WO2012141288A1 - 携帯端末及び把持特徴学習方法 - Google Patents
携帯端末及び把持特徴学習方法 Download PDFInfo
- Publication number
- WO2012141288A1 WO2012141288A1 PCT/JP2012/060128 JP2012060128W WO2012141288A1 WO 2012141288 A1 WO2012141288 A1 WO 2012141288A1 JP 2012060128 W JP2012060128 W JP 2012060128W WO 2012141288 A1 WO2012141288 A1 WO 2012141288A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- template
- gripping feature
- sample
- gripping
- correction
- Prior art date
Links
Images
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
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B1/00—Comparing elements, i.e. elements for effecting comparison directly or indirectly between a desired value and existing or anticipated values
- G05B1/01—Comparing elements, i.e. elements for effecting comparison directly or indirectly between a desired value and existing or anticipated values electric
-
- 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L63/00—Network architectures or network communication protocols for network security
- H04L63/08—Network architectures or network communication protocols for network security for authentication of entities
- H04L63/0861—Network architectures or network communication protocols for network security for authentication of entities using biometrical features, e.g. fingerprint, retina-scan
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L9/00—Cryptographic mechanisms or cryptographic arrangements for secret or secure communications; Network security protocols
- H04L9/32—Cryptographic mechanisms or cryptographic arrangements for secret or secure communications; Network security protocols including means for verifying the identity or authority of a user of the system or for message authentication, e.g. authorization, entity authentication, data integrity or data verification, non-repudiation, key authentication or verification of credentials
- H04L9/3226—Cryptographic mechanisms or cryptographic arrangements for secret or secure communications; Network security protocols including means for verifying the identity or authority of a user of the system or for message authentication, e.g. authorization, entity authentication, data integrity or data verification, non-repudiation, key authentication or verification of credentials using a predetermined code, e.g. password, passphrase or PIN
- H04L9/3231—Biological data, e.g. fingerprint, voice or retina
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M1/00—Substation equipment, e.g. for use by subscribers
- H04M1/66—Substation equipment, e.g. for use by subscribers with means for preventing unauthorised or fraudulent calling
- H04M1/667—Preventing unauthorised calls from a telephone set
- H04M1/67—Preventing unauthorised calls from a telephone set by electronic means
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W12/00—Security arrangements; Authentication; Protecting privacy or anonymity
- H04W12/06—Authentication
- H04W12/065—Continuous authentication
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L2209/00—Additional information or applications relating to cryptographic mechanisms or cryptographic arrangements for secret or secure communication H04L9/00
- H04L2209/80—Wireless
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W12/00—Security arrangements; Authentication; Protecting privacy or anonymity
- H04W12/60—Context-dependent security
- H04W12/68—Gesture-dependent or behaviour-dependent
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W88/00—Devices specially adapted for wireless communication networks, e.g. terminals, base stations or access point devices
- H04W88/02—Terminal devices
Definitions
- the present invention relates to a mobile terminal and a gripping feature learning method for acquiring a gripping feature sample when the mobile terminal is gripped and performing identity authentication.
- Patent Document 1 the position of the mobile terminal held by the user at the time of user authentication is acquired by a plurality of pressure sensors, and the user grips the position after the user authentication.
- a portable terminal that invalidates data necessary to receive provision of a service input by a user when a change exceeding a certain level occurs, and cancels the validity of the already performed personal authentication. For this reason, even if the mobile terminal is stolen while performing personal authentication and inputting data necessary to receive the provision of services, the personal authentication and user The data entered by becomes invalid. In this way, in order to receive the provision of the service after the personal authentication is invalidated, the personal authentication is required again, so that unauthorized use by a third party can be effectively prevented.
- the person authentication method using biometric information such as Patent Document 1 is preliminarily provided with information called a template, which is a grip pressure value sequence characteristic to the principal by learning from the acquired grip pressure distribution (grip pressure value sequence). This is executed by comparing a sample of a gripping pressure value sequence (hereinafter referred to as a gripping feature sample or simply a sample) acquired and registered by the sensor at the time of authentication with a registered template. A lot of pattern recognition technology is used for this comparison. In pattern recognition, the degree of similarity between a template and a sample is obtained using the distance between vectors. Examples of distances often used for biometric authentication include Mahalanobis general distance and Hamming distance.
- an object of the present invention is to provide a mobile terminal that can use the personal authentication template used in the mobile terminal before the model change even in the mobile terminal after the model change.
- the portable terminal of the present invention is characterized in that a gripping feature sample when gripped is acquired by a sensor array composed of a plurality of sensors, and personal authentication is performed using an old personal authentication template.
- a template storage unit, a feature segment extraction unit, a segment position correction unit, a template collation unit, and a template storage unit are provided.
- the gripping feature sample acquisition unit acquires a gripping feature sample from the sensor array.
- the old template storage unit stores a personal authentication template used for personal authentication in a mobile terminal used in the past as an old template.
- the feature segment extraction unit extracts a feature segment from the old template, and compares the old template with the gripped feature sample for each feature segment to calculate a distance.
- the segment position correction unit deforms and corrects the old template in the feature segment whose distance calculated by the feature segment extraction unit is not less than a predetermined value, and generates a correction template.
- the template collation unit collates the correction template with the acquired gripping feature sample and calculates the inter-vector distance.
- the template storage unit stores the correction template as a personal authentication template when the inter-vector distance between the correction template and the acquired gripping feature sample is equal to or less than a predetermined value.
- the mobile terminal of the present invention since the personal authentication template used in the mobile terminal before the model change can be used even in the mobile terminal after the model change, the user authentication template every time the model of the mobile terminal is changed. There is no need to learn again, and the convenience of the user is improved.
- the figure which shows the portable terminal 800d provided with a pressure sensor array.
- FIG. 1 is a block diagram showing a configuration of a mobile terminal according to Embodiment 1.
- 5 is a flowchart showing a user authentication template learning operation of the mobile terminal according to the first embodiment.
- 5 is a flowchart illustrating an authentication operation of the mobile terminal according to the first embodiment.
- 10 is a flowchart showing an old template diversion operation of the mobile terminal according to the second embodiment.
- gripping feature samples acquired by the mobile terminals 800 and 800 ′ shown in FIG. 14 and FIG. 15 as functional configuration blocks according to all embodiments of the present invention will be described. Humans are inherently different in (1) finger length, (2) strength of grip, etc., and (3) habit when holding a mobile terminal, etc.
- the gripping feature is very excellent as biometric information used for personal authentication. Specifically, the gripping feature authentication has the same degree of accuracy as general face authentication for both the person rejection rate and the other person acceptance rate.
- the gripping feature sample include a gripping pressure distribution, a gripping shape distribution, and a gripping heat / heat distribution.
- the gripping pressure distribution can be acquired by arranging a plurality of pressure sensors on the surface of the mobile terminal 800, 800 ′ in a planar or linear distribution.
- the grip shape distribution can be acquired by the planar or linear distribution arrangement of the CCD (CMOS) sensor.
- CMOS CCD
- the gripping pressure distribution is used as a specific example as the gripping feature sample, and the pressure sensor array is linearly arranged on the outer periphery of the mobile terminals 800 and 800 ′, and each acquired by the pressure sensor array.
- a pressure value sequence in a predetermined order of the pressure values at the positions is used as a gripping feature sample.
- the gripping feature sample may be acquired at the same time as the sampling trigger is generated, for example.
- the sampling trigger is a preset timing for acquiring gripping feature samples. For example, when it is desired to acquire a gripping feature sample when the browser software of the mobile terminals 800 and 800 ′ is activated, the sampling trigger can be set to “browsing browser activation key pressed”. This sampling trigger “when the browser is activated and the determination key is pressed” is used when the browser is activated and when the user presses the determination key of the mobile terminal 800 or 800 ′, this operation is used as a sampling trigger to immediately acquire a gripping feature sample. It means that.
- a sampling trigger may be automatically generated to acquire a gripping feature sample.
