CN103530542B - Based on the smart phone user authentication method that multiple image switches - Google Patents

Based on the smart phone user authentication method that multiple image switches Download PDF

Info

Publication number
CN103530542B
CN103530542B CN201310485761.6A CN201310485761A CN103530542B CN 103530542 B CN103530542 B CN 103530542B CN 201310485761 A CN201310485761 A CN 201310485761A CN 103530542 B CN103530542 B CN 103530542B
Authority
CN
China
Prior art keywords
user
authentication method
smart phone
finger motion
user authentication
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.)
Expired - Fee Related
Application number
CN201310485761.6A
Other languages
Chinese (zh)
Other versions
CN103530542A (en
Inventor
秦中元
胡爱群
杨中云
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.)
Southeast University
Original Assignee
Southeast University
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 Southeast University filed Critical Southeast University
Priority to CN201310485761.6A priority Critical patent/CN103530542B/en
Publication of CN103530542A publication Critical patent/CN103530542A/en
Application granted granted Critical
Publication of CN103530542B publication Critical patent/CN103530542B/en
Expired - Fee Related legal-status Critical Current
Anticipated expiration legal-status Critical

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
    • G06F21/316—User authentication by observing the pattern of computer usage, e.g. typical user behaviour
    • 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
    • G06F3/048—Interaction techniques based on graphical user interfaces [GUI]
    • G06F3/0487—Interaction techniques based on graphical user interfaces [GUI] using specific features provided by the input device, e.g. functions controlled by the rotation of a mouse with dual sensing arrangements, or of the nature of the input device, e.g. tap gestures based on pressure sensed by a digitiser
    • G06F3/0488—Interaction techniques based on graphical user interfaces [GUI] using specific features provided by the input device, e.g. functions controlled by the rotation of a mouse with dual sensing arrangements, or of the nature of the input device, e.g. tap gestures based on pressure sensed by a digitiser using a touch-screen or digitiser, e.g. input of commands through traced gestures
    • G06F3/04883—Interaction techniques based on graphical user interfaces [GUI] using specific features provided by the input device, e.g. functions controlled by the rotation of a mouse with dual sensing arrangements, or of the nature of the input device, e.g. tap gestures based on pressure sensed by a digitiser using a touch-screen or digitiser, e.g. input of commands through traced gestures for inputting data by handwriting, e.g. gesture or text

Abstract

The present invention proposes a kind of smart phone user authentication method switched based on multiple image, the present invention is first by the selected image sequence of user, this image sequence is stored in the internal storage of smart mobile phone, then the motion feature sequence pointed when recording user switches these images, comprises starting point coordinate, terminal point coordinate, speed etc.This characteristic sequence is labeled as after treatment the condition code of user, in order to distinguish different users.Compared with PIN certification, the present invention expands key space greatly, and convenient and practical, and not needing increases any extras, has very high discrimination and security.

