Lucent Technologies Inc.

At+t Corp.

Ramanujan S Kashi

Gordon Thomas Wilfong

Jianying Hu

Winston Lowell Nelson

William Turin

Daniel P Lopresti

A method for recognizing a table structure from delineated table region in an electronic document using hierarchical clustering of data strings. The cluster groupings are segregated effectively using the distances from a positional vector associated with words and groups of words rather than a minimum number of blank spaces between words. Once a data tree of the hierarchical clusterings is constructed, the tree is scanned downward from the root to find appropriate column boundaries using a columnization algorithm. Then using successive heuristic algorithms, determine column and row headers and row boundaries.

Method for identifying and using table structures

Document type comparison and classification using layout classification is accomplished by first segmenting a document page into blocks of text and white space. A grid of rows and columns, forming bins, is created on the page to intersect the blocks. Layout information is identified using a unique fixed length interval vector, to represent each row on the segmented document. By computing the Manhattan distance between interval vectors of all rows of two document pages and performing a warping function to determine the row to row correspondence, two documents may be compared by their layout. Furthermore, interval vectors may be grouped into N clusters with a cluster center, defined as the median of the interval vectors of the cluster, replacing each interval vector in its cluster. Using Hidden Markov Models, documents can be compared to document type models comprising rows represented by cluster centers and identified as belonging to one or more document types. In addition, documents stored in a database may be retrieved, deleted, or otherwise managed by type, using their corresponding vector sets without requiring expensive OCR of the document. Furthermore, based on the classification, it is a simple matter to locate which blocks of data contain certain information. Where only that information is desired, it is not necessary to perform OCR on the entire document. Rather OCR may be limited to those blocks where the particular information is expected based on the document type.

Method for document comparison and classification using document image layout

A method for comparing a ranking scheme for an object, such as a document image, with a known standard, or ideal ranking scheme for a comparative assessment of the performance and reliability of the two ranking schemes, is taught. The same set of objects are processed and ranked by both ranking schemes. The ranking scheme being tested is examined for all subject objects ranked lower than its ranking by the ideal ranking scheme. The test ranking scheme is charged for each swapped object which it ranked higher than the subject object, which the ideal ranking scheme ranked lower.

Method for comparing object ranking schemes

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.

Growing community of inventors

Bridgewater, NJ, United States of America

Ramanujan S Kashi