Abstract: A signature card is used with a computing system. The card plugs into a host computer and is, for example, a personal computer memory card internal association (PCMCIA) card. The card includes a write-on pad for receiving input from a stylus. A memory stores the input received by the write-on pad. An interface transfers the input stored by the memory to the host computer. The card also includes an independent power source which is independent from the host computer.

Abstract: A system and method of collecting payments uses an automated system to generate a draft, payable to the creditor and drawn on the payor's checking account, pursuant to the payor's authorization. The draft is then executed by the debt collector as authorized signatory for the payor, and deposited into the payee's account to complete payment. The automated system has an input screen which shows necessary information for generation of the draft, and may be read to the system operator over the telephone by the authorizing payor. When verification is complete, the system generates a paper bank draft payable to the payor, using MICR ink so that the draft can be processed in the banking system like an ordinary check. The signature block of the draft is made for the collection agent "as authorized signatory for" the payor. The system provides for an authorization code to be given to a client system to permit printing of a specified additional number of checks.

Abstract: A method and system for data entry of handwritten text into a computer program that is not designed to accept handwritten text is provided. In preferred embodiments, the computer program is designed to operate in a windowing environment. A data entry program receives handwritten data, recognizes the data, and sends the recognized data to the computer program. The computer program processes the recognized data as if it had been entered from the keyboard. According to the present invention, the data entry program overlaps the window of the computer program with an invisible window. To the user, it looks as if the computer program is accepting handwritten data directly.

Abstract: In a process of signature verification, an off-line test signature is compared to one or more on-line reference signatures. Dynamic data obtained from the reference signature or signatures may be used to improve the thinning of the test signature. Such data may also be used for segmenting the test signature and sequencing the resulting strokes. In some embodiments, the invention includes evaluating a dynamic error, based at least in part on such sequencing of the test signature. In some further embodiments, the invention includes producing a rendering of at least one on-line reference signature as a two-dimensional image, and evaluating a static error based, at least in part, on shape-matching between the rendered image and the test signature.

Abstract: Linear structures are used to identify persons. In order to be able to combine a multiplicity of such linear structures in a database, their original images are analyzed and reconstructed using orthonormal basic functions. A preferred direction of the linear structure is determined for each pixel. A quality measure is used to evaluate the reliability of the analyzed data. Singularities (SI) and minutiae (MI) are extracted and stored.

Abstract: A signature device for capture or capture and verification includes a variety of advantageous features including, for example, an ability to work in conjunction with an IC card; an improved angle correction technique; an improved technique for adapting to biometric signature changes; and many other new improvements.

Abstract: A method identifying components is disclosed. Measured values of a randomly produced property of the component are recorded. The measured values are biuniquely assigned to the component by means of a characteristic parameter and the measured values accessibly storing the measured values, or a unique code assigned thereto. Further, the characteristic parameter are accessibly stored.

Abstract: A portable, hand-held apparatus for capturing a gray scale image of a signature within a box having fiducial marks in the corners. Portions of the image outside the box are trimmed away and the box is oriented and scaled to a standard size and shape. Signature storage requirements are minimized and signature recognition is facilitated by thresholding the gray scale image and thinning the strokes of the signature to an image width of one pixel.

Abstract: A signature verification method operates by comparing the numerical values of parameters evaluated on a trial signature with stored reference data derived from previously entered reference signatures. The parameters include global features of the signature, and also include a stroke-direction code (SDC) of the signature. An SDC is derived by subdividing the signature into a sequence of time-ordered, spatially oriented line segments, each segment extending between a pair of discrete points along the signature. Each line segment has a stroke-direction value. The SDC is the ordered sequence of these stroke-direction values.

Abstract: A micro computer, constituting a signature recognition apparatus, comprises an automatic signature creating section, a data extracting section, a recognition network section, a retrieval section, and a memory section. The data extracting section creates personal data representing a plurality of personal characteristics or features based on an input signature. The recognition network section selects the data to be used for evaluation from the personal data representing personal characteristics or features, and executes an evaluation of thus chosen data. The retrieval section, using the genetic algorithm, finds out a combination pattern having preferable evaluation result. Accordingly, in recognizing signatures, it becomes possible to know beforehand what kind of personal characteristics or features data should be utilized for the recognition of the given signatures, thereby increasing the accuracy in the recognition.