Description

Based on the smart phone user authentication method that multiple image switches
Technical field
The present invention relates to the user authentication technique of smart mobile phone, in particular, is the method for authenticated identity safely and effectively on the smart mobile phone being furnished with touch-screen.
Background technology
Smart mobile phone is in the development obtaining making rapid progress in recent years, and they possess abundant interface (as first-class in touch-screen, WIFI, 3G, shooting) and powerful processing power.The portability exclusive due to it and various application program, smart mobile phone is more and more important affects daily life.Photo, mail, address list, even bank account, be nearly all kept in intelligent terminal.Therefore the identity of how authentication intelligent cellie, thus protect the safety of these private datas, just become a problem demanding prompt solution.
User authen method the most frequently used is at present PIN (Personal Identification Number) (PersonalIdentificationNumber, PIN) certification.Similar with the input password of computing machine, PIN certification needs user to input the numeric string of a regular length (being generally 5 ~ 8).This method simple practical, but its key space is less, and the PIN (Personal Identification Number) key space of such as 8 is only 10 8, this makes it easily be subject to brute force attack, and PIN (Personal Identification Number) is easily peeped by people or steals.
Another kind of comparatively conventional intelligent terminal user authentication method is image authentication, and it shows some net points on the touchscreen, and general size is 3 × 3, and then user's finger draws a curve, connects some lattice point.And the image authentication of non-critical in fact, but lattice point certification, because lattice point number is less, so its key space is also less, is easily subject to Brute Force to this method.
In addition the multiple user authen method based on biological characteristic is also had, comparative maturity be fingerprint recognition, the accuracy rate of current fingerprint recognition is higher, but general intelligence terminal touch screen does not possess finger print collecting function, therefore also needs additionally to install special fingerprint collecting equipment additional.Also have indivedual smart mobile phone to be proposed recognition of face, but the accuracy rate of recognition of face is lower, and algorithm is complicated, process data volume is large, the required time is longer, thus have impact on Consumer's Experience.In addition in addition knowledge method for distinguishing is carried out to user's handwritten signature, but its calculated amount is also larger.
Summary of the invention
For the deficiency of above conventional user authen method, the object of the invention is to propose a kind of practicality safely and effectively based on the smart phone user authentication techniques that multiple image switches.By gathering the finger motion feature of user when image switches, effectively identify different user.Whole process can be divided into registration phase and authentication phase, and particular content is described below:
(1) registration phase
First be initialization, comprise and set up user name, and image in smart mobile phone internal storage is listed select image sequence for user.Enter training process afterwards, this process comprises the extraction of twice finger motion characteristic sequence S and S ', if the distance of twice finger motion characteristic sequence S and S ' extracted is less than given threshold value, then registration process terminates, otherwise continues extraction twice user's finger motion characteristic sequence and judge.
Further, finger motion locus when wanting recording user at every turn to switch image when user's characteristic code T extracts, comprises starting point coordinate, terminal point coordinate, speed etc.Starting point coordinate and terminal point coordinate directly can read touchscreen events attribute and obtain, and speed gets the average velocity between this period of moving period, is obtained divided by interval time by the distance between zequin and terminal.
(2) authentication phase
First prompting inputs user name, and then show the piece image of this user registration, and point out user to switch, recording user finger motion characteristic sequence afterwards, comprises starting point, terminal and speed etc.Show lower piece image again and point out user to switch, recording user's finger motion characteristic sequence equally, until switch to last piece image.User's finger motion characteristic sequence of record gained and the user's characteristic code T that records when register are before compared, if between distance be less than given threshold value, then user authentication is successfully, otherwise authentification failure.
Compared with prior art, the invention has the beneficial effects as follows: by gathering the finger motion feature of user when image switches, this characteristic sequence is labeled as after treatment the condition code of user, in order to distinguish different users.Compared with authentication method in the past, the present invention not only key space expands greatly, has higher violence attack performance, and easy to operate, and computation complexity is low, easily remembers, and not needing increases any extras, has very high discrimination and security.
Accompanying drawing explanation
Fig. 1 is the user's register flow path figure in the embodiment of the present invention;
Fig. 2 is the user authentication process flow diagram of the embodiment of the present invention.
Embodiment
The specific embodiment of the present invention is set forth below in conjunction with accompanying drawing.
Enforcement of the present invention is divided into 2 steps, that is:
The first step, user registration course;
Second step, user authentication process.
As shown in Figure 1, concrete steps are described in detail as follows user registration course:
(1), user name is set up;
This user name is made up of 6 ~ 20 alphanumerics, such as " zhangsan2013 ", " wangguihua " etc.
(2), image sequence is selected;
List an image collection and therefrom select multiple image, such as 5 width for user, form an image sequence.For safety, this image sequence should be kept at smart mobile phone internal memory card but not external memory card as in SD card, picture format is not limit, and general selects JPG file.
(3) the finger motion characteristic sequence S, during recording user switching image;
Do not limit during the movement locus that user points when switching, can be from left to right, also can be from right to left, or even from the top down etc.If image sequence length is 5, then the action switched carries out 4 times altogether, and finger motion characteristic sequence when namely needing record 4 users to switch image, is designated as S.Each record content is a five-tuple, comprises the starting point coordinate of finger motion, terminal point coordinate and speed.Starting point coordinate and terminal point coordinate directly can read touchscreen events attribute and obtain, and speed gets the average velocity between this period of moving period, is obtained divided by interval time by the distance between zequin and terminal.The unit of starting point and terminal can adopt pixel value, and speed unit is pixel/second.Such as certain finger motion locus switching record is (300,20,100,24,200).
(4), again recording user switch image time finger motion characteristic sequence S ';
Step is with (3), and the finger motion characteristic sequence again during recording user switching image, is designated as S '.
(5) the distance D between S and S ', is calculated;
Adopt Euclidean distance computing formula.
If S=is (S 1, S 2..., S n-1, S n), S '=(S ' 1, S ' 2..., S ' n-1, S ' n), then the distance D between S and S ' is:
D = ( S 1 - S 1 ′ ) 2 + ( S 2 - S 2 ′ ) 2 + · · · + ( S n - S n ′ ) 2 )
(6), judge whether D is less than given threshold value;
If be less than, the finger motion characteristic sequence coupling of twice record be described, the condition code of user can be adopted as, otherwise gone to step (3), again input the finger motion characteristic sequence of user.
(7), user's characteristic code is preserved.
S and S ' corresponding element is averaged as the condition code of user, and is saved in log file.
So far, user registration course terminates.
As shown in Figure 2, concrete steps are described in detail as follows user authentication process:
(1), user inputs user name;
Because intelligent terminal generally only has owner to operate, for simplicity, the user name of equipment owner can be set to default value, need not all input at every turn.User name can be inputted by hand when other users use.
(2), the piece image that sets of display user, and point out user to start blocked operation;
(3) the finger motion characteristic sequence S, during recording user switching image;
If image sequence length is 5, then finger motion locus when needing record 4 users to switch image altogether, is designated as S.Each record content is a five-tuple, comprises the starting point coordinate of finger motion, terminal point coordinate and speed.The unit of starting point and terminal can adopt pixel value, and speed unit is pixel/second.Such as certain finger motion locus switching record is (280,20,90,24,210).
(4) the distance D between S and user's characteristic code, is calculated;
User's characteristic code, for generating when user registers, is designated as T.Distance between S and T adopts Euclidean distance formula.If S=is (S 1, S 2..., S n-1, S n), T=(T 1, T 2..., T n-1, T n), then the distance D between S and T is:
D = ( S 1 - T 1 ) 2 + ( S 2 - T 2 ) 2 + · · · + ( S n - T n ) 2 )
(5) user's whether authentication success, is judged.
Relatively whether D is less than given threshold value, if be less than, illustrates that the finger motion characteristic sequence that user inputs mates with the user's characteristic code preserved in advance, therefore accepting this user is the user that step (1) inputs, authentication success, otherwise think that both do not mate, authentification failure.
Compared with PIN certification, key space of the present invention has been expanded greatly.Without loss of generality, if screen resolution is 480 × 800, image sequence length is 5, then switching times is 4, and the span of speed is namely 0 ~ 933, key space can be obtained for (480 × 800 × 480 × 800 × 933) 4≈ 3.58 × 10 56, comparatively PIN (Personal Identification Number) key space is 10 8have and greatly expanded.If the resolution of touch-screen increases, key space also can increase further.
The above; be only the present invention's preferably embodiment, but protection scope of the present invention is not limited thereto, is anyly familiar with those skilled in the art in the technical scope that the present invention discloses; the change that can expect easily or replacement, all should be encompassed within protection scope of the present invention.Therefore, protection scope of the present invention should be as the criterion with the protection domain of claim.

