CN105912910A - Cellphone sensing based online signature identity authentication method and system - Google Patents
Cellphone sensing based online signature identity authentication method and system Download PDFInfo
- Publication number
- CN105912910A CN105912910A CN201610250594.0A CN201610250594A CN105912910A CN 105912910 A CN105912910 A CN 105912910A CN 201610250594 A CN201610250594 A CN 201610250594A CN 105912910 A CN105912910 A CN 105912910A
- Authority
- CN
- China
- Prior art keywords
- user
- information
- mobile phone
- module
- training
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/30—Authentication, i.e. establishing the identity or authorisation of security principals
- G06F21/31—User authentication
- G06F21/32—User authentication using biometric data, e.g. fingerprints, iris scans or voiceprints
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/03—Arrangements for converting the position or the displacement of a member into a coded form
- G06F3/033—Pointing devices displaced or positioned by the user, e.g. mice, trackballs, pens or joysticks; Accessories therefor
- G06F3/0346—Pointing devices displaced or positioned by the user, e.g. mice, trackballs, pens or joysticks; Accessories therefor with detection of the device orientation or free movement in a 3D space, e.g. 3D mice, 6-DOF [six degrees of freedom] pointers using gyroscopes, accelerometers or tilt-sensors
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/30—Noise filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
- G06V10/751—Comparing pixel values or logical combinations thereof, or feature values having positional relevance, e.g. template matching
-
- 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
- G06V40/30—Writer recognition; Reading and verifying signatures
- G06V40/33—Writer recognition; Reading and verifying signatures based only on signature image, e.g. static signature recognition
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M1/00—Substation equipment, e.g. for use by subscribers
- H04M1/72—Mobile telephones; Cordless telephones, i.e. devices for establishing wireless links to base stations without route selection
- H04M1/724—User interfaces specially adapted for cordless or mobile telephones
- H04M1/72448—User interfaces specially adapted for cordless or mobile telephones with means for adapting the functionality of the device according to specific conditions
- H04M1/72463—User interfaces specially adapted for cordless or mobile telephones with means for adapting the functionality of the device according to specific conditions to restrict the functionality of the device
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M2203/00—Aspects of automatic or semi-automatic exchanges
- H04M2203/60—Aspects of automatic or semi-automatic exchanges related to security aspects in telephonic communication systems
- H04M2203/6054—Biometric subscriber identification
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Human Computer Interaction (AREA)
- General Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computer Security & Cryptography (AREA)
- Software Systems (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Computing Systems (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Computer Hardware Design (AREA)
- User Interface Of Digital Computer (AREA)
- Telephone Function (AREA)
Abstract
The present invention discloses a cellphone sensing based online signature identity authentication method and system. The method comprises: firstly training handwriting tracks of a real user and a fake user so as to obtain a similarity threshold, and storing the threshold and real user information used for training in a local user template library; and in a user identity authentication process, collecting user track information through a cellphone sensor, after extracting feature information of the tracks, carrying out similarity matching on the feature information and feature information in the user template library by using a DTW algorithm to obtain a minimum similarity value, and comparing the similarity value with the threshold stored in the local template library to determine whether the current user is the real user.
Description
Technical field
The present invention relates to a kind of personal identification side utilizing mobile phone sensor and on-line signature technological incorporation
Formula, uses mobile phone acceleration sensor, gyroscope to sign with DTW (dynamic time warping) particularly to one
The technological means of name algorithm fusion, realizes the mobile phone identity authentication of safe and convenient.
Background technology
At present, the mobile phone personal identification of known existence has numerical ciphers and password combination, biological characteristic
The modes such as identification, the authentication mode that wherein numerical ciphers and password combine realizes simple, but exists certain
Potential safety hazard, be easily broken, irremediable loss time serious, may be brought；Biological characteristic is known
Other mode is the authentication utilizing the uniqueness of the individual biological sign being had to carry out user, but due to
Obtain the costliness of biometric device and the immature of technology, cause the application on mobile phone to be difficult to promote.
So, this field of mobile phone personal identification needs further R and D.
Summary of the invention
In order to overcome the safety problem and the complexity of authentication mode that existing mobile phone authentication mode generally exists
Problem, it is provided that a kind of on-line signature identity identifying method based on mobile phone sensing and system.
