Classifications

• • G—PHYSICS
  • G06—COMPUTING; CALCULATING OR COUNTING
  • G06F—ELECTRIC DIGITAL DATA PROCESSING
  • G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
  • G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
  • G06F3/03—Arrangements for converting the position or the displacement of a member into a coded form
  • G06F3/0304—Detection arrangements using opto-electronic means
• • G—PHYSICS
  • G06—COMPUTING; CALCULATING OR COUNTING
  • G06F—ELECTRIC DIGITAL DATA PROCESSING
  • G06F18/00—Pattern recognition
• • G—PHYSICS
  • G06—COMPUTING; CALCULATING OR COUNTING
  • G06F—ELECTRIC DIGITAL DATA PROCESSING
  • G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
  • G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
  • G06F3/03—Arrangements for converting the position or the displacement of a member into a coded form
  • G06F3/033—Pointing devices displaced or positioned by the user, e.g. mice, trackballs, pens or joysticks; Accessories therefor
  • G06F3/0346—Pointing devices displaced or positioned by the user, e.g. mice, trackballs, pens or joysticks; Accessories therefor with detection of the device orientation or free movement in a 3D space, e.g. 3D mice, 6-DOF [six degrees of freedom] pointers using gyroscopes, accelerometers or tilt-sensors
• • G—PHYSICS
  • G06—COMPUTING; CALCULATING OR COUNTING
  • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
  • G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
  • G06V30/10—Character recognition
  • G06V30/22—Character recognition characterised by the type of writing
  • G06V30/228—Character recognition characterised by the type of writing of three-dimensional handwriting, e.g. writing in the air
• • G—PHYSICS
  • G06—COMPUTING; CALCULATING OR COUNTING
  • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
  • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
  • G06V40/30—Writer recognition; Reading and verifying signatures
• • G—PHYSICS
  • G07—CHECKING-DEVICES
  • G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
  • G07C9/00—Individual registration on entry or exit
  • G07C9/30—Individual registration on entry or exit not involving the use of a pass
  • G07C9/32—Individual registration on entry or exit not involving the use of a pass in combination with an identity check
  • G07C9/35—Individual registration on entry or exit not involving the use of a pass in combination with an identity check by means of a handwritten signature