Claims (9)

1., based on the smart phone user authentication method that multiple image switches, it is characterized in that: comprise user registration course and user authentication process;
(1) first described user registration course needs set up user name and select image sequence, then user switches image successively and records this user's finger motion characteristic sequence S, the distance between twice finger motion characteristic sequence S and S ' is characterized by Euclidean distance D, further judgement Euclidean distance D and given threshold size, finally extract the condition code T of this user;
(2) described user authentication process comprises and inputs user name, then the image needing user to switch is shown and recording user finger motion characteristic sequence S, compared with given threshold value by the distance D` calculated between S and user's characteristic code T, identify the object of cellphone subscriber; Distance D` between described S and user's characteristic code T adopts Euclidean distance formula, if S=is (S 1, S 2..., S n-1, S n), T=(T 1, T 2..., T n-1, T n), then:
D ` = ( S 1 - T 1 ) 2 + ( S 2 - T 2 ) 2 + ... + ( S n - T n ) 2 .
2. the smart phone user authentication method switched based on multiple image according to claim 1, is characterized in that: described selection image sequence should be kept in smart mobile phone embedded memory card, and picture format is not limit.
3. the smart phone user authentication method switched based on multiple image according to claim 1, is characterized in that: the movement locus that described user switches the finger of image is successively unrestricted.
4. the smart phone user authentication method switched based on multiple image according to claim 1, it is characterized in that: described user's finger motion characteristic sequence S, it records content is at every turn a five-tuple; Described five-tuple comprises the starting point coordinate of finger motion, terminal point coordinate and speed;
Described starting point coordinate, terminal point coordinate directly can read touchscreen events attribute and obtain, and described speed gets the average velocity between this period of moving period, are obtained divided by interval time by the distance between zequin and terminal.
5. the smart phone user authentication method switched based on multiple image according to claim 1, is characterized in that: describedly characterize distance between twice finger motion characteristic sequence S and S ', if S=is (S by Euclidean distance D 1, S 2..., S n-1, S n), S '=(S ' 1, S ' 2..., S ' n-1, S ' n), then the distance between S and S ' is:
D = ( S 1 - S 1 ′ ) 2 + ( S 2 - S 2 ′ ) 2 + ... + ( S n - S n ′ ) 2 .
6. the smart phone user authentication method switched based on multiple image according to claim 1, it is characterized in that: described judgement Euclidean distance D and given threshold size: if D is less than given threshold value, the then finger motion characteristic sequence coupling of twice record, the condition code T of user can be adopted as, otherwise, again input the finger motion characteristic sequence of user.
7. the smart phone user authentication method switched based on multiple image according to claim 1, is characterized in that: the mean value that described user's characteristic code T gets for S and S ' corresponding element.
8. the smart phone user authentication method switched based on multiple image according to claim 1, is characterized in that: describedly the user name of this smart mobile phone is set to default value when inputting user name.
9. the smart phone user authentication method switched based on multiple image according to claim 1, it is characterized in that: described D` compares with given threshold value, if D is less than given threshold value, then the finger motion characteristic sequence of user's input mates with the user's characteristic code preserved in advance, authentication success, otherwise authentification failure.
CN201310485761.6A 2013-10-16 2013-10-16 Based on the smart phone user authentication method that multiple image switches Expired - Fee Related CN103530542B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201310485761.6A CN103530542B (en) 2013-10-16 2013-10-16 Based on the smart phone user authentication method that multiple image switches