The technical solution adopted for the present invention to solve the technical problems is:
A kind of on-line signature identity identifying method based on mobile phone sensing is provided, it is characterised in that
Training stage:
Step 1-1, the handwriting tracks of the tape label being obtained user and non-user by embedded in mobile phone sensor are believed
Breath；
Step 1-2, the handwriting tracks information of different user is passed through pretreatment operation；
Step 1-3, extract pretreated track characteristic information, including the spatial coordinated information after normalization,
Azimuth information and tilt angle information；
Step 1-4, utilization DTW algorithm obtain the similarity between the track characteristic information of different user, from
And obtain the distance threshold T judging between true and false user；And by the user trajectory characteristic information trained and away from
Leave in the template base of user this locality from threshold value T；
Cognitive phase:
Step 2-1, obtain user's handwriting tracks information carry out pretreatment by mobile phone sensor；
Step 2-2, extract pretreated track characteristic information, including the spatial coordinated information after normalization,
Azimuth information and tilt angle information；
Rail in step 2-3, track characteristic information and the user this locality template base will extracted by DTW algorithm
Mark characteristic information contrasts, and obtains the similarity S between two tracks；
Step 2-4, the distance threshold T that obtains during similarity S and training is compared, as S≤T
Time, it is determined that for real user, it is otherwise to forge user.
In method of the present invention, in step 1-1, it is main biography with the acceleration transducer of embedded in mobile phone
Sensor, with gyroscope as aiding sensors, the data that wherein acceleration transducer obtains are acceleration of gravity
With actual motion acceleration in all directions and, gyroscope detection mobile phone direction in moving process
Change, to obtain the real-time angular velocity that mobile phone moves.
In method of the present invention, in the template base of user this locality, each user deposits 3 signature templates,
Comprise three user's signatures of maximum, minima and par particular point.
In method of the present invention, step 2-1 particularly as follows:
Leave in local standard template base during user trajectory characteristic information to be verified and training
Track characteristic information compares respectively, obtains 3 similarities, choose wherein minimum similarity with
The distance threshold left in local template base compares.
In method of the present invention, user's handwriting tracks information is carried out by step 1-2 and step 2-1
Pretreatment specifically includes:
By Gaussian filter, the user's handwriting tracks information obtained is removed noise therein, and noise is main
The white Gaussian noise produced at work from mobile phone device；
The handwritten signature center of gravity at two dimensional surface is calculated by the meansigma methods asking for coordinate points；
Each handwritten signature coordinate is deducted center-of-gravity value, and the new coordinate after being translated, this center of gravity becomes new
Zero；
New coordinate is carried out size normalization, passes through formulaLook for novelty the two dimension of coordinate sequence
Quadratic sum open radical sign, n represents total number of coordinates of track, more respectively by formula x (t)=x (t)/M,
Y (t)=y (t)/M normalization transverse and longitudinal coordinate sequence.
Present invention also offers a kind of on-line signature identity authorization system based on mobile phone sensing, this system bag
Include training module and identification module, wherein:
Training module includes:
Training trace information acquisition module, for obtaining user and non-user by embedded in mobile phone sensor
The handwriting tracks information of tape label；
Training pretreatment module, for passing through pretreatment operation by the handwriting tracks information of different user；
Training extraction module, is used for extracting pretreated track characteristic information, including the sky after normalization
Between coordinate information, azimuth information and tilt angle information；
Local template base sets up module, for using DTW algorithm to obtain the track characteristic information of different user
Between similarity, thus obtain the distance threshold T judging between true and false user；And the user that will train
Track characteristic information and distance threshold T leave in the template base of user this locality；
Identification module includes:
Trace information acquisition module, for obtaining user's handwriting tracks information by mobile phone sensor；
Pretreatment module, for carrying out pretreatment to user's handwriting tracks information；
Extraction module, extracts pretreated track characteristic information, believes including the space coordinates after normalization
Breath, azimuth information and tilt angle information；
Comparing module, is used for the track characteristic information extracted and user this locality template base by DTW algorithm
In track characteristic information contrast, obtain the similarity S between two tracks；
Determination module, for by similarity S with train during the distance threshold T that obtains compare,
As S≤T, it is determined that for real user, be otherwise to forge user.