- the gripping feature sample necessary for learning the personal authentication template using the sampling trigger has the following advantages. If the sampling trigger is used, the gripping feature sample is automatically acquired and accumulated by using the user's own key operation as an acquisition timing. As a result, it is possible to acquire gripping feature samples in a state where the user is unconscious and using the terminal in the most natural state and in a relaxed state, and the variance of the observation values of the gripping feature samples can be reduced. In addition, when the message indicating that the acquisition of the gripping feature sample is started is displayed in the use preparation guide based on the display of the mobile terminal, the user who has received the message is holding, and the user does not use the usual gripping method.
- the personal authentication template is a template representing the gripping characteristics of the user.
- the personal authentication template is learned from the average value of the above-described gripping feature samples acquired from the user.
- the learned personal authentication template is collated with a gripping feature sample newly acquired after learning. Whether or not the gripping feature sample newly acquired after learning is the same person as the personal authentication template is determined based on the magnitude of the value (vector distance, for example, Mahalanobis general distance) obtained by the collation.
- x i, j be the pressure value acquired by the i-th sensor in the j-th measurement to be used for learning.
- n the maximum number of sensors and m is the maximum number of gripping feature sample acquisitions used for learning.
- m the maximum number of gripping feature sample acquisitions used for learning.
- Each is an integer of 2 or more.
- the mean, variance, and vector of pressure values are defined as follows:
- the average vector of gripping feature samples is used as a personal authentication template.
- the subscript "le” is added to the personal authentication template.
- the Mahalanobis generalized distance f 1 is expressed by the following equation.
- the Euclidean distance f 2 is defined as follows.
- the Manhattan distance f 3 is defined as follows.
- the above three distance references can be determined in common using the determination formulas shown below.
- the subscript “self” is attached to the data of the person acquired for the determination process, and the subscript “oth” is attached to the data of the other person. If the threshold value for determining another person is defined as x thre , the expression for determining another person can be expressed as follows.
- ⁇ About the mobile terminals 800a, 800b, 800b ′, 800c, 800d> 1, 2, 5, 6, and 7 show different types of portable terminals 800a, 800b, 800b ′, 800c, and 800d as specific examples of their shapes.
- the mobile terminals 800a, 800b, 800b ′, 800c, and 800d have all the functions of the mobile terminals 800 and 800 ′ according to the embodiments of the present invention.
- ⁇ Reference point used for sensor position specification in this specification> Reference points used when specifying the sensor position in the present invention will be described with reference to FIGS.
- the mobile terminals 800a and 800b in FIGS. 1 and 2 are different types of smartphones.
- the portable terminals 800c and 800d in FIGS. 6 and 7 are not a smartphone but an old foldable portable terminal and a sliding portable terminal.
- the body 101 has a pressure sensor array Ra on the right side, a pressure sensor array Ua on the upper side, a pressure sensor array La on the left side, and a pressure sensor array Ba on the lower side.
- the pressure sensor array Ra includes seven pressure sensors 105a-1 to 105a-7.
- the pressure sensor array Ua includes four pressure sensors 105a-8 to 105a-11.
- the pressure sensor array La is assumed to include seven pressure sensors 105a-12 to 105a-18.
- the pressure sensor array Ba is assumed to include four pressure sensors 105a-19 to 105a-22.
- the sensor array refers to the entire sensor array when these sensor arrays Ra, Ua, La, and Ba are not specified.
- the arrangement and number of sensors are arbitrary and are not limited to the configuration shown in FIG. Further, the arrangement of the sensors in FIG. 1 is merely an example for making the following description easy to understand.
- the reference point OX used for specifying the sensor position is, for example, the touch panel (display surface 102). It can be a diagonal intersection (position indicated by a cross in FIG. 1).
- each sensor position has a reference point OX as an apex angle, and a straight line passing through the reference point OX and the lower right corner of the body 101 and a straight line passing through the reference point OX and the center of the pressure sensor are formed. It can be expressed as an angle (counterclockwise).
- t-th mobile terminal 800a (t is an arbitrary natural number) shall be denoted as angle angle .theta.a t to locate the pressure sensor 105a-t of.
- angle angle .theta.a the fifth angle of the pressure sensor 105a-5 of the pressure sensor array Ra as shown in FIG. 1 is referred to as angle .theta.a 5.
- a portable terminal 800b in FIG. 2 has a substantially rectangular plate-like body 101 like the portable terminal 800a in FIG. 1, and has a rectangular display surface 102 that functions as a touch panel on its upper surface, a plurality of keys 104, and a camera lens 106. Is provided. Furthermore, the pressure sensor array Rb composed of five pressure sensors 105b-1 to 105b-5 on the right side surface of the body 101, the pressure sensor array Ub composed of three pressure sensors 105b-3 to 105b-8 on the upper side surface, and the left side surface It is assumed that a pressure sensor array Lb composed of five pressure sensors 105b-9 to 105b-13 and a pressure sensor array Bb composed of three pressure sensors 105b-14 to 105b-16 are provided on the lower surface.
- the reference point OX used for specifying the sensor position can be, for example, a diagonal intersection of the touch panel (display surface 102) (position indicated by a cross in FIG. 1).
- each sensor position includes a straight line passing through the reference point OX and the lower right corner of the body 101, and a straight line passing through the reference point OX and the center of the pressure sensor. It can be expressed as an angle (counterclockwise).
- an angle specifying the position of the t-th (t is an arbitrary natural number) pressure sensor 105b-t of the mobile terminal 800b is expressed as an angle ⁇ b t . Therefore sixth angle of the pressure sensor 105b-6 of the pressure sensor array Rb as shown in FIG. 2 is referred to as angle .theta.b 6.
- the portable terminal 800c has a substantially rectangular plate-like body 101A. And a rectangular plate-like cover 101B that is foldably attached to one short side of the body 101A.
- a rectangular display surface 102 is provided on the inner side surface of the cover 101B, an enter key 103A is provided at the center of the upper surface of the body 101A on the cover 101B side, and an input key 107 is provided therebelow.
- the pressure sensor array Rc composed of nine pressure sensors 105c-1 to 105c-9 on the right side of the body 101A
- the pressure sensor array Lc composed of nine pressure sensors 105c-10 to 105c-18 on the left side
- a pressure sensor array Bc composed of five pressure sensors 105c-19 to 105c-23 is provided.
- the reference point OX used for specifying the sensor position can be, for example, the center of the enter key 103c (position indicated by a cross in FIG. 6).
- the sensor position is, for example, as shown in FIG. 6, with a reference point as the apex angle of a corner, a straight line connecting the reference point OX and the lower right corner of the body 101 ⁇ / b> A, and a straight line passing through the reference point OX and the center of the pressure sensor.
- An angle to locate the t-th pressure sensor 105c-t of the mobile terminal 800c shall be referred to as angle .theta.c t. Therefore, as shown in FIG. 6, for example, the angle of the seventh pressure sensor 105c- 7 is expressed as an angle ⁇ c7.
- the portable terminal 800d has a substantially rectangular plate-like body 101A. And a rectangular plate-like cover 101B slidably mounted on the body 101A. A rectangular display surface 102 and an enter key 103d are provided on the outer surface of the cover 101B, and an input key 107 is provided on the upper surface of the body 101A. Further, the pressure sensor array Rd including seven pressure sensors 105d-1 to 105d-7 on the right side surface of the body 101A, the pressure sensor array Ld including seven pressure sensors 105d-8 to 105d-14 on the left side surface, and the lower side surface. It is assumed that a pressure sensor array Bd including five pressure sensors 105d-15 to 105d-19 is provided.
- the reference point OX used for specifying the sensor position can be, for example, the center of the decision key 103d (position indicated by a cross in FIG. 7).
- the sensor position is, for example, as shown in FIG. 7, with the reference point OX being the apex angle of the corner, a straight line connecting the reference point OX and the lower right corner of the body 101A, and a straight line passing through the reference point OX and the center of the pressure sensor. It can be expressed by the angle formed by (counterclockwise).