Abstract: In a method for determining a reference autograph character string on the basis of a set of sample autograph character strings from the same writer, a particularly characteristic autograph character string can be selected from a set of produced sample autograph character strings, e.g. signatures. In signature verification, such references are needed to serve as a comparison measure in the identification of the signer. The method according to the invention divides the produced character strings of a sample set of signatures into strokes according to the execution, and compares individual strokes with respect to the recorded dynamic parameters, such as for example pressure and locus coordinates and writing speed, in order to enable the determination of the deviation of all the strokes of the sample character strings from one another.

Abstract: The purpose of the present invention is to provide a handwriting information detecting method and apparatus for the same, in which a user can choose any handwriting tool such as a pen or a pencil, and when the user writes with the tool, the handwriting information can be detected. The handwriting information detecting method of the present invention comprises steps of detecting a motion of a writing tool, held by a writing tool holder comprising at least one acceleration sensor, based on at least one acceleration signal output from the at least one acceleration sensor when the writing tool is grasped by fingers; and recognizing handwriting information of a character or a figure written by the writing tool according to the detected motion thereof, and outputting the information.

Abstract: Verification apparatus (2) comprising a writing instrument (4) having a body (6) and a grip sensor (8) for sensing grip pressure patterns of a person (10) when the person (10) is holding the writing instrument (4) and executing an intended movement, the verification apparatus (2) being such that the sensed grip pressure patterns are able to be compared with stored grip pressure patterns values for the person (10) in order to obtain information about the person (10) executing the movement with the writing instrument (4) The verification apparatus (2) may include a writing pressure sensor (14), an angle pressure sensor (24) and a gyroscope (32).

Abstract: Forgeries are detected by curve fitting the signature in question. The length of the curve fitted signature and the length of the signature in question are compared. If the signature in question is a traced or copied forgery, it will tend to have a significant amount of jitter which results in a significantly longer length than the curved fitted signature.

Abstract: An improved method of segmentation and feature-based description for verification/authentication of contour images (e.g. handwritten signatures) is described, directed to a system which employs a set of parameters extracted from a dynamic description of a contour image template to perform segmentation of incoming contour images being verified/authenticated by the system. The preferred embodiment would consist of a central processing unit incorporating a high-performance computer, and of many autonomous verification units (e.g. ATM machines) equipped with inexpensive processing devices. In the central processing unit, a contour image template is segmented into strokes according to the segmentation parameters which are computed using selective properties of the mathematical transformation for said contour image template. For illustration purpose, a discrete cosine transform (DCT) is being used.

Abstract: A method for recording compressed data which includes a perpendicular test as well as a parallel test for discarding handwritten data points relative to a series of guide lines. The parallel test determines whether a data point lies at a true distance within a predetermined threshold distance either side of the guide line. The perpendicular test determines whether the data point lies between two perpendicular lines through the end points of the guideline. Both tests must be satisfied before a data point is discarded. To save memory space, the guidelines are defined by an endpoint and a delta value. Error is maintained at a predetermined limit by adjusting the delta values prior to storage.

Abstract: A method of automated signature verification, in which a test signature, e.g., a signature entered by an operator, may be preprocessed and examined for test features. The test features may be compared against features of a set of template signatures, and verified in response to the presence or absence of the test features in the template signatures. The test signature may be preprocessed, so as to normalize it and remove artifacts which are irrelevant to verification. The features of the template signatures may be determined and stored in an associative memory or a data structure with associative memory capabilities, e.g., a discrete Hopfield artificial neural network. The method of verification may be adjusted to greater or lesser sensitivity in response to external conditions.

Abstract: A computer-based method and system for capturing and verifying a handwritten signature. The handwritten signature may relate to a document, such as an electronically stored document. An image of the document is displayed. A user signs the document electronically, and the handwritten signature is electronically captured. A set of measurements relating to the handwritten signature is determined and stored in a signature envelope. Optionally, a checksum of a checksum of the document can be determined and stored in the signature envelope. The claimed identity of the signatory can also be stored in the signature envelope. The signature envelope is encrypted. The signature envelope can be communicated to another application or computer platform, or stored for later verification. The signature envelope is decrypted, and the set of measurements stored in the signature envelope are compared against a known set of handwritten signature measurements to verify the identity of the signatory.

