International Business Machines Corporation

Manthri S Narasimha

Gregory M Bednar

George B Fryer

Brian E Fitzpatrick

John C Harmon

A method and apparatus of processing data is disclosed for recognizing unknown characters of a known character set, some of the characters having diacritical marks. The method includes the steps of storing the image data of an unknown character which may contain a diacritical mark. From the stored image data a predetermined localized area of data is extracted that corresponds to the expected location of the diacritical mark. The extracted diacritical mark image data and at