In system of the present invention, training trace information acquisition module is specifically with the acceleration of embedded in mobile phone
Sensor is master reference, with gyroscope as aiding sensors, and the data obtained by acceleration transducer
For acceleration of gravity and actual motion acceleration in all directions and, detect mobile phone by gyroscope and exist
Direction change in moving process, to obtain the real-time angular velocity that mobile phone moves.
In system of the present invention, local template base sets up module specifically in user this locality template base
In, deposit 3 signature templates for each user, comprise maximum, minima and par particular point
Three user's signatures.
In system of the present invention, pretreatment module is specifically for by user trajectory feature letter to be verified
The track characteristic information left in local standard template base during breath and training compares respectively, obtains 3
Individual similarity, chooses wherein minimum similarity and the distance threshold left in local template base does
Relatively.
In system of the present invention, user's handwriting tracks is believed by training pretreatment module with pretreatment module
Breath carries out specifically including during pretreatment:
By Gaussian filter, the user's handwriting tracks information obtained is removed noise therein, and noise is main
The white Gaussian noise produced at work from mobile phone device；
The handwritten signature center of gravity at two dimensional surface is calculated by the meansigma methods asking for coordinate points；
Each handwritten signature coordinate is deducted center-of-gravity value, and the new coordinate after being translated, this center of gravity becomes new
Zero；
New coordinate is carried out size normalization, passes through formulaLook for novelty the two dimension of coordinate sequence
Quadratic sum open radical sign, n represents total number of coordinates of track, more respectively by formula x (t)=x (t)/M,
Y (t)=y (t)/M normalization transverse and longitudinal coordinate sequence.
The beneficial effect comprise that: the present invention by mobile phone sensor and on-line signature technological incorporation,
Track when utilizing mobile phone acceleration sensor and gyroscope to catch people's cell phone aloft obtains people's
Signature, then utilizes the signature hand writing technology of maturation to complete mobile phone identity authentication function, can solve at present
The insecurity problem that exists of mobile phone authentication mode, also solve the complexity that current techniques realizes simultaneously.
Accompanying drawing explanation
Below in conjunction with drawings and Examples, the invention will be further described, in accompanying drawing:
Fig. 1 is the flow chart of the on-line signature identity identifying method that the embodiment of the present invention senses based on mobile phone；
Fig. 2 is the flow chart of the on-line signature identity authorization system that the embodiment of the present invention senses based on mobile phone.
Detailed description of the invention
In order to make the purpose of the present invention, technical scheme and advantage clearer, below in conjunction with accompanying drawing and
Embodiment, is further elaborated to the present invention.Should be appreciated that described herein being embodied as
Example only in order to explain the present invention, is not intended to limit the present invention.
The present invention is in the authentication procedures of user, and the sensor using smart mobile phone built-in catches user
The trace information that hands aloft streaks, acceleration transducer and gyroscope mainly by mobile phone come here
Complete the direction of track and the detection of angular transformation, thus realize arbitrarily writing user at three dimensions
Handwriting information reappears in two dimensional surface；Mobile phone acceleration information is obtained particular by acceleration transducer,
Acceleration double integral be can get the displacement that mobile phone moves along a direction, the mobile phone of gyroscope detection simultaneously
Direction change in moving process, thus obtain whole trace informations that mobile phone in three dimensions moves；
Trace information is described in two dimensional surface, trace information is carried out pretreatment, remove some noises and superfluous
Remaining information, after next step extraction pretreatment, the feature of information, is carried out characteristic information by DTW algorithm
Similarity measurement；In the training process, training data includes the specific handwriting tracks of user and non-user,
Training obtains belonging to the threshold value of each user, and the handwriting tracks characteristic information of real user is stored in use
In the personal template storehouse at family；During identifying, equally, extract after the trace information pretreatment that will obtain
Its characteristic information, then this feature information is obtained by DTW algorithm with the characteristic information in user template storehouse
Similar value between two kinds of information, then the threshold value that this similar value is local with being saved in user is compared, as
Fruit less than local threshold value, is then judged to this user, is otherwise judged to forge user.