Abstract: A method and apparatus for generating a reconstructed image from a compressed image. An exemplary method in accordance with the present invention includes the steps of identifying pairs of compressed image data points having a connection therebetween in a linear segment approximation of the reconstructed image; estimating timing information such as a number of original image data points between each of the connected pairs of compressed image data points; and fitting a spline segment to each of the pairs of compressed image data points and the estimated number of original image data points corresponding thereto, such that the fitted spline segments in combination form the reconstructed image. The reconstructed image may then be smoothed by replacing spline segments which produce undesirable deviations in the reconstructed image with conic section spline segments.

Abstract: A verification method for use in a verification system comprises a verification terminal operated by a verification authority, a remote terminal remote from the verification terminal, and a communication link coupling the verification terminal to the remote terminal. The method includes the steps of generating a document data file from an identity document provided at the remote terminal, and then transmitting the document data file from the remote terminal to the verification terminal. The method further includes generating a verification data file that verifies an attribute of the document at the verification terminal. The verification data file preferably comprises a digitized signature of the verification authority operating the verification terminal. The verification data file is transmitted to the remote terminal. Finally, the document data file and the verification data file are merged to produce a verification record. The verification record may be time stamped and stored and/or printed by a printer.

Abstract: A system for capturing handwritten data includes a base station, a docking station coupled to the base station and a plurality of portable handwriting capture devices, which may be in the form of pads or trays. The pads or trays normally rest in quick release slots in the docking station, and are removed from the slots when put into use. Each pad includes a digitizer for capturing handwritten information, a controller for digitizing the information, a memory for storing the digitized information and an interface for transmitting the digitized information through the docking station to the base station, where it is decoded. A paper slip may be placed over the digitizer and retained in position, where it provides visual feedback to a person writing on the pad and also provides a written record.

Abstract: Methods and systems for performing handwriting recognition which include, in part, application of stochastic modeling techniques in conjunction with language modeling. Handwriting recognition is performed on a received data set, which is representative of a handwriting sample comprised of one or more symbols. Recognition is performed by representing the data set as a sequence of features and then processing the features utilizing stochastic modeling in conjunction with an evolutional grammer for performing stroke identification, to identify the handwriting sample.

Abstract: The adaptive dynamic signature verification system of the invention includes a number of types of signature verification terminals which digitize signatures for further verification by statistical analysis. A feature set is employed that consists of a number of personalized features, some static and some dynamic, each of which is normalized with respect to both time and spatial dimensions and allows for a degree of inconsistency in both speed and size of genuine signatures without losing the ability to discriminate against forgery attempts. The statistical approach also develops and employs either an individual-specific or a common feature subset for accurate signature discrimination.

Abstract: A signature recognition apparatus reduces the volume of training data needed and shortens the learning period. In the apparatus, a sample generating section generates sample data. A coupling load coefficient is determined based on the sample data, thereby obviating the need for additional sample data. The apparatus also uses a fuzzy net which implements a linear function in its output layer to shorten the learning period relative to the learning period required for a net implementing a non-linear function such as a sigmoid.

Abstract: A computer-based method and system for capturing and verifying a handwritten signature. The handwritten signature may relate to a document, such as an electronically stored document. An image of the document is displayed. A user signs the document electronically, and the handwritten signature is electronically captured. A set of measurements relating to the handwritten signature is determined and stored in a signature envelope. Optionally, a checksum of a checksum of the document can be determined and stored in the signature envelope. The claimed identity of the signatory can also be stored in the signature envelope. The signature envelope is encrypted. The signature envelope can be communicated to another application or computer platform, or stored for later verification. The signature envelope is decrypted, and the set of measurements stored in the signature envelope are compared against a known set of handwritten signature measurements to verify the identity of the signatory.

Abstract: A portable pen pointing device and a processing system with pen pointing device which can be easily used. The portable pen pointing device includes a memory for storing user's specific penmanship/handwriting information and a pen interface unit for supplying the user's specific penmanship/handwriting information to a processor body of the processing system. The processor body interprets a writing sample on the basis of the user's specific penmanship/handwriting information supplied from the portable pen pointing device through the pen interface unit thereof. With this construction, there is no need to read information from a storage medium such as a flexible disk in which a user's specific dictionary for penmanship/handwriting interpretation is written. Also, an operation of establishing a certain writing environment becomes unnecessary or easy.

Abstract: The stress wave activity produced during a first generation of a piece of handwriting in an enrollment procedure is put into a store and the stress wave activities produced for subsequent generations of the piece of handwriting in the enrollment procedure are used sequentially to produce a weighted average of the stored stress wave activity and the stress wave activity of the subsequent generation of the piece of handwriting and replaces the stored stress wave activity; the weighted average includes a weighted average of amplitudes and times of events. For subsequent generations of the piece of the handwriting are resequenced in order of increasing difference from the respective stored stress wave activity. The subsequent generations of the piece of handwriting are again used to sequentially produce weighted averages and replace the stored stress wave activity.

