Showing papers on "Handwriting recognition published in 1977"

Syntactic Recognition of Handwritten Numerals

Abstract: A method is described for the recognition of free-form (unconstrained) handwritten numerals. At first the tracings of the input characters are converted into polygons, and then they are processed by a general syntactic parser whose output is a high-level representation in terms of strokes, quadratic arcs, corners, etc., in much the same way as a human observer might. Next a number of regular expressions are defined which characterize each class of symbols, and the final recognition is performed by a finite automaton. The method was tested on IEEE Data Base 1.2.2 with a success rate of about 95 percent.

Hybrid Optical/Digital Image Processing Applied to Handwriting Recognition and Aerial Photograph Clustering

Abstract: Orthogonalized components of images are provided by the association of pure optical processing and digital procedures, in order to implement statistical pattern recognition operations. In a first step, preprocessed data are optically delivered—typically by sampling Fourier spectra that are to be modelled for information compression purposes. They satisfy both the orthonormal and dimensionally reduced description of the considered images which are not to be entirely digitized. The extraction of features consists of computing the dominant eigenvectors of the data covariance matrix, or the Fourier description of differences between spectra. Images are classified in the reduced eigenvector space. Applications to handwriting recognition are presented, starting from a series of complete pages, as well as the extraction of cadastral structures from aerial photographs.

Piezoelectric sensor pen for dynamic signature verification

Abstract: The concept of using handwriting dynamics for electronic identification is discussed. A piezo-electric sensor pen for obtaining the pen point dynamics during writing is described. Design equations are derived and details of an operating device are presented. Typical output waveforms are shown to demonstrate the operation of the pen and to show the dissimilarities between dynamics of a genuine signature and an attempted forgery.