The on-line signature identity identifying method that the embodiment of the present invention senses based on mobile phone, with reference to Fig. 1, this certification
Method mainly comprises the steps that
Training stage:
Step 1-1, the handwriting tracks of the tape label being obtained user and non-user by embedded in mobile phone sensor are believed
Breath；
Step 1-2, the handwriting tracks information of different user is passed through pretreatment operation；
Step 1-3, extract pretreated track characteristic information, including the spatial coordinated information after normalization,
Azimuth information and tilt angle information；
Step 1-4, utilization DTW algorithm (Dynamic Time Warping, dynamic time returns standard) obtain
Similarity between the track characteristic information of different user, thus obtain judging the distance between true and false user
Threshold value T；And leave the user trajectory characteristic information trained and distance threshold T in user this locality template base
In；
Cognitive phase:
Step 2-1, obtain user's handwriting tracks information carry out pretreatment by mobile phone sensor；
Step 2-2, extract pretreated track characteristic information, including the spatial coordinated information after normalization,
Azimuth information and tilt angle information；
Rail in step 2-3, track characteristic information and the user this locality template base will extracted by DTW algorithm
Mark characteristic information contrasts, and obtains the similarity S between two tracks；
Step 2-4, the distance threshold T that obtains during similarity S and training is compared, as S≤T
Time, it is determined that for real user, it is otherwise to forge user.
In step 1-1, with the acceleration transducer of embedded in mobile phone as master reference, with gyroscope for auxiliary
Sensor, the data that wherein acceleration transducer obtains are acceleration of gravity with actual motion acceleration respectively
Sum on individual direction, the direction change in moving process of the gyroscope detection mobile phone, move obtaining mobile phone
Real-time angular velocity.
In one embodiment of the present of invention, in the template base of user this locality, each user deposits 3 signature moulds
Plate, comprises three user's signatures of maximum, minima and par particular point.
Step 2-1 particularly as follows:
Leave in local standard template base during user trajectory characteristic information to be verified and training
Track characteristic information compares respectively, obtains 3 similarities, choose wherein minimum similarity with
The distance threshold left in local template base compares.
Step 1-2 and step 2-1 carry out pretreatment to user's handwriting tracks information specifically include:
By Gaussian filter, the user's handwriting tracks information obtained is removed noise therein, and noise is main
The white Gaussian noise produced at work from mobile phone device；
The handwritten signature center of gravity at two dimensional surface is calculated by the meansigma methods asking for coordinate points；
Each handwritten signature coordinate is deducted center-of-gravity value, and the new coordinate after being translated, this center of gravity becomes new
Zero；
New coordinate is carried out size normalization, passes through formulaLook for novelty the two dimension of coordinate sequence
Quadratic sum open radical sign, n represents total number of coordinates of track, more respectively by formula x (t)=x (t)/M,
Y (t)=y (t)/M normalization transverse and longitudinal coordinate sequence.
The embodiment of the present invention is used for realizing above-mentioned enforcement based on the on-line signature identity authorization system that mobile phone senses
The authentication method of example, this system includes training module and identification module, as in figure 2 it is shown, wherein:
Training module includes:
Training trace information acquisition module, for obtaining user and non-user by embedded in mobile phone sensor
The handwriting tracks information of tape label；
Training pretreatment module, for passing through pretreatment operation by the handwriting tracks information of different user；
Training extraction module, is used for extracting pretreated track characteristic information, including the sky after normalization
Between coordinate information, azimuth information and tilt angle information；
Local template base sets up module, for using DTW algorithm to obtain the track characteristic information of different user
Between similarity, thus obtain the distance threshold T judging between true and false user；And the user that will train
Track characteristic information and distance threshold T leave in the template base of user this locality；
Identification module includes:
Trace information acquisition module, for obtaining user's handwriting tracks information by mobile phone sensor；
Pretreatment module, for carrying out pretreatment to user's handwriting tracks information；
Extraction module, extracts pretreated track characteristic information, believes including the space coordinates after normalization
Breath, azimuth information and tilt angle information；
Comparing module, is used for the track characteristic information extracted and user this locality template base by DTW algorithm
In track characteristic information contrast, obtain the similarity S between two tracks；
Determination module, for by similarity S with train during the distance threshold T that obtains compare,
As S≤T, it is determined that for real user, be otherwise to forge user.
Wherein training trace information acquisition module and trace information acquisition module can share a module realization,
Training pretreatment module and pretreatment module can share a module and realize, training extraction module and extraction mould
Block also can share a module and realize.