Abstract: A data card terminal, such as a credit card transaction terminal, is disclosed. The terminal includes a transaction terminal comprising an embossed character reader and magnetic stripe reader, with a separate signature capture printer. The transaction terminal is operative for detecting the physical presence of a data card during a card transaction. The embossed character reader employs a tactile imager and pattern recognition for detecting the embossed characters on the data card. A signature capturing printer prints a paper receipt, which is signed by a cardholder at a signature capturing window on the printer. A signature capturing system digitizes and compresses signals corresponding to the signature of the card holder. Transaction data including compressed signature signals and signals indicative of the presence of the card are transmitted to the host computer system of a transaction processor, who guarantees the transaction as chargeback-protected under certain circumstances.

Abstract: A signature capture pad (or signature capture/PIN pad) operative for gathering signature data associated with customer transactions includes a digitizer, microprocessor, and a plurality of serial ports, and may be connected to a point-of-sale (POS) terminal, such as an electronic cash register. The signature capture pad provides compressed or uncompressed signature signals in response to commands received from the POS terminal. Uncompressed signature data may be used to provide a facsimile signature on a display or printer at the POS terminal, whereby the signature may be approved by the operator. A signature capture cycle is terminated upon receipt of a command from the POS terminal, or upon the expiration of an optional timer. The maximum size of the compressed signature data is selectable by the POS terminal. Compressed signature data exceeding the prescribed size may be post-processed at a lower resolution.

Abstract: A handwriting verification method which is less expensive to implement than previous methods, employs simpler algorithms than previous methods, and which requires fewer points than previous methods. The method includes the steps of determining a set of positional data points for a handwritten signature entered into the digitizer, determining a set of global variable values associated with the signature from the positional data points, determining head and tail strings having shape information for the signature, reading previously computed head and tail strings from a storage medium carried by the person, reading the verification information from the storage medium, determining a range of acceptance values for each global variable, and determining whether each of the global verification values lies within the range of acceptance. If at least one of the global verification values lies outside the range of acceptance, the method further includes the step of rejecting the subsequent signature as a forgery.

Abstract: Force resolving system and method which are particularly suitable for use in the analysis of handwriting and the verification of signatures. A platen is coupled to a plurality of force transducers in such manner that only forces acting along mutually perpendicular axes are applied to the transducers. In one disclosed embodiment, each of the transducers has a film of piezoelectric material and a pressure plate which bears against the film, and forces are applied to the transducers by balls in rolling engagement with the pressure plates. In another disclosed embodiment, the forces are applied to the transducers by flexure elements connected between the platen and the pressure plates. The balls and flexure elements transfer forces acting in a directions perpendicular to the film and permit relative movement of the platen and the transducers in directions parallel to the film.

Abstract: A signature verification system consisting of a durable pressure sensitive data input stylus, signal processing, and computer algorithms for enrollment of signatures and verification. The stylus contains two transducers placed so that axial force and lateral force are measured simultaneously. Combining the two signals at digitized sample points yields a ratio of pressures indicative of the angle of the stylus to the writing surface at that moment, controlling for variations in actual force. The ratio, called a relative angle, is calculated for the entire signal train of a signature and for various simple divisions, or segments. Segments are equal divisions of the signal train by various divisions. While the relative angle of the whole signature may vary unpredictably between signings, the unique variations around the average relative angle form unique signature discriminates. Variations are measured by comparing relative angle measurements of segments, one to another, in all mathematical combinations.

Abstract: A three-axis force measurement stylus includes a housing and a cartridge and an interface between the housing and the cartridge wherein the interface comprises a plurality of pressure sensitive sheets, preferably of variable resistance pressure sensitive Mylar films which sense the force between the cartridge and the housing. The cartridge and the housings are disposed at a skew angle relative to the axis of the stylus to be able to sense forces in three dimensions. In a specific embodiment, the cartridge forms a conical section which mates with a complimentary conical section of the housing. Membranes of the force sensitive material are provided along three fingers from an apex of the conical section. The cartridge is preloaded against the conical section by a spring between the housing and the cartridge. Alternatively to the force sensitive film, a sheet of a piezoelectric pressure-sensitive material may be substituted.