- An angle to locate the t-th pressure sensor 105d-t of the mobile terminal 800d shall be referred to as an angle [theta] d t. Therefore, as shown in FIG.
- model change refers to changing the model of a mobile terminal to a different model when transferring the contract to a different calling company when only changing the model of the mobile terminal to a different model while continuing the contract with the same calling company.
- model change it includes a case where the mobile terminal is deposited with a call company for reasons such as failure, and the model is temporarily changed to an alternative mobile terminal that is temporarily lent out by the call company.
- FIG. 3 is a diagram showing a gripping state of the mobile terminal 800a of FIG.
- FIG. 4 is a diagram showing a gripping state of the mobile terminal 800b of FIG.
- FIG. 8 is a diagram showing a gripping state of the mobile terminal 800c of FIG.
- FIG. 9 is a diagram showing a gripping state of the mobile terminal 800d of FIG.
- the mobile terminal 800a and the mobile terminal 800b are smartphones.
- the mobile terminal 800c and the mobile terminal 800d are old-type mobile terminals other than smartphones. As shown in FIG. 3 and FIG.
- FIG. 5 is a diagram illustrating a gripping state of the mobile terminal 800b ′.
- the model change is performed from the portable terminal 800a to the portable terminal 800b ′, and the portable terminal 800b ′ after the model change has the sensor position (relative position from the reference point) with the portable terminal 800a before the model change.
- the operation key for example, camera starting button etc.
- FIG. 12A is a diagram illustrating a personal authentication template before the model change when the grip state is different before and after the model change
- FIG. 12B is a diagram illustrating a grip feature sample after the model change.
- FIG. 12A shows an old template
- FIG. 12B shows measured values of the gripping pressure distribution when the user grips the mobile terminal 800b '.
- the vertical axis represents the gripping pressure (kPa)
- the horizontal axis represents the angle (°) that defines the above-mentioned reference point as the apex angle.
- the positions corresponding to the thumb, index finger, middle finger, ring finger, and little finger are indicated in the graph by arrows indicating THM, IND, MID, ANN, and LIT, respectively.
- the values of the old template corresponding to each pressure sensor are indicated by black squares, and the measured values of the holding pressure when the portable terminal 800b 'is held by each pressure sensor in FIG. 12B are indicated by white triangles.
- a line obtained by smoothing fitting each measurement point is represented by a solid line in FIG. 12A and a broken line in FIG. 12B.
- the gripping feature of the user is that the position of the middle finger is shifted in the direction of the index finger, and the features of the other fingers are hardly changed.
- the peak position of the gripping pressure generated by pressing the middle finger (MID) in FIG. 12B is shifted in the positive angle direction from the position of the middle finger in FIG.
- the correction of the change in gripping characteristics caused by the change in gripping state before and after the model change will be described below.
- the mobile terminals 800 and 800 ′ shown as functional blocks include a feature segment extraction unit 830 and a segment position correction unit 835.
- the feature segment extraction unit 830 extracts feature segments from the old template, and the segment position correction unit 835 performs correction of the old template by deformation correction described later.
- 13A is a diagram for explaining feature segment extraction by the feature segment extraction unit 830
- FIG. 13B is a diagram for explaining deformation correction by the segment position correction unit 835.
- a curve obtained by smoothing the value of the old template with respect to the angular position of each pressure sensor using, for example, a trigonometric function or another desired function is obtained by a solid line on the mobile terminal 800b ′ after the model change. Measurement points of the gripping pressure are schematically shown by white triangles.
- the curve obtained by fitting is obtained as a digital value of gripping pressure for a series of discrete angular positions (digital values) including sensor positions and positions between sensors.
- feature segments are extracted from the old template.
- Well-known edge detection or the like can be used to extract feature segments. For example, a zero point having a positive slope of a first derivative of a curve can be extracted, and each region divided by this point can be used as a feature segment.
- the region of approximately 0 ° to 30 ° corresponding to the pressing position of the ring finger is divided into segments indicated by broken lines so as to include the start point, peak position, and end point of the ring finger pressing range. The same applies to the middle finger and the index finger.
- the distance between the old template and the measurement point of the gripping pressure acquired in the mobile terminal 800b 'after the model change is measured.
- This distance is, for example, the value of the gripping pressure value of each sensor angular position belonging to each feature segment of the old template and each measurement point of the gripping pressure belonging to the same feature segment acquired in the mobile terminal 800b ′ after the model change.
- the inter-vector distance expressed in the same manner as Equation (4), (5), (6),
- the angular position that serves as the upper boundary of each feature segment belongs to that feature segment, but the absolute value of the difference between the template value and the measured gripping pressure value is greater than or equal to a predetermined value at the intermediate angular positions at both ends of the segment.
- the angular positions at both ends of the segment are also included in the segment. It is possible to determine whether or not the gripping feature has changed depending on whether or not the distance for each feature segment thus obtained exceeds a predetermined threshold value. For example, in FIG. 13A, in the region of approximately 30 ° to 60 ° corresponding to the pressing position of the middle finger in the mobile terminal 800a before the model change, the position of the middle finger changes before and after the model change, so a solid line graph (old White triangular points (measurement points of gripping pressure acquired in the portable terminal 800b after the model change) are not on the template. Therefore, the distance of the feature segment corresponding to the pressing position of the middle finger is larger than the distance in other feature segments. In FIG.
- a cross mark is displayed for a feature segment whose distance exceeds a predetermined threshold value
- a ⁇ mark is displayed for a feature segment whose distance does not exceed a predetermined threshold value. It is.
- the following deformation correction is applied to the old template in the feature segment marked with a cross.
- the deformation correction is performed by shifting the old template in the feature segment whose distance exceeds the threshold, such as the feature segment of approximately 30 ° to 60 ° in FIG. 13A, in the horizontal axis direction. Specifically, the template of the feature segment whose distance exceeds the threshold is shifted between the template and the measurement sample gripping pressure value at each segment position shifted by one sensor angular interval in the direction in which the angular position increases or decreases in the angular position. Calculate the distance between vectors and shift the segment template to the angular position where the distance is minimized.
- the curve obtained by smooth fitting the values of the old template was used to divide the template into segments.
- a broken line that simply connects the values of the old template with straight lines is used. It may be used to perform segment division. In this way, the deviation of the gripping feature before and after the model change is obtained in the feature segment unit, and if the deviation exceeds the threshold value, the gripping feature is partially changed by performing deformation correction that shifts the old template in the feature segment unit. Even if it is deformed, the old template can be used by correcting this effectively.
- FIG. 1 is a diagram showing a portable terminal 800b having a pressure sensor array.
- the user initially uses the portable terminal 800a, has already learned the personal authentication template by the learning function provided in the portable terminal 800a, and then the user has changed the model from the portable terminal 800a to the portable terminal 800b.
- the mobile terminal 800b is a smartphone similarly to the mobile terminal 800a.
- the pressure sensor Ra on the right side surface of the portable terminal 800a includes seven pressure sensors 105a-1 to 105a-7.
- the pressure sensor Rb on the right side surface of the mobile terminal 800b includes five pressure sensors 105b-1 to 105b-5, and the number of pressure sensors of the mobile terminal 800b is smaller than the number of sensors of the mobile terminal 800a.
- the pressure sensor Ua on the upper side of the mobile terminal 800a includes four pressure sensors 105a-8 to 105a-11, whereas the pressure sensor Ub on the upper side of the mobile terminal 800b has three pressure sensors 105b-6.
- the number of pressure sensors of the portable terminal 800b is smaller than the number of sensors of the portable terminal 800a.
- the position and quantity of the pressure sensor cannot be arranged equally in all models due to its structural design.
- the sensor position, quantity, and the like change accordingly.
- FIGS. 3 and 4 each illustrate a state in which the user of the mobile terminal 800a holds the mobile terminal 800a before the model change and the mobile terminal 800b after the model change.