Definitions

• the present invention relates to a system and a method for signature verification and identification; and, more particularly, to a system and a method for inputting a multi-dimensional signature and verifying the inputted signature in an information device such as a computer.
• the PKI technology utilizes two keys, i.e., a public key and a private key, which act the parts of a key and a lock.
• the public key of the PKI is provided in public by an authentication agent and the private key is kept in secret by a user. Since the PKI employing the two keys uses an asymmetric encryption technigue, a third party cannot counterfeit or falsify a message being transmitted between users of the PKI. That is, since the PKI uses two different encryption and decryption keys contrary to a conventional encryption technology employing two symmetric keys, the PKI provides its users with better security.
• the private key of the PKI is a sort of a password
• the user should memorize or keep a record of the private key.
• the private key may be lost or fraudulently used by a third party.
• unique biological information of a user e.g., information on the user's finger print or iris
• the uniqueness of the biological information may not be perfectly verified since the biological information is generated spontaneously.
• an electronic signature method employing biological information does not provide a satisfactory recognition rate, which is a requisite for commercializing the biological information based signature method.
• problems such as a possibility of alteration of the biological information as time passes, a loss of the biological information in case of a physically handicapped person and so on.
• Another method for signature verification and identification in accordance with the prior art inputs a signature of a user through an electronic input device such as an electronic pen and compares the inputted signature with a reference signature.
• Such a signature method may use information on velocity or pressure of the user' s writing in addition to inputted two-dimensional signature information.
• the additional information on the user' s writing manner increases uniqueness of the signature.
• the recognition rate of this method is relatively low since it is difficult to distinguish the difference between the users' writing manners and the user's writing manner itself may be inconsistent.
• a multi-dimensional signature system including: an input device for inputting a time series of a signature and feature values attached to the time series; and a signature recognition device for determining whether the inputted time series and feature values are matched to a time series of a reference signature and reference feature values by comparing the inputted time series and feature values with the reference time series and feature values.
• a multi-dimensional signature verification method including the steps of: inputting a time series of a signature and feature values attached to the time series; and determining whether the inputted time series and feature values are matched to a time series of a reference signature and reference feature values by comparing the inputted time series and feature values with the reference time series and feature values.
• Fig. 1 sets forth a multi-dimensional signature system employing a motion mouse in accordance with a preferred embodiment of the present invention
• Fig. 2 depicts a motion mouse in accordance with a preferred embodiment of the present invention
• Fig. 3 illustrates an example of a three-dimensional signature inputted by using a motion mouse in accordance with the present invention and a reference signature to be compared with the inputted three-dimensional signature;
• Fig. 4 provides an example of a multi-dimensional signature and feature values having a form of a musical note inputted by using a method for inputting a multi-dimensional signature in accordance with a preferred embodiment of the present invention
• Fig. 5 presents a method for verifying a multi- dimensional signature in accordance with a preferred embodiment of the present invention.
• a multi-dimensional signature system in accordance with the present invention includes a signature input device, such as a pointing device, an electronic pen and a conventional mouse, for inputting a time series of a multi- dimensional signature into an information device such as a computer; and a signature recognition device for verifying the inputted signature by comparing the time series of the multi-dimensional signature with that of a reference signature stored in the information device.
• a signature input device such as a pointing device, an electronic pen and a conventional mouse
• the multi-dimensional signature system of the present invention may input a time series of an additional dimensional data (i.e., depth data for the time series of the signature) in addition to the inputted time series of the signature in case the dimension of the inputted time series is low (e.g., if a two-dimensional signature is inputted, the time series of the inputted signature has three dimensions (i.e., x and y coordinates and time)).
• the additional dimensional data may be a z- coordinate of a time series of a signature inputted in a three-dimensional space.
• the additional dimensional data may be numerical values or tone values of a musical note, which are inputted by a user.
• the system includes a computer 110, a camera 120 for capturing an image, which is connected to the computer 110, a pointing device 200 (hereinafter referred to as a "motion mouse") for representing three-dimensional positions and status information of an object.
• the computer 110 includes a signature inputting device (or a signature input program) for analyzing an image of a movement of the motion mouse 200 to thereby obtain a time series of a user' s signature data and a signature recognition device (or a signature recognition program) for verifying the signature by comparing the inputted time series with that of a reference signature .
• a user of the computer 110 represents his or her own multi-dimensional signature by moving the motion mouse 200 in a three-dimensional space in front of the camera 120.
• the camera 120 captures images of the movements of the motion mouse 200, such that an analysis software executed in the computer 110 analyzes the images captured by the camera 120 to recognize the three-dimensional positions and the status information of the motion mouse 200.
• the motion mouse 200 since the motion mouse 200 does not have to transmit/receive any information through a wired or wireless connection, the motion mouse 200 can move freely in a three- dimensional space in front of the camera 120. For instance, the motion mouse 200 may rotate or move in left/right and up/down directions or any combination thereof. Accordingly, the user is able to input a multi-dimensional signature having various shapes by using the motion mouse 200.
• Fig. 2 illustrates a configuration of the motion mouse 200 in accordance with a preferred embodiment of the present invention.
• the motion mouse 200 includes a plurality of illuminators 211 to 213 on its front surface and a plurality of switches 221 to 223 on its side for controlling ON/OFF status of the illuminators 211 to 213.
• the switches 221 to 223 respectively control flickering (ON/OFF) of the illuminators 211 to 213, so that a combination of the ON/OFF status of the illuminators 211 to 213 represents feature values inputted in addition to the time series of a multi- dimensional signature represented by three-dimensional movements of the motion mouse 200.
• the numbers and types of the illuminators and the switches may vary depending on the number and type of the feature values added to the time series of the multi- dimensional signature. Further, in order to represent the feature values, indicators having different sizes, shapes and/or colors may be arranged on the front surface of the motion mouse 200 instead of the illuminators 211 to 213.
• the motion mouse 200 generates a time series of three- dimensional positions, each sample of which is produced at regular intervals. In this case, the generated time series may be interpolated, such that the time series has a more continuous and smooth contour.
• the time series of a three- dimensional signature and feature values inputted by using the motion mouse 200 are stored in the computer 110.
• Fig. 3 illustrates examples of a time series of a three-dimensional signature inputted by using the motion mouse 200 and that of a reference signature to be compared with the inputted three-dimensional signature.
• the multi-dimensional signature system in accordance with the preferred embodiment of the present invention employs the motion mouse to input a three-dimensional signature.
• the multi- dimensional signature system may use an inputting device for inputting two-dimensional coordinates such as a conventional electronic pen or mouse.
• a time series of a multi-dimensional signature is obtained as follows. That is, after a signer inputs a two-dimensional signature by using a conventional mouse, an additional time series representing a third dimension (z) may be inputted.
• the signer may select each of the segments and input additionally a feature value corresponding to the selected segment. This way of inputting the feature value may be applied to the case of using the motion mouse of the present invention.
• the feature values added to the time series of the signature may be musical tone values of a musical note.
• the inputted feature values are considered as a melody of certain music.
• the signer selects a certain point of the inputted time series of the three-dimensional signature and then inputs a musical tone as a feature value corresponding to the selected point. This makes it more user-friendly and convenient to input a multi-dimensional signature.
• a recognition rate of the signature can be improved. That is, since characteristics of a two- or three-dimensional signature may vary depending on mental and physical conditions of a signer, a consistent recognition rate of the signature is not guaranteed. However, since the feature values added to the signature are constant and are easy for the signer to remember, a uniform recognition rate of the signature is maintained.
• a similarity between the inputted time series and feature values and a reference time series and feature values stored in the computer 110 is calculated. Thereafter, the calculated similarity is compared with a predetermined threshold value. If the similarity is larger than the threshold value, the inputted signature is determined to be made by an owner of the reference signature.
• the inputted time series of the signature may be normalized such that the length of the inputted time series becomes identical to that of the reference time series. Further, the DTW (dynamic time warping) method may be applied to the process of calculating the similarity. Further, in order to improve the recognition rate of the inputted signature, each segment of the inputted signature may be weighted based on the importance of the segment.
• Fig. 5 presents a flowchart showing a method for verifying a multi-dimensional signature in accordance with a preferred embodiment of the present invention.
• a signer inputs a time series of a multi- dimensional signature and/or feature values by using a pointing device (step 510) .
• the pointing device may be a conventional mouse or the above-mentioned motion mouse 200.
• the signer uses the motion mouse 200, it is possible to input the feature values by using the switches 221 to 223 arranged on the motion mouse 200 while representing the multi-dimensional signature by moving the motion mouse 200. That is, by selecting one of the switches 221 to 223 or a combination thereof, the signer can controls the flickering (ON/OFF) of the illuminators 211 to 213 installed on the front surface of the motion mouse 200.
• the multi-dimensional signature and the feature values attached thereto are recognized by analyzing images representing the motion of the motion mouse 200 and the flickering of the illuminators 211 to 213.
• the feature values of the present invention may be a depth value corresponding to each of segments comprising the inputted multi-dimensional signature.
• the depth value corresponding to each of the segments may be a numerical value or a musical tone of a musical note.
• the signer selects one of the segments comprising the multi- dimensional signature and then inputs a feature value corresponding to the selected segment.
• the time series of the multi- dimensional signature is normalized (step 520). Thereafter, a similarity between the normalized time series and that of a reference signature, which are stored in a memory, is calculated (step 530) .
• the DTW (dynamic time warping) method which is employed in a conventional time series data recognition application, may be utilized.
• a warping algorithm is used to correct the inputted multi-dimensional signature, thereby minimizing a dynamic error between the inputted multi-dimensional signature and the reference signature.
• a dynamic programming matching algorithm is performed to calculate a similarity between the corrected multi-dimensional signature and the reference signature.
• each of the segments of the inputted multi-dimensional signature may be weighted based on the degree of its importance. Thereafter, the calculated similarity is compared with a predetermined threshold value (step 540) .
• the multi-dimensional signature system of the present invention improves the recognition rate of a multi-dimensional signature by inputting feature values, i.e., certain values or codes, in addition to a time series of a signature inputted through a pointing device.
• the additionally inputted feature values are simple values or codes that are easy to memorize. Further, even if an original signature of a signer happens to be revealed in public, a security of the signature may be maintained due to the feature values kept secret by the signer.

