Lucent Technologies Inc.

At+t Corp.

Winston Lowell Nelson

William Turin

Ramanujan S Kashi

Gordon Thomas Wilfong

Jianying Hu

A signature verification method involves segmenting a smoothed and normalized signature and, for each segment, evaluating at least one local feature, thereby to obtain a feature-value vector. The method further includes computing the likelihood that the segments having the observed sequence of feature values were generated by a particular hidden Markov model, such model comprising a sequence of states having duration probabilities and feature-value histograms. In one aspect, the invention involves explicit state-duration modeling to account for duration in the respective states underlying the unknown signature. In another aspect, the invention involves computing a measure of signature complexity, and setting the number of states of the hidden Markov model according to such complexity measure.

Signature verification method using hidden markov models

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.

Method and apparatus for verifying static signatures using dynamic

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.

Method and apparatus for parametric signature verification using global

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. The timing information may be estimated using, for example, a linear time model, in which a fixed number of original image data points are estimated between each pair of compressed image data points, or a constant velocity model, in which the estimated number of original image data points is proportional to, or more generally, a function of the distance between the pair of compressed points. One such function of distance particularly well-suited to reconstruction of handwriting images is a square root of the distance.

Growing community of inventors

Morristown, NJ, United States of America

Winston Lowell Nelson