When system starts first, entering the training process of system, real user is held respectively with forging user
Identical handwriting information the most repeatedly write by mobile phone, by mobile phone sensor using these information gatherings as
The training data of system, stores each data vector of one tape label, label available digital 1
Represent real user, represent forgery user with-1, after the feature extraction to training data, obtain
DTW similarity between data, finally obtain one for the level threshold value identifying process, and by this threshold
The training data of value and real user together leaves in local template base；During mobile phone interaction, use
The handwriting information of mobile phone writing training the most aloft is held at family, and system judges automatically according to this handwriting information
Currently used person is real user or forges user.After system start-up, further according to above-mentioned authentication method pair
The skyborne signature of user's handheld mobile phone is authenticated.
To sum up, the present invention, by mobile phone sensor and on-line signature technological incorporation, can solve current mobile phone
The insecurity problem that authentication mode exists, also solves the complexity that current techniques realizes simultaneously；This
The easily operation simple, convenient of bright system, safety height.From the point of view of hardware spending, the present invention needs use
Hardware device mainly have mobile phone acceleration sensor and gyroscope, these are existing portions in existing mobile phone
Part, low price, extra hardware spending will not be increased；From the point of view of software development, the present invention uses
Ripe feature extraction and DTW signature algorithm, can reach recognition effect of well signing.The present invention is
Big characteristic is to be combined by both technological perfectionisms, solves to deposit in existing mobile phone personal identification system
Some drawbacks.
It should be appreciated that for those of ordinary skills, can be changed according to the above description
Enter or convert, and all these modifications and variations all should belong to the protection domain of claims of the present invention.
Claims (10)
1. an on-line signature identity identifying method based on mobile phone sensing, it is characterised in that include following
Step:
Training stage:
Step 1-1, the handwriting tracks of the tape label being obtained user and non-user by embedded in mobile phone sensor are believed
Breath；
Step 1-2, the handwriting tracks information of different user is passed through pretreatment operation；
Step 1-3, extract pretreated track characteristic information, including the spatial coordinated information after normalization,
Azimuth information and tilt angle information；
Step 1-4, utilization DTW algorithm obtain the similarity between the track characteristic information of different user, from
And obtain the distance threshold T judging between true and false user；And by the user trajectory characteristic information trained and away from
Leave in the template base of user this locality from threshold value T；
Cognitive phase:
Step 2-1, obtain user's handwriting tracks information carry out pretreatment by mobile phone sensor；
Step 2-2, extract pretreated track characteristic information, including the spatial coordinated information after normalization,
Azimuth information and tilt angle information；
Rail in step 2-3, track characteristic information and the user this locality template base will extracted by DTW algorithm
Mark characteristic information contrasts, and obtains the similarity S between two tracks；
Step 2-4, the distance threshold T that obtains during similarity S and training is compared, as S≤T
Time, it is determined that for real user, it is otherwise to forge user.
Method the most according to claim 1, it is characterised in that in step 1-1, with embedded in mobile phone
Acceleration transducer be master reference, with gyroscope as aiding sensors, wherein acceleration transducer obtains
Data be acceleration of gravity with actual motion acceleration in all directions and, gyroscope detects hands
Machine direction change in moving process, to obtain the real-time angular velocity that mobile phone moves.
Method the most according to claim 1, it is characterised in that in the template base of user this locality, each
User deposits 3 signature templates, comprises three users of maximum, minima and par particular point
Signature.
Method the most according to claim 3, it is characterised in that step 2-1 particularly as follows:
Leave in local standard template base during user trajectory characteristic information to be verified and training
Track characteristic information compares respectively, obtains 3 similarities, choose wherein minimum similarity with
The distance threshold left in local template base compares.
Method the most according to claim 1, it is characterised in that step 1-2 is right with step 2-1
User's handwriting tracks information carries out pretreatment and specifically includes:
By Gaussian filter, the user's handwriting tracks information obtained is removed noise therein, and noise is main
The white Gaussian noise produced at work from mobile phone device；
The handwritten signature center of gravity at two dimensional surface is calculated by the meansigma methods asking for coordinate points；
Each handwritten signature coordinate is deducted center-of-gravity value, and the new coordinate after being translated, this center of gravity becomes new
Zero；
New coordinate is carried out size normalization, passes through formulaLook for novelty the two dimension of coordinate sequence
Quadratic sum open radical sign, n represents total number of coordinates of track, more respectively by formula x (t)=x (t)/M,
Y (t)=y (t)/M normalization transverse and longitudinal coordinate sequence.
