximum and minimum value sets of the writing force, and respectively calculating the mean value and the variance of the maximum and minimum values of the writing force;
F6) calculating the intersection points between all strokes in the handwriting W: let C { (x)i,yj)|(xi,yj) Is the intersection point of the ith and j strokes, i is more than or equal to 1, j is less than or equal to m, represents the set of the intersection points between all strokes in the handwriting W, and B is { (x)i,yi) I belongs to K and represents the starting and stopping point set of all strokes, and D is C ∪ B;
F7) calculate the mean and variance of all intersection location information: computing a set of intersectionsThe mean and variance of all samples in D over the x and y components,
F10) Clustering the intersection points in the handwriting: clustering all the cross points in the set C according to the position relation by adopting a clustering algorithm, and setting E { (d)1,r1),(d2,r2),...,(dk,rk) Expressing a clustering result returned by a clustering algorithm, wherein k expresses the number of obtained categories; di,riRepresenting the number of intersection points in the ith category and the intra-category distance of the ith category, wherein i is more than or equal to 1 and less than or equal to k;
F12) And (4) ending: returning the handwriting W a simulation complexity index P3 related to hand-eye coordination and a simulation complexity index P4 related to observation.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911224765.2A CN111310545B (en) | 2019-12-04 | 2019-12-04 | Method for measuring handwriting simulation complexity in online handwriting authentication |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911224765.2A CN111310545B (en) | 2019-12-04 | 2019-12-04 | Method for measuring handwriting simulation complexity in online handwriting authentication |
Publications (2)
Publication Number | Publication Date |
---|---|
CN111310545A true CN111310545A (en) | 2020-06-19 |
CN111310545B CN111310545B (en) | 2023-03-31 |
Family
ID=71150711
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201911224765.2A Active CN111310545B (en) | 2019-12-04 | 2019-12-04 | Method for measuring handwriting simulation complexity in online handwriting authentication |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111310545B (en) |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20110217679A1 (en) * | 2008-11-05 | 2011-09-08 | Carmel-Haifa University Economic Corporation Ltd. | Diagnosis method and system based on handwriting analysis |
WO2014169835A1 (en) * | 2013-04-18 | 2014-10-23 | 武汉汉德瑞庭科技有限公司 | Online handwriting authentication method and system based on finger information |
CN104166499A (en) * | 2014-07-10 | 2014-11-26 | 武汉汉德瑞庭科技有限公司 | Handwriting practice system and practice handwriting automatic detecting and evaluating method |
CN111310546A (en) * | 2019-12-04 | 2020-06-19 | 江南大学 | Method for extracting and authenticating writing rhythm characteristics in online handwriting authentication |
-
2019
- 2019-12-04 CN CN201911224765.2A patent/CN111310545B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20110217679A1 (en) * | 2008-11-05 | 2011-09-08 | Carmel-Haifa University Economic Corporation Ltd. | Diagnosis method and system based on handwriting analysis |
WO2014169835A1 (en) * | 2013-04-18 | 2014-10-23 | 武汉汉德瑞庭科技有限公司 | Online handwriting authentication method and system based on finger information |
CN104166499A (en) * | 2014-07-10 | 2014-11-26 | 武汉汉德瑞庭科技有限公司 | Handwriting practice system and practice handwriting automatic detecting and evaluating method |
CN111310546A (en) * | 2019-12-04 | 2020-06-19 | 江南大学 | Method for extracting and authenticating writing rhythm characteristics in online handwriting authentication |
Non-Patent Citations (3)
Title |
---|
SEN, ANAMIKA,ET.AL: "An Algorithm to Extract Handwriting Feature for Personality Analysis", 《INTERNATIONAL CONFERENCE ON WIRELESS COMMUNICATION (ICWICOM)》 * |
王贵容: "浅谈如何鉴别模仿笔迹", 《中国防伪报道》 * |
邹杰等: "基于笔画特征的在线笔迹匹配算法", 《自动化学报》 * |
Also Published As
Publication number | Publication date |
---|---|
CN111310545B (en) | 2023-03-31 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN103400105B (en) | Method identifying non-front-side facial expression based on attitude normalization | |
CN103473492B (en) | Authority recognition method and user terminal | |
Griswold-Steiner et al. | Handwriting watcher: A mechanism for smartwatch-driven handwriting authentication | |
CN109997152A (en) | Zero sample learning being aligned using multiple dimensioned manifold | |
Dimauro et al. | Analysis of stability in hand-written dynamic signatures | |
CN105426882A (en) | Method for rapidly positioning human eyes in human face image | |
CN111401105B (en) | Video expression recognition method, device and equipment | |
CN110175657A (en) | A kind of image multi-tag labeling method, device, equipment and readable storage medium storing program for executing | |
CN109255339B (en) | Classification method based on self-adaptive deep forest human gait energy map | |
Pratama et al. | Face recognition for presence system by using residual networks-50 architecture | |
CN103198297B (en) | Based on the kinematic similarity assessment method of correlativity geometric properties | |
CN109685104B (en) | Determination method and device for recognition model | |
Tanguay | Hidden Markov models for gesture recognition | |
CN111310545B (en) | Method for measuring handwriting simulation complexity in online handwriting authentication | |
Hansen et al. | Neural mechanisms for the robust representation of junctions | |
CN110020638A (en) | Facial expression recognizing method, device, equipment and medium | |
Han et al. | An interactive grading and learning system for chinese calligraphy | |
CN109886091A (en) | Three-dimensional face expression recognition methods based on Weight part curl mode | |
Sugiharti et al. | Facial recognition using two-dimensional principal component analysis and k-nearest neighbor: a case analysis of facial images | |
CN109753922A (en) | Anthropomorphic robot expression recognition method based on dense convolutional neural networks | |
CN103294998A (en) | Face visual feature representation method based on attribute space | |
CN106648149B (en) | A kind of aerial hand-written character recognition method based on accelerometer and gyroscope | |
CN111599444A (en) | Intelligent tongue diagnosis detection method and device, intelligent terminal and storage medium | |
CN111062022A (en) | Slider verification method and device based on disturbance visual feedback and electronic equipment | |
Shaheen et al. | Sar: Stroke authorship recognition |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant | ||
PE01 | Entry into force of the registration of the contract for pledge of patent right |
Denomination of invention: A measurement method for the complexity of handwriting imitation in online handwriting authentication Effective date of registration: 20231026 Granted publication date: 20230331 Pledgee: Guanggu Branch of Wuhan Rural Commercial Bank Co.,Ltd. Pledgor: WUHAN TECHNOLOGY AND BUSINESS University Registration number: Y2023980062886 |
|
PE01 | Entry into force of the registration of the contract for pledge of patent right |