- FIG. 10A shows a personal authentication template before the model change when the sensor position is different before and after the model change
- FIG. 10B shows an example of a gripping feature sample after the model change
- FIG. 10A shows a personal authentication template (hereinafter referred to as an old template) learned in the mobile terminal 800a before the model change
- FIG. 10B shows a gripping pressure distribution (gripping feature sample) when the mobile terminal 800b after the model change is gripped. Each is shown.
- the vertical axis represents the gripping pressure (kPa)
- the horizontal axis represents the angle (°) that defines the above-mentioned reference point as the apex angle.
- the positions corresponding to the thumb, index finger, middle finger, ring finger, and little finger are indicated in the graph by arrows indicating THM, IND, MID, ANN, and LIT, respectively.
- the value of the old template in each pressure sensor is indicated by a black square, and the measured value of the gripping pressure when the portable terminal 800b is gripped by each pressure sensor is indicated by a white circle.
- a curve obtained by smoothing each measurement point is represented by a solid line in FIG. 10A and a broken line in FIG. 10B.
- the gripping characteristics of the user are almost unchanged before and after the model change.
- the way of gripping the user's mobile terminal does not change greatly before and after the model change, the external shapes of the graphs in FIGS. 10A and 10B are different because the finger changes the position of the mobile terminal with a strong pressure because the sensor position changes. This is because whether or not there is a sensor in the area to be pressed changes.
- the pressing position of the index finger is approximately 90 °, as is clear from the graph of FIG. 10A
- the portable terminal 800a measures the peak value because the pressure sensor 105a-6 exists at this position. Can do.
- the mobile terminal 800b after the model change as is apparent from the graph of FIG.
- the position at which the index finger is pressed approximately 90 ° is located between the pressure sensors 105b-4 and 105b-5. This is because the pressure sensors 105b-4 and 105b-5 cannot detect the peak value of the pressing force of the index finger. In this way, when the position of the pressure sensor arranged differs depending on the model before and after the model change, the acquired gripping pressure distribution is different, but actually the approximate gripping pressure distribution by the same user is measured at different positions. It ’s just a difference.
- FIG. 6 is a diagram showing a portable terminal 800c having a pressure sensor array.
- FIG. 7 is a diagram showing a portable terminal 800d having a pressure sensor array.
- the mobile terminal 800c is not a smartphone but an old foldable mobile terminal.
- the mobile terminal 800d is not a smartphone but an old slide type mobile terminal.
- the sensor position of the seventh pressure sensor of the mobile terminal 800c is ⁇ c 7
- the sensor position of the seventh pressure sensor of the mobile terminal 800d is ⁇ d 7
- ⁇ c 7 is ⁇ d 7 It is a larger value.
- the model key change (point indicated by a cross) in the model change from the portable terminal 800c to the portable terminal 800d is compared.
- the gripping features on the appearance are not greatly changed. Therefore, even in this case, when the position of the pressure sensor is different before and after the model change, the acquired gripping pressure distribution is different, but in reality, it is only a difference by measuring the approximate gripping pressure distribution by the same user at different positions.
- a portable terminal 800 ′ shown as a functional block in FIG. 15 according to the second embodiment of the present invention includes a sensor position storage unit 810 and a sensor position correction unit 815. Other details will be described later.
- the sensor position correction unit 815 corrects the change in the grip pressure distribution caused by the position change of the pressure sensor by interpolation. This correction will be described in detail with reference to FIGS. 11A and 11B.
- FIG. 11A shows the graphs of FIGS. 10A and 10B superimposed on each other.
- the solid line graph is the graph of FIG.
- the broken line graph is the graph of FIG. 10B, that is, the grip pressure distribution of the mobile terminal 800b after the model change (grip feature sample). It is.
- the measurement points of the gripping pressure by the pressure sensor of the portable terminal 800b after the model change are indicated by white circles.
- the measurement point (white circle) by the pressure sensor array of the portable terminal 800b is ideally a fitting curve of the old template before the model change. Should be located at or near the top. Therefore, as shown in FIG.
- the gripping pressure value at the sensor angle position ⁇ b t (one-dot chain line in the figure) of the mobile terminal 800 b after the model change in the fitting curve of the old template already obtained before the model change is an interpolation value.
- the predicted value of the personal authentication template at the new sensor position (white circle in FIG. 11B)
- these predicted measurement points (white circle in FIG. 11B) can be used as the personal authentication template after the model change.
- the mobile terminal 800 according to a second embodiment of the present invention 'it is necessary to store the sensor position .theta.b t of the mobile terminal 800b in the changed model to the sensor position storage unit 810.
- the sensor position is not limited to the angle described above, but it is desirable to use at least the center of the touch panel (decision key) as a reference point. This is because if the center position of the touch panel (decision key) is used as a reference point, the gripping characteristics of the user are stabilized before and after the model change unless there is a large change in the mobile terminal size.
- the old template by performing interpolation using the sensor position on the old template, it can be converted to the personal authentication template in the mobile terminal 800b after the model change, and thus the old template can be used.
- This method can be used when changing to a model that is equal to or less than the number of pressure sensors of the model before the change, but the opposite is not preferable because the estimation error increases.
- a high-accuracy user authentication template can be acquired by using normal user authentication template learning described later together.
- the old template can also be corrected when a change in gripping state and a change in position of the pressure sensor occur before and after the model change.
- feature segment extraction and deformation correction are performed on the old template.
- the comparison between the old template after the deformation correction and the gripping feature sample acquired after the model change is performed to obtain the vector distance.
- interpolation is performed for the old template after the deformation correction based on the sensor position stored in the sensor position storage unit. In this way, even when the change in the gripping state and the change in the position of the pressure sensor occur simultaneously before and after the model change, the old template can be corrected and used in the portable terminal after the model change.
- FIG. 14 is a block diagram illustrating a configuration of the mobile terminal 800 according to the present embodiment.
- FIG. 16 is a flowchart (F1) showing the old template diversion operation of the mobile terminal 800 according to the present embodiment.
- the mobile terminal 800 of this embodiment includes a pressure sensor array 105, a gripping feature sample acquisition unit 120, a switching unit 125, a sample temporary storage unit 130, an old template storage unit 805, a feature segment extraction unit 830, a segment A position correction unit 835, a template collation unit 820, a template storage unit 155, a template learning unit 135, a personal authentication unit 160, and a lock unit 180 are provided. It is assumed that the mobile terminal 800 can be switched between the learning state and the authentication state by the switching unit 125 included in the mobile terminal 800. Here, it is assumed that the switching unit 125 is set to the learning state (connected to the sample temporary storage unit 130 side).
- the gripping feature sample acquisition unit 120 acquires gripping feature samples from the pressure sensor array 105 (S120).
- the sample temporary storage unit 130 temporarily stores the gripping feature sample acquired by the gripping feature sample acquisition unit 120.
- the old template storage unit 805 stores a personal authentication template used for personal authentication in a mobile terminal used in the past as an old template.
- the feature segment extraction unit 830 extracts feature segments from the old template, and compares the old template with the gripped feature sample for each feature segment to calculate the distance (S830) (details are ⁇ feature segment extraction, segment position (Refer to> column for correction of).
- the segment position correcting unit 835 generates a correction template by correcting the deformation by shifting the old template in the feature segment whose distance calculated by the feature segment extracting unit 830 is not less than or equal to a predetermined value (S835). (See the section on segment extraction and segment position correction).
- the template collation unit 820 collates the correction template with the acquired gripping feature sample in step S835, and calculates the vector distance (S825). If the inter-vector distance between the correction template and the acquired gripping feature sample is equal to or smaller than a predetermined value (S825Y), the template storage unit 155 stores the correction template as a personal authentication template (S155).
- the vector distance used here is the Mahalanobis general distance, which is a distance often used for biometric authentication.
- the deformation correction data (the position of the feature segment that requires deformation correction, the shift direction of the feature segment, the shift amount, etc.) of the mobile terminal 800 of this embodiment is recorded in a server or the like, and another user changes the model. Even when the gripping feature changes, the mobile terminal 800 after the model change owned by another user accesses the server to acquire the corresponding deformation correction data, and based on the acquired deformation correction data, the old template Deformation correction may be performed.