6. an on-line signature identity authorization system based on mobile phone sensing, it is characterised in that this system bag
Include training module and identification module, wherein:
Training module includes:
Training trace information acquisition module, for obtaining user and non-user by embedded in mobile phone sensor
The handwriting tracks information of tape label；
Training pretreatment module, for passing through pretreatment operation by the handwriting tracks information of different user；
Training extraction module, is used for extracting pretreated track characteristic information, including the sky after normalization
Between coordinate information, azimuth information and tilt angle information；
Local template base sets up module, for using DTW algorithm to obtain the track characteristic information of different user
Between similarity, thus obtain the distance threshold T judging between true and false user；And the user that will train
Track characteristic information and distance threshold T leave in the template base of user this locality；
Identification module includes:
Trace information acquisition module, for obtaining user's handwriting tracks information by mobile phone sensor；
Pretreatment module, for carrying out pretreatment to user's handwriting tracks information；
Extraction module, extracts pretreated track characteristic information, believes including the space coordinates after normalization
Breath, azimuth information and tilt angle information；
Comparing module, is used for the track characteristic information extracted and user this locality template base by DTW algorithm
In track characteristic information contrast, obtain the similarity S between two tracks；
Determination module, for by similarity S with train during the distance threshold T that obtains compare,
As S≤T, it is determined that for real user, be otherwise to forge user.
System the most according to claim 6, it is characterised in that training trace information acquisition module tool
Body is with the acceleration transducer of embedded in mobile phone as master reference, with gyroscope as aiding sensors, by adding
The data that velocity sensor obtains be acceleration of gravity with actual motion acceleration in all directions and,
Changed by gyroscope detection mobile phone direction in moving process, to obtain the real-time angle speed that mobile phone moves
Degree.
System the most according to claim 6, it is characterised in that it is concrete that local template base sets up module
For in the template base of user this locality, deposit 3 signature templates for each user, comprise maximum,
Little value and three user's signatures of par particular point.
System the most according to claim 8, it is characterised in that pretreatment module will be specifically for treating
The track characteristic in local standard template base is left in during the user trajectory characteristic information of checking and training
Information compares respectively, obtains 3 similarities, chooses wherein minimum similarity and leaves this in
Distance threshold in ground template base compares.
System the most according to claim 6, it is characterised in that training pretreatment module and pre-place
Reason module specifically includes when user's handwriting tracks information is carried out pretreatment:
By Gaussian filter, the user's handwriting tracks information obtained is removed noise therein, and noise is main
The white Gaussian noise produced at work from mobile phone device；
The handwritten signature center of gravity at two dimensional surface is calculated by the meansigma methods asking for coordinate points；
Each handwritten signature coordinate is deducted center-of-gravity value, and the new coordinate after being translated, this center of gravity becomes new
Zero；
New coordinate is carried out size normalization, passes through formulaLook for novelty the two dimension of coordinate sequence
Quadratic sum open radical sign, n represents total number of coordinates of track, more respectively by formula x (t)=x (t)/M,
Y (t)=y (t)/M normalization transverse and longitudinal coordinate sequence.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610250594.0A CN105912910A (en) | 2016-04-21 | 2016-04-21 | Cellphone sensing based online signature identity authentication method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610250594.0A CN105912910A (en) | 2016-04-21 | 2016-04-21 | Cellphone sensing based online signature identity authentication method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105912910A true CN105912910A (en) | 2016-08-31 |