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201310485761.6A CN103530542B (en) 2013-10-16 2013-10-16 Based on the smart phone user authentication method that multiple image switches

Publications (2)

Publication Number Publication Date
CN103530542A CN103530542A (en) 2014-01-22
CN103530542B true CN103530542B (en) 2016-04-06

Family

ID=49932546

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201310485761.6A Expired - Fee Related CN103530542B (en) 2013-10-16 2013-10-16 Based on the smart phone user authentication method that multiple image switches

Country Status (1)

Country Link
CN (1) CN103530542B (en)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104239761B (en) * 2014-09-15 2017-06-27 西安交通大学 The identity for sliding behavioural characteristic based on touch screen continues authentication method
JP5991793B1 (en) * 2016-02-29 2016-09-14 株式会社ｕｎｅｒｒｙ Program, information processing apparatus and system

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102779251A (en) * 2012-06-29 2012-11-14 鸿富锦精密工业（深圳）有限公司 Electronic device and encrypting/decrypting method thereof
CN103246453A (en) * 2012-02-01 2013-08-14 上海博路信息技术有限公司 Unlocking method based on picture region actions

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103246453A (en) * 2012-02-01 2013-08-14 上海博路信息技术有限公司 Unlocking method based on picture region actions
CN102779251A (en) * 2012-06-29 2012-11-14 鸿富锦精密工业（深圳）有限公司 Electronic device and encrypting/decrypting method thereof

Also Published As

Publication number Publication date
CN103530542A (en) 2014-01-22

Similar Documents

Publication Publication Date Title
Li et al. Using data augmentation in continuous authentication on smartphones
CN104765995B (en) Smart machine identity identifying method and client based on contact action
US10643055B2 (en) Fingerprint recognition method and system capable of improving fingerprint recognition rate
Shahzad et al. Behavior based human authentication on touch screen devices using gestures and signatures
CN101197665B (en) Dynamic password generation method and device thereof
CN102117392A (en) Gesture-based signature authentication
CN103595538B (en) Identity verification method based on mobile phone acceleration sensor
EP3203681B1 (en) Sequential biometric cryptosystem and sequential biometric cryptographic processing method
CN104408341A (en) Smart phone user identity authentication method based on gyroscope behavior characteristics
CN105025018B (en) A kind of method carrying out safety verification in communication process
CN102946481A (en) Method and system for unlocking human face expression
CN105068743A (en) Mobile terminal user identity authentication method based on multi-finger touch behavior characteristics
CN104050406A (en) Method and terminal equipment for carrying out authentication through fingerprint combinations
CN105159475B (en) A kind of characters input method and device
CN104182669A (en) Mobile terminal starting system and mobile terminal starting method
WO2015169151A1 (en) Touch screen unlocking method, device and electronic device, display and mobile terminal
CN101673329B (en) Establishment method of biometric data, electronic device and computer program product thereof
Temper et al. Touch to authenticate—Continuous biometric authentication on mobile devices
Siirtola et al. Effect of context in swipe gesture-based continuous authentication on smartphones
US20120093374A1 (en) Electronic device and method for identifying use by unauthorized users
CN103530542B (en) Based on the smart phone user authentication method that multiple image switches
CN203165055U (en) Access remote controller
CN107426397A (en) Model training method and auth method based on user behavior feature
Alpar Biometric touchstroke authentication by fuzzy proximity of touch locations
Zhang et al. Multimodal continuous user authentication on mobile devices via interaction patterns

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
C14 Grant of patent or utility model
GR01 Patent grant
CF01 Termination of patent right due to non-payment of annual fee
CF01 Termination of patent right due to non-payment of annual fee

Granted publication date: 20160406

Termination date: 20181016