- the mobile terminal 800 of this embodiment performs deformation correction on the old template for each feature segment, the old template can be used even when the gripping feature changes before and after the model change. It is not necessary to re-learn the user authentication template every time the model is changed, and the convenience of the user is improved.
- FIG. 17 is a flowchart (F2) illustrating the personal authentication template learning operation of the mobile terminal 800 according to the present embodiment.
- F2 a flowchart illustrating the personal authentication template learning operation of the mobile terminal 800 according to the present embodiment.
- the switching unit 125 is set to the learning state (connected to the sample temporary storage unit 130 side).
- the gripping feature sample acquisition unit 120 acquires a gripping feature sample from the pressure sensor array 105 (S120).
- the number of acquired gripping feature samples is Sm
- the learning start sample number is SFm.
- the learning start sample number SFm is predetermined as the number of samples necessary for learning the personal authentication template. This is because there is a high possibility that a sufficiently accurate personal authentication template cannot be generated even if learning of the personal authentication template is performed with a small number of gripping feature samples acquired.
- the number of samples empirically known to be necessary for obtaining the learning start number SFm is set as the learning start sample number SFm. Therefore, when the number Sm of gripping feature samples stored in the sample temporary storage unit 130 reaches the learning start sample number SFm (Sm ⁇ SFm), the process proceeds to step S135, and the template learning unit 135 selects the gripping feature samples.
- the user authentication template is learned by using (S130Y, S135), and the learned user authentication template is stored in the template storage unit 155 (S155).
- the operation returns to the start and continues to acquire gripping feature samples.
- the identity authentication template is obtained from the average value of the gripping feature samples (the gripping pressure distribution in the embodiment) by calculating the above formulas (1), (2), (3).
- the mobile terminal 800 of the present embodiment can be obtained after the model change by the normal personal authentication template learning method. It is possible to learn a personal authentication template that reflects the gripping characteristics of the user.
- FIG. 18 is a flowchart (F3) illustrating the authentication operation of the mobile terminal 800 according to the present embodiment.
- the switching unit 125 is set to the authentication state (connected to the personal authentication unit 160 side).
- the template learning described above has already been completed.
- the gripping feature sample acquisition unit 120 acquires gripping feature samples from the pressure sensor array 105 (S120).
- the personal authentication unit 160 compares the learned (diverted) personal authentication template with the gripping feature sample to perform personal authentication (S160).
- the method for comparing the personal authentication template and the gripping feature sample can be realized as follows, for example.
- the personal authentication unit 160 obtains the inter-vector distance between the personal authentication template and the gripping feature sample acquired in the authentication state, for example, the distance represented by the above formula (4) or (5) or (6).
- the identity authentication unit 160 concludes that the acquired gripping feature sample is that of the principal if the distance is equal to or smaller than a certain value, for example, as expressed by the inequality (7) described above. On the other hand, if the distance between the user authentication template and the gripping feature sample is not less than a certain value, it is concluded that the acquired gripping feature sample is not the subject's own.
- FIG. 15 is a block diagram illustrating a configuration of a mobile terminal 800 ′ according to the present embodiment.
- FIG. 19 is a flowchart (F4) showing the old template diversion operation of the portable terminal 800 'according to the present embodiment.
- a mobile terminal 800 ′ according to the present embodiment is obtained by adding a sensor position storage unit 810 and a sensor position correction unit 815 to the configuration of the mobile terminal 800 of FIG. 14.
- the operations of the components other than the sensor position storage unit 810 and the sensor position correction unit 815 perform the same operations as the components having the same numbers in the first embodiment, and thus the description thereof is omitted.
- the switching unit 125 included in the mobile terminal 800 ′ can switch the mobile terminal 800 ′ to either the learning state or the authentication state.
- the switching unit 125 is set to the learning state.
- Steps S120, S830, S835, S825, and S155 in the flowchart F4 are the same operations as steps S120, S830, S835, S825, and S155 in the flowchart F1 described above, and thus description thereof is omitted.
- the difference from the first embodiment is the operation after step S825N.
- the sensor position storage unit 810 stores the position of the sensor in the currently used mobile terminal. If the inter-vector distance between the correction template and the acquired gripping feature sample is not less than or equal to a predetermined value (S825N), the sensor position correction unit 815 acquires the correction template and the sensor position, and corrects according to the sensor position.
- the template is interpolated to generate an interpolation template (S815) (for details, refer to the section ⁇ About sensor position correction>).
- the template collation unit 820 collates the interpolation template with the gripping feature sample in step S815 and calculates the inter-vector distance (S820).
- the template storage unit 155 stores the interpolation template as a personal authentication template (S155).
- the inter-vector distance between the interpolation template and the acquired gripping feature sample is not less than or equal to a predetermined value (S825N)
- F2 to start
- the personal authentication template learning operation (flowchart F2) in the learning state of the mobile terminal 800 ′ according to the present embodiment and the authentication operation (flowchart F3) in the authentication state of the mobile terminal 800 ′ according to the present embodiment are the same as those in the first embodiment. Therefore, the explanation is omitted.
- the mobile terminal 800 ′ according to the present embodiment performs interpolation on the old template using the sensor position, the old template can be used even when the sensor position changes before and after the model change. Each time the model is changed, it is not necessary to re-learn the user authentication template, and the convenience of the user is improved.
- the program describing the processing contents can be recorded on a computer-readable recording medium.
- the computer-readable recording medium may be any recording medium such as a magnetic recording device, an optical disk, a magneto-optical recording medium, and a semiconductor memory.
- this program is distributed by selling, transferring, or lending a portable recording medium such as a DVD or CD-ROM in which the program is recorded. Furthermore, the program may be distributed by storing the program in a storage device of the server computer and transferring the program from the server computer to another computer via a network.
- a computer that executes such a program first stores a program recorded on a portable recording medium or a program transferred from a server computer in its own storage device.
- the computer reads the program stored in its own recording medium and executes the process according to the read program.
- the computer may directly read the program from a portable recording medium and execute processing according to the program, and the program is transferred from the server computer to the computer.
- the processing according to the received program may be executed sequentially.
- the program is not transferred from the server computer to the computer, and the above-described processing is executed by a so-called ASP (Application Service Provider) type service that realizes a processing function only by an execution instruction and result acquisition. It is good.
- the program in this embodiment includes information that is used for processing by an electronic computer and that conforms to the program (data that is not a direct command to the computer but has a property that defines the processing of the computer).
- the present apparatus is configured by executing a predetermined program on a computer.
- a predetermined program on a computer.
- at least a part of these processing contents may be realized by hardware.