Family
ID=56746794
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610250594.0A Pending CN105912910A (en) | 2016-04-21 | 2016-04-21 | Cellphone sensing based online signature identity authentication method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105912910A (en) |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106411952A (en) * | 2016-12-01 | 2017-02-15 | 安徽工业大学 | Telekinetic-dynamic-gesture-based user identity authentication method and apparatus |
| CN106874834A (en) * | 2016-12-27 | 2017-06-20 | 电子科技大学 | The personal secrets protection system of Behavior-based control feature |
| CN107153780A (en) * | 2017-05-05 | 2017-09-12 | 西安交通大学苏州研究院 | The writing behavioural characteristic authentication method of electronic equipment is dressed based on wrist |
| CN108536314A (en) * | 2017-03-06 | 2018-09-14 | 华为技术有限公司 | Method for identifying ID and device |
| CN108563988A (en) * | 2018-03-06 | 2018-09-21 | 上海数迹智能科技有限公司 | A kind of finger tip track identification sorting technique |
| CN109145776A (en) * | 2018-08-01 | 2019-01-04 | 上海市数字证书认证中心有限公司 | Identity identifying method, device and identification terminal |
| CN109145778A (en) * | 2018-08-01 | 2019-01-04 | 上海市数字证书认证中心有限公司 | Identity identifying method, device and identification terminal |
| CN109376554A (en) * | 2018-10-16 | 2019-02-22 | 周金明 | Multiple terminals electronic document based on label and view examines label method and careful label system |
| CN109446905A (en) * | 2018-09-26 | 2019-03-08 | 深圳壹账通智能科技有限公司 | Sign electronically checking method, device, computer equipment and storage medium |
| CN110414196A (en) * | 2019-07-29 | 2019-11-05 | 深圳大学 | A kind of smartwatch auth method based on vibration signal |
| CN110942042A (en) * | 2019-12-02 | 2020-03-31 | 深圳棒棒帮科技有限公司 | Three-dimensional handwritten signature authentication method, system, storage medium and equipment |
| CN111669710A (en) * | 2020-04-21 | 2020-09-15 | 上海因势智能科技有限公司 | Demographic deduplication method |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101079707A (en) * | 2007-06-21 | 2007-11-28 | 中国科学院合肥物质科学研究院 | Identity authentication method based on revocable handwritten signature |
| CN103984416A (en) * | 2014-06-10 | 2014-08-13 | 北京邮电大学 | Gesture recognition method based on acceleration sensor |
| CN104408341A (en) * | 2014-11-13 | 2015-03-11 | 西安交通大学 | Smart phone user identity authentication method based on gyroscope behavior characteristics |
| CN104484644A (en) * | 2014-11-06 | 2015-04-01 | 三星电子（中国）研发中心 | Gesture identification method and device |
| CN104657638A (en) * | 2015-01-22 | 2015-05-27 | 成都朝越科技有限公司 | Motion-characteristic-based mobile phone unlocking method |
| CN104850773A (en) * | 2015-05-14 | 2015-08-19 | 西安交通大学 | User identity authentication method for intelligent mobile terminal |
| CN103442114B (en) * | 2013-08-16 | 2015-10-21 | 中南大学 | A kind of identity identifying method based on dynamic gesture |
-
2016
- 2016-04-21 CN CN201610250594.0A patent/CN105912910A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101079707A (en) * | 2007-06-21 | 2007-11-28 | 中国科学院合肥物质科学研究院 | Identity authentication method based on revocable handwritten signature |
| CN103442114B (en) * | 2013-08-16 | 2015-10-21 | 中南大学 | A kind of identity identifying method based on dynamic gesture |
| CN103984416A (en) * | 2014-06-10 | 2014-08-13 | 北京邮电大学 | Gesture recognition method based on acceleration sensor |
| CN104484644A (en) * | 2014-11-06 | 2015-04-01 | 三星电子（中国）研发中心 | Gesture identification method and device |
| CN104408341A (en) * | 2014-11-13 | 2015-03-11 | 西安交通大学 | Smart phone user identity authentication method based on gyroscope behavior characteristics |
| CN104657638A (en) * | 2015-01-22 | 2015-05-27 | 成都朝越科技有限公司 | Motion-characteristic-based mobile phone unlocking method |
| CN104850773A (en) * | 2015-05-14 | 2015-08-19 | 西安交通大学 | User identity authentication method for intelligent mobile terminal |
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106411952B (en) * | 2016-12-01 | 2019-07-26 | 安徽工业大学 | One kind is every lost motion state gesture user identity identifying method and device |
| CN106411952A (en) * | 2016-12-01 | 2017-02-15 | 安徽工业大学 | Telekinetic-dynamic-gesture-based user identity authentication method and apparatus |
| CN106874834A (en) * | 2016-12-27 | 2017-06-20 | 电子科技大学 | The personal secrets protection system of Behavior-based control feature |
