Abstract: A piecewise parametric polynomial curve-fitting method using an iterative transformation-reparametrization technique is used to compress information describing lines, such as those formed by handwritten lines, for storage in a compressed form in a computer. The curve-fitting method is applied iteratively with adaptive segmenting of curve segments to optimize piecewise approximations of complex curves. Each piecewise segment is iteratively lengthened, parameterized with an updatable parametrization table, and approximated using a cosine-type transform. To minimize approximation errors, both the accuracy and the trend of the approximation errors are monitored. In order to match end-point positions of the piecewise approximation segments, the cosine coefficients representing each piecewise segment are modified in view of the edge conditions so the segments properly abut one another upon reconstruction.
Type:
Grant
Filed:
February 22, 1994
Date of Patent:
December 5, 1995
Assignee:
Paragraph International
Inventors:
Vladislav G. Polyakov, Mikhail A. Ryleev
Abstract: A method and apparatus for cursive script recognition employs an intermediate cursive words description language constructed of elements in the form of metastrokes wherein each of the metastrokes is a member of a metric space, the metric space being expressible as a matrix of likelihood of matching between input metastrokes and predefined metastrokes forming a vocabulary. Typically, a minimum of twenty metastrokes is used to form the vocabulary or set of allowable stroke elemental shapes, although as many as seventy may be used, with a correlation factor or measurement of similarity being defined between strings of metastrokes. Techniques for interpreting the metastrokes as words include substituting, adding, and deleting metastrokes in an input sequence, measuring similarity and comparing with entries in a dictionary of words constructed of metastroke sequences and variants of metastroke sequences. Weighting of similarity may include penalties for lack of similarity.
Type:
Grant
Filed:
March 23, 1994
Date of Patent:
November 14, 1995
Assignee:
Paragraph International
Inventors:
Shelja A. Guberman, Ilia Lossev, Alexander V. Pashintsev
Abstract: A method and apparatus for cursive script recognition employs an intermediate cursive words description language constructed of elements in the form of metastrokes wherein each of the metastrokes is a member of a metric space, the metric space being expressible as a matrix of likelihood of matching between input metastrokes and predefined metastrokes forming a vocabulary. Typically, a minimum of twenty metastrokes is used to form the vocabulary or set of allowable stroke elemental shapes, although as many as seventy may be used, with a correlation factor or measurement of similarity being defined between strings of metastrokes. Techniques for interpreting the metastrokes as words include substituting, adding, and deleting metastrokes in an input sequence, measuring similarity and comparing with entries in a dictionary of words constructed of metastroke sequences and variants of metastroke sequences. Weighting of similarity may include penalties for lack of similarity.
Type:
Grant
Filed:
September 24, 1992
Date of Patent:
May 17, 1994
Assignee:
Paragraph International
Inventors:
Shelja A. Guberman, Ilia Lossev, Alexander V. Pashintsev