Landscapes
- Engineering & Computer Science (AREA)
- Computer Security & Cryptography (AREA)
- General Engineering & Computer Science (AREA)
- Computer Hardware Design (AREA)
- Theoretical Computer Science (AREA)
- Signal Processing (AREA)
- Computer Networks & Wireless Communication (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Software Systems (AREA)
- Biomedical Technology (AREA)
- Social Psychology (AREA)
- Computing Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biodiversity & Conservation Biology (AREA)
- Automation & Control Theory (AREA)
- Telephone Function (AREA)
- Collating Specific Patterns (AREA)
Abstract
Description
まず、図14、15に本発明の全ての実施例に係る機能構成ブロックで示す携帯端末800、800’が取得する把持特徴サンプルについて説明する。人間は生得的に(1)手指の長さ、(2)握る力の強さ、などが異なることに加え、後天的に(3)携帯端末を持つ時の癖、などが異なっているため、把持特徴は本人認証に用いる生体情報として非常に優れている。具体的には、把持特徴認証は、本人拒否率および他人受入率とも、一般的な顔認証と同程度の精度を有する。把持特徴サンプルとしては、例えば把持圧力分布、把持形状分布、把持温熱分布などが考えられる。これらの把持特徴サンプルの取得方法としては、例えば複数の圧力センサを携帯端末800、800’の面に面状、もしくは直線状に分布配置することにより把持圧力分布を取得することができる。
把持特徴サンプルは、例えばサンプリングトリガの発生と同時に取得することとしてもよい。サンプリングトリガとは、予め設定した把持特徴サンプルの取得タイミングのことである。例えば携帯端末800、800’のブラウザソフトを起動しているときの把持特徴サンプルを取得したい場合には、サンプリングトリガを「ブラウザ起動中∩決定キー押下」と設定することができる。このサンプリングトリガ「ブラウザ起動中∩決定キー押下」は、ブラウザ起動中であってかつユーザが携帯端末800、800’の決定キーを押した場合、この操作をサンプリングトリガとして直ちに把持特徴サンプルを取得することを意味している。決定キーなどの操作キーを押下することがあまりない通話中などに把持特徴サンプルを取得したい場合には、例えばサンプリングトリガを「3分に一回」と設定し、通話状態が3分間継続するごとに自動的にサンプリングトリガを発生させて、把持特徴サンプルを取得することとしてもよい。
本発明の全ての実施例に係る携帯端末800、800’が本人認証時に用いる本人認証テンプレートについて詳細に説明する。本人認証テンプレートとは、ユーザの把持特徴を代表して表す雛形のことである。本人認証テンプレートは、ユーザから取得した前述の把持特徴サンプルの平均値などから学習される。学習された本人認証テンプレートは、学習後に新たに取得された把持特徴サンプルと照合される。照合により求めた値(ベクトル間距離、例えばマハラノビス汎距離)の大小により、学習後に新たに取得された把持特徴サンプルが本人認証テンプレートと同一人物のものであるか否かが判定される。
図1、2、5、6、7にそれぞれ異なる機種の携帯端末800a、800b、800b’、800c、800dをそれらの形状の具体例として示す。以下、携帯端末800a、800b、800b’、800c、800dはすべて本発明の実施例に係る携帯端末800、800’のいずれかの機能を備えているものとする。
<本明細書におけるセンサ位置特定に用いる基準点について>
図1、2、6、7を参照して本発明においてセンサ位置を特定する際に用いる基準点について説明する。本明細書において図1及び2の携帯端末800a及び800bは互いに異なる機種のスマートフォンであるものとする。また、図6及び7の携帯端末800c、800dはスマートフォンではなく旧型の折り畳み式携帯端末とスライド式の携帯端末であるものとする。
<機種変更について>
本発明の携帯端末800、800’は機種変更前の携帯端末において使用していた本人認証テンプレートを機種変更後の携帯端末において流用することを目的としている。ここで、機種変更とは、同一の通話会社と契約を継続したまま、携帯端末の機種のみを異なる機種に変更する場合、異なる通話会社に契約を移す時に併せて携帯端末の機種を異なる機種に変更する場合、故障などの理由で自身の携帯端末を通話会社に預けており、この間一時的に通話会社より貸し出される代替の携帯端末に一時的に機種変更している場合などを含む。
<機種変更前後における把持状態の変化について>
機種変更前後において把持特徴が変化する例として、例えば機種変更の前後における機種の形状、操作キーの位置が変化するなどにより、把持特徴自体が変化する例がある。機種変更前後における操作キーの配置変化に伴って、把持特徴が変化する場合について図3、図5を参照して具体的に説明する。図5は携帯端末800b’の把持状態を示す図である。本説明において、携帯端末800aから携帯端末800b’に機種変更が行われるものとし、機種変更後の携帯端末800b’は、機種変更前の携帯端末800aとセンサ位置(基準点からの相対位置)は全く同じであるが、その右側面に携帯端末800aが備えていない操作キー(例えばカメラ起動ボタンなど)108を備えているものとする。この場合、ユーザは図5に示すように普段の把持状態においてこの操作キー108を誤って押下してしまうことにより携帯端末を誤動作させないように、この操作キー108がある位置と指の位置が重ならないように、指の配置を少しずらして把持するようになる(図5の矢印参照)。図3と図5を比較すればわかるように、ユーザは中指の位置を少し人差し指側にずらすことにより携帯端末800b’の右側面の操作キー108の押下を避けている。
機種変更前後における把持状態の変化によって生じる把持特徴の変化の補正については、旧テンプレートと、新たに取得した把持特徴サンプルとの間の距離を求め、この距離から新たな本人認証テンプレートを統計的手法により推定することができる。新たな本人認証テンプレートを実現する方法の一具体例について説明する。
<機種変更前後における圧力センサの位置変化について>
次に引き続き図1を、新たに図2を参照して機種変更の前後で圧力センサの位置が変化した場合について詳細に説明する。図2は圧力センサアレイを備える携帯端末800bを示す図である。本説明において、ユーザは当初携帯端末800aを使用しており、携帯端末800aが備える学習機能によって本人認証テンプレートを学習済みであり、その後ユーザは携帯端末800aから携帯端末800bに機種変更を行ったものとする。ここで、前述したように携帯端末800bは携帯端末800aと同様にスマートフォンであるものとする。
上述の機種変更前後における圧力センサの位置変化によって生じる把持特徴の変化の補正について以下に説明する。本発明の実施例2に係る図15に機能ブロックで示す携帯端末800’はセンサ位置記憶部810とセンサ位置補正部815とを備える。その他については後で詳述する。センサ位置補正部815は上記の圧力センサの位置変化によって生じる把持圧力分布の変化の補正を補間により行う。図11A,11Bを参照してこの補正について詳細に説明する。図11Aは図10A、図10Bのグラフを重ねて表示したものである。実線のグラフは図10Aのグラフ、つまり機種変更前における携帯端末800aで学習された旧テンプレート、破線のグラフは図10Bのグラフ、つまり機種変更後における携帯端末800bの把持圧力分布(把持特徴サンプル)である。また、図10Bと同様に、機種変更後における携帯端末800bの圧力センサによる把持圧力の測定点を白丸で示した。図11Aに示すように、ユーザの把持特徴自体に機種変更前後で変化がなければ、携帯端末800bの圧力センサアレイによる測定点(白丸)は、理想的には機種変更前の旧テンプレートのフィッティング曲線上又はその近傍に位置するはずである。従って、図11Bのように、機種変更前に既に得られている旧テンプレートのフィッティング曲線における、機種変更後の携帯端末800bのセンサ角度位置θbt(図中一点鎖線)の把持圧力値を補間値として抽出し、新たなセンサ位置における本人認証テンプレートの予測値(図11Bの白丸)とし、これら予測された測定点(図11Bの白丸)を機種変更後の本人認証テンプレートとすることができる。このような処理をするために、本発明の実施例2に係る携帯端末800’は機種変更後における携帯端末800bのセンサ位置θbtをセンサ位置記憶部810に記憶しておく必要がある。センサ位置は上記で説明したような角度で表記するものに限られないが、少なくともタッチパネル(決定キー)の中心を基準点とすることが望ましい。タッチパネル(決定キー)の中心位置を基準点とすると、携帯端末サイズに大きな変化がない限り、機種変更前後でユーザの把持特徴が安定するからである。
機種変更の前後において把持状態の変化と圧力センサの位置変化が同時に起こる場合にも旧テンプレートを補正することができる。この場合にはまず、旧テンプレートに対して特徴セグメントの抽出、変形補正(セグメント位置の補正)を行う。変形補正後の旧テンプレートと機種変更後に取得された把持特徴サンプルとを比較照合し、ベクトル間距離を求める。ベクトル間距離が予め定めたしきい値を超える場合には、センサ位置記憶部に記憶されたセンサ位置に基づいて、変形補正後の旧テンプレートについて補間を行う。このようにして、機種変更の前後において把持状態の変化と圧力センサの位置変化が同時に起こる場合についても、旧テンプレートを補正して機種変更後の携帯端末においても流用することができる。
Claims (9)
- 把持特徴サンプルを複数のセンサからなるセンサアレイにより取得し、本人認証テンプレートを用いて本人認証を行う機能を有する携帯端末であって、
前記センサアレイから把持特徴サンプルを取得する把持特徴サンプル取得部と、
過去に使用していた携帯端末において本人認証に用いられた本人認証テンプレートを旧テンプレートとして記憶する旧テンプレート記憶部と、
前記旧テンプレートから特徴セグメントを抽出し、当該特徴セグメントごとに前記旧テンプレートと前記把持特徴サンプルとを照合して距離を計算する特徴セグメント抽出部と、
前記特徴セグメント抽出部が計算した距離が予め定めた値以下でない特徴セグメントにおいて前記旧テンプレートを変形補正して補正テンプレートを生成するセグメント位置補正部と、
前記補正テンプレートと前記取得された把持特徴サンプルとを照合してベクトル間距離を計算するテンプレート照合部と、