| CN108536314A (en) * | 2017-03-06 | 2018-09-14 | 华为技术有限公司 | Method for identifying ID and device |
| CN107153780A (en) * | 2017-05-05 | 2017-09-12 | 西安交通大学苏州研究院 | The writing behavioural characteristic authentication method of electronic equipment is dressed based on wrist |
| CN108563988A (en) * | 2018-03-06 | 2018-09-21 | 上海数迹智能科技有限公司 | A kind of finger tip track identification sorting technique |
| CN108563988B (en) * | 2018-03-06 | 2021-12-03 | 上海数迹智能科技有限公司 | Fingertip track identification and classification method |
| CN109145776A (en) * | 2018-08-01 | 2019-01-04 | 上海市数字证书认证中心有限公司 | Identity identifying method, device and identification terminal |
| CN109145778A (en) * | 2018-08-01 | 2019-01-04 | 上海市数字证书认证中心有限公司 | Identity identifying method, device and identification terminal |
| CN109446905A (en) * | 2018-09-26 | 2019-03-08 | 深圳壹账通智能科技有限公司 | Sign electronically checking method, device, computer equipment and storage medium |
| CN109376554A (en) * | 2018-10-16 | 2019-02-22 | 周金明 | Multiple terminals electronic document based on label and view examines label method and careful label system |
| CN109376554B (en) * | 2018-10-16 | 2022-02-11 | 周金明 | Multi-terminal electronic document examination and signature method and system based on labels and views |
| CN110414196A (en) * | 2019-07-29 | 2019-11-05 | 深圳大学 | A kind of smartwatch auth method based on vibration signal |
| CN110942042A (en) * | 2019-12-02 | 2020-03-31 | 深圳棒棒帮科技有限公司 | Three-dimensional handwritten signature authentication method, system, storage medium and equipment |
| CN110942042B (en) * | 2019-12-02 | 2022-11-08 | 深圳棒棒帮科技有限公司 | Three-dimensional handwritten signature authentication method, system, storage medium and equipment |
| CN111669710A (en) * | 2020-04-21 | 2020-09-15 | 上海因势智能科技有限公司 | Demographic deduplication method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105912910A (en) | Cellphone sensing based online signature identity authentication method and system | |
| Tian et al. | KinWrite: Handwriting-Based Authentication Using Kinect. | |
| US7873189B2 (en) | Face recognition by dividing an image and evaluating a similarity vector with a support vector machine | |
| CN106354252B (en) | A kind of continuation character gesture track recognition method based on STDW | |
| CN100514352C (en) | Vena characteristic extracting method of finger vena identification system | |
| CN107844748A (en) | Auth method, device, storage medium and computer equipment | |
| CN105068743A (en) | Mobile terminal user identity authentication method based on multi-finger touch behavior characteristics | |
| CN103268483A (en) | Method for recognizing palmprint acquired in non-contact mode in open environment | |
| CN100410962C (en) | ID recognizing device of combining side profile and characteristic of ear | |
| CN103761466A (en) | Method and device for identity authentication | |
| US11416592B2 (en) | Method for online signature verification using wrist-worn devices | |
| CN108564040B (en) | Fingerprint activity detection method based on deep convolution characteristics | |
| CN104036254A (en) | Face recognition method | |
| US8953852B2 (en) | Method for face recognition | |
| Xu et al. | Challenge-response authentication using in-air handwriting style verification | |
| CN106934362B (en) | On-Line Signature Handwriting Verification Techniques based on behavioral characteristics subregion | |
| CN102411712B (en) | Handwriting-based method for identity identification and terminal thereof | |
| CN107592422B (en) | A kind of identity identifying method and system based on gesture feature | |
| CN112492090A (en) | Continuous identity authentication method fusing sliding track and dynamic characteristics on smart phone | |
| Behera et al. | Fast signature spotting in continuous air writing | |
| CN109286499B (en) | Behavior feature-based presence authentication method | |
| Tolosana et al. | Increasing the robustness of biometric templates for dynamic signature biometric systems | |
| CN103593660B (en) | The palm grain identification method that gradient of intersecting under a kind of invariant feature image encodes | |
| Kutzner et al. | User verification using safe handwritten passwords on smartphones | |
| CN113111322A (en) | Intelligent mobile phone auxiliary authentication method based on multi-mode fusion |
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 |
Application publication date: 20160831 |
|
| RJ01 | Rejection of invention patent application after publication |