Landscapes

• Engineering & Computer Science (AREA)
• Theoretical Computer Science (AREA)
• Physics & Mathematics (AREA)
• General Physics & Mathematics (AREA)
• General Engineering & Computer Science (AREA)
• Human Computer Interaction (AREA)
• Multimedia (AREA)
• Computer Vision & Pattern Recognition (AREA)
• Bioinformatics & Cheminformatics (AREA)
• Bioinformatics & Computational Biology (AREA)
• Artificial Intelligence (AREA)
• Data Mining & Analysis (AREA)
• Evolutionary Biology (AREA)
• Evolutionary Computation (AREA)
• Life Sciences & Earth Sciences (AREA)
• Collating Specific Patterns (AREA)

Priority Applications (1)

Applications Claiming Priority (2)

Publications (1)

Family

ID=30113073

Family Applications (1)

Country Status (3)

Citations (3)

• 2002
  • 2002-07-04 KR KR1020020038513A patent/KR20040003736A/ko not_active Application Discontinuation
• 2003
  • 2003-06-27 AU AU2003243043A patent/AU2003243043A1/en not_active Abandoned
  • 2003-06-27 WO PCT/KR2003/001259 patent/WO2004006170A1/en not_active Application Discontinuation

Patent Citations (3)

Also Published As

Similar Documents

Legal Events