前記補正テンプレートと前記取得された把持特徴サンプルとのベクトル間距離が予め定めた値以下である場合に、前記補正テンプレートを前記本人認証テンプレートとして記憶するテンプレート記憶部と、
を含む。 - 請求項1に記載の携帯端末であって、
前記補正テンプレートと前記取得された把持特徴サンプルとのベクトル間距離が予め定めた値以下でない場合に、前記把持特徴サンプルを一定数記憶するサンプル一時記憶部と、
前記サンプル一時記憶部に前記把持特徴サンプルが一定数記憶されている場合に、当該把持特徴サンプルを用いて前記本人認証テンプレートを学習し、前記テンプレート記憶部に記憶するテンプレート学習部と、
をさらに含む。 - 請求項1に記載の携帯端末であって、
現在使用中の携帯端末におけるセンサの位置を記憶するセンサ位置記憶部と、
前記補正テンプレートと前記取得された把持特徴サンプルとのベクトル間距離が予め定めた値以下でない場合に、前記補正テンプレートと、前記センサ位置とを取得して、前記センサ位置に応じて前記補正テンプレートを補間して補間テンプレートを生成するセンサ位置補正部とをさらに含み、
前記テンプレート照合部は、前記補間テンプレートと前記把持特徴サンプルとを照合してベクトル間距離を計算するよう構成されており、
前記テンプレート記憶部は、前記補間テンプレートと前記把持特徴サンプルとのベクトル間距離が予め定めた値以下である場合に、前記補間テンプレートを前記本人認証テンプレートとして記憶するように構成されている。 - 請求項3に記載の携帯端末であって、
前記補間テンプレートと前記把持特徴サンプルとのベクトル間距離が予め定めた値以下でない場合に、前記把持特徴サンプルを一定数記憶するサンプル一時記憶部と、
前記サンプル一時記憶部に前記把持特徴サンプルが一定数記憶されている場合に、当該把持特徴サンプルを用いて本人認証テンプレートを学習し、前記テンプレート記憶部に記憶するテンプレート学習部と、
をさらに含む。 - 把持特徴サンプルを複数のサンプルからなるセンサアレイにより取得し、本人認証に用いる本人認証テンプレートの学習を行う把持特徴学習方法であって、
前記センサアレイから把持特徴サンプルを取得する把持特徴サンプル取得ステップと、
過去に使用していた携帯端末において本人認証に用いられた本人認証テンプレートを旧テンプレートとして記憶する旧テンプレート記憶ステップと、
前記旧テンプレートから特徴セグメントを抽出し、当該特徴セグメントごとに前記旧テンプレートと前記把持特徴サンプルとを照合して距離を計算する特徴セグメント抽出ステップと、
前記特徴セグメント抽出ステップが計算した距離が予め定めた値以下でない特徴セグメントにおいて前記旧テンプレートを変形補正して補正テンプレートを生成するセグメント位置補正ステップと、
前記補正テンプレートと前記取得された把持特徴サンプルとを照合してベクトル間距離を計算するテンプレート照合ステップと、
前記補正テンプレートと前記取得された把持特徴サンプルとのベクトル間距離が予め定めた値以下である場合に、前記補正テンプレートを前記本人認証テンプレートとして記憶するテンプレート記憶ステップと、
を含む。 - 請求項5に記載の把持特徴学習方法であって、
前記補正テンプレートと前記取得された把持特徴サンプルとのベクトル間距離が予め定めた値以下でない場合に、前記把持特徴サンプルを一定数記憶するサンプル一時記憶ステップと、
前記サンプル一時記憶ステップにおいて前記把持特徴サンプルが一定数記憶されている場合に、当該把持特徴サンプルを用いて前記本人認証テンプレートを学習して記憶するテンプレート学習ステップと、
をさらに含む。 - 請求項5に記載の把持特徴学習方法であって、
現在使用中の携帯端末におけるセンサの位置を記憶するセンサ位置記憶ステップと、
前記補正テンプレートと前記取得された把持特徴サンプルとのベクトル間距離が予め定めた値以下でない場合に、前記補正テンプレートと、前記センサ位置とを取得して、前記センサ位置に応じて前記補正テンプレートを補間して補間テンプレートを生成するセンサ位置補正ステップとをさらに含み、
前記テンプレート照合ステップは、
前記補間テンプレートと前記把持特徴サンプルとを照合してベクトル間距離を計算し、
前記テンプレート記憶ステップは、
前記補間テンプレートと前記把持特徴サンプルとのベクトル間距離が予め定めた値以下である場合に、前記補間テンプレートを前記本人認証テンプレートとして記憶する。 - 請求項7に記載の把持特徴学習方法であって、
前記補間テンプレートと前記把持特徴サンプルとのベクトル間距離が予め定めた値以下でない場合に、前記把持特徴サンプルを一定数記憶するサンプル一時記憶ステップと、
前記サンプル一時記憶ステップにおいて前記把持特徴サンプルが一定数記憶されている場合に、当該把持特徴サンプルを用いて本人認証テンプレートを学習して記憶するテンプレート学習ステップと、
をさらに含む。 - 請求項5から8の何れかに記載の把持特徴学習方法をコンピュータで実行するプログラムを記憶した記録媒体。
Priority Applications (4)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2013509977A JP5456939B2 (ja) | 2011-04-15 | 2012-04-13 | 携帯端末及び把持特徴学習方法 |
CN2012800039763A CN103238157A (zh) | 2011-04-15 | 2012-04-13 | 便携终端及抓持特征学习方法 |
US13/881,233 US20130214905A1 (en) | 2011-04-15 | 2012-04-13 | Portable terminal and gripping-feature learning method |
EP12771486.3A EP2624162A4 (en) | 2011-04-15 | 2012-04-13 | PORTABLE DEVICE AND METHOD FOR STORING GRAPHIC FEATURES THEREFOR |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2011-090669 | 2011-04-15 | ||
JP2011090669 | 2011-04-15 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2012141288A1 true WO2012141288A1 (ja) | 2012-10-18 |
Family
ID=47009447
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2012/060128 WO2012141288A1 (ja) | 2011-04-15 | 2012-04-13 | 携帯端末及び把持特徴学習方法 |
Country Status (5)
Country | Link |
---|---|
US (1) | US20130214905A1 (ja) |
EP (1) | EP2624162A4 (ja) |
JP (1) | JP5456939B2 (ja) |
CN (1) | CN103238157A (ja) |
WO (1) | WO2012141288A1 (ja) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2014110638A (ja) * | 2012-12-03 | 2014-06-12 | Samsung Electronics Co Ltd | 画面ロックを制御する方法及び携帯端末 |
JP2014127755A (ja) * | 2012-12-25 | 2014-07-07 | Kyocera Corp | 携帯端末装置 |
JP2016515747A (ja) * | 2013-04-19 | 2016-05-30 | クゥアルコム・インコーポレイテッドQualcomm Incorporated | ハンドヘルドデバイスおよび方法での片手およびマルチモーダルの対話のためのグリップ力センサアレイ |
US9621700B2 (en) | 2012-12-25 | 2017-04-11 | Kyocera Corporation | Mobile terminal device |
Families Citing this family (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US10530770B2 (en) | 2017-06-28 | 2020-01-07 | International Business Machines Corporation | Pressure-based authentication |
US10929516B2 (en) * | 2018-10-08 | 2021-02-23 | Advanced New Technologies Co., Ltd. | Dynamic grip signature for personal authentication |
WO2024118688A2 (en) * | 2022-11-29 | 2024-06-06 | The Regents Of The University Of California | Mobile device based hand grip strength measurement |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2005173930A (ja) * | 2003-12-10 | 2005-06-30 | Sony Corp | 電子機器、認証方法 |
JP2005275661A (ja) * | 2004-03-24 | 2005-10-06 | Fujitsu Ltd | バイオメトリクス情報管理システムおよびバイオメトリクス情報管理サーバ |
JP2009077221A (ja) * | 2007-09-21 | 2009-04-09 | Toshiba Digital Media Engineering Corp | 情報携帯機器および認証方法 |
Family Cites Families (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6970583B2 (en) * | 2000-05-25 | 2005-11-29 | Black Gerald R | Identity authentication device |
CN100414558C (zh) * | 2002-12-06 | 2008-08-27 | 中国科学院自动化研究所 | 基于模板学习的自动指纹识别系统和方法 |
US8090945B2 (en) * | 2005-09-16 | 2012-01-03 | Tara Chand Singhal | Systems and methods for multi-factor remote user authentication |
EP2947592B1 (en) * | 2007-09-24 | 2021-10-27 | Apple Inc. | Embedded authentication systems in an electronic device |
CN101231691A (zh) * | 2007-12-24 | 2008-07-30 | 浙江金指码科技有限公司 | 通过指纹数据数量调整的学习型智能指纹识别比对方法 |
JP4950964B2 (ja) * | 2008-08-19 | 2012-06-13 | パナソニック株式会社 | 情報処理装置 |
JP2010061528A (ja) * | 2008-09-05 | 2010-03-18 | Fujitsu Ltd | 生体認証装置、生体認証プログラム及び生体認証方法 |
JP5098973B2 (ja) * | 2008-11-27 | 2012-12-12 | 富士通株式会社 | 生体認証装置、生体認証方法及び生体認証プログラム |
US20100254578A1 (en) * | 2009-04-06 | 2010-10-07 | Mercedeh Modir Shanechi | Handwriting authentication method, system and computer program |
WO2010122807A1 (ja) * | 2009-04-24 | 2010-10-28 | ミツミ電機株式会社 | 個人認証装置 |
US8762734B2 (en) * | 2010-02-10 | 2014-06-24 | Raytheon Company | Biometric pressure grip |
-
2012
- 2012-04-13 JP JP2013509977A patent/JP5456939B2/ja not_active Expired - Fee Related
- 2012-04-13 WO PCT/JP2012/060128 patent/WO2012141288A1/ja active Application Filing
- 2012-04-13 CN CN2012800039763A patent/CN103238157A/zh active Pending
- 2012-04-13 US US13/881,233 patent/US20130214905A1/en not_active Abandoned
- 2012-04-13 EP EP12771486.3A patent/EP2624162A4/en not_active Withdrawn
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2005173930A (ja) * | 2003-12-10 | 2005-06-30 | Sony Corp | 電子機器、認証方法 |
JP2005275661A (ja) * | 2004-03-24 | 2005-10-06 | Fujitsu Ltd | バイオメトリクス情報管理システムおよびバイオメトリクス情報管理サーバ |
JP2009077221A (ja) * | 2007-09-21 | 2009-04-09 | Toshiba Digital Media Engineering Corp | 情報携帯機器および認証方法 |
Non-Patent Citations (1)
Title |
---|
See also references of EP2624162A4 * |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2014110638A (ja) * | 2012-12-03 | 2014-06-12 | Samsung Electronics Co Ltd | 画面ロックを制御する方法及び携帯端末 |
CN108834091A (zh) * | 2012-12-03 | 2018-11-16 | 三星电子株式会社 | 控制屏幕锁定的方法和移动终端 |
US10278075B2 (en) | 2012-12-03 | 2019-04-30 | Samsung Electronics Co., Ltd. | Method and mobile terminal for controlling screen lock |
US11109233B2 (en) | 2012-12-03 | 2021-08-31 | Samsung Electronics Co., Ltd. | Method and mobile terminal for controlling screen lock |
CN108834091B (zh) * | 2012-12-03 | 2022-04-19 | 三星电子株式会社 | 控制屏幕锁定的方法和移动终端 |
US11751053B2 (en) | 2012-12-03 | 2023-09-05 | Samsung Electronics Co., Ltd. | Method and mobile terminal for controlling screen lock |
JP2014127755A (ja) * | 2012-12-25 | 2014-07-07 | Kyocera Corp | 携帯端末装置 |
US9621700B2 (en) | 2012-12-25 | 2017-04-11 | Kyocera Corporation | Mobile terminal device |
JP2016515747A (ja) * | 2013-04-19 | 2016-05-30 | クゥアルコム・インコーポレイテッドQualcomm Incorporated | ハンドヘルドデバイスおよび方法での片手およびマルチモーダルの対話のためのグリップ力センサアレイ |
Also Published As
Publication number | Publication date |
---|---|
JPWO2012141288A1 (ja) | 2014-07-28 |
EP2624162A1 (en) | 2013-08-07 |
US20130214905A1 (en) | 2013-08-22 |
JP5456939B2 (ja) | 2014-04-02 |
CN103238157A (zh) | 2013-08-07 |
EP2624162A4 (en) | 2015-03-25 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
JP5442909B2 (ja) | 携帯端末及び把持特徴学習方法 | |
JP5456939B2 (ja) | 携帯端末及び把持特徴学習方法 | |
US20170046508A1 (en) | Biometric authentication using gesture | |
JP6837288B2 (ja) | 指紋認証方法及び装置 | |
Lee et al. | Secure pick up: Implicit authentication when you start using the smartphone | |
US9223955B2 (en) | User-authentication gestures | |
JP5810581B2 (ja) | 生体情報処理装置、生体情報処理方法、および生体情報処理プログラム | |
US20160147987A1 (en) | Biometrics-based authentication method and apparatus | |
JP5567151B2 (ja) | 移動情報端末、把持特徴学習方法、把持特徴認証方法及び記録媒体 | |
AU2016201759B2 (en) | Methods and Systems for Detecting User Head Motion During an Authentication Transaction | |
US9411946B2 (en) | Fingerprint password | |
WO2014029324A1 (zh) | 一种终端操作方法及终端 | |
US20130326604A1 (en) | Rhythm-based authentication | |
WO2012102111A1 (ja) | 移動情報端末、把持特徴学習方法、及び把持特徴認証方法 | |
KR20130133223A (ko) | 바이오키네마틱 입력을 이용한 사용자 식별 | |
US9483682B1 (en) | Fingerprint recognition method and device thereof | |
US20180089519A1 (en) | Multi-modal user authentication | |
WO2016188230A1 (zh) | 一种解锁方法及装置 | |
KR100905675B1 (ko) | 지문인식 장치 및 방법 | |
EP1792267A1 (en) | Feature extraction algorithm for automatic ear recognition | |
EP3655874B1 (en) | Method and electronic device for authenticating a user | |
CN102368288A (zh) | 一种验证密码的方法及应用该方法的移动终端 | |
WO2015070549A1 (zh) | 一种皮肤纹理的采集及其身份识别方法和系统 | |
US8826392B2 (en) | Device and method for authenticating biological information | |
JP2005275605A (ja) | 個人認証装置および個人認証方法 |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 12771486 Country of ref document: EP Kind code of ref document: A1 |
|
ENP | Entry into the national phase |
Ref document number: 2013509977 Country of ref document: JP Kind code of ref document: A |
|
WWE | Wipo information: entry into national phase |
Ref document number: 13881233 Country of ref document: US |
|
WWE | Wipo information: entry into national phase |
Ref document number: 2012771486 Country of ref document: EP |
|
NENP | Non-entry into the national phase |
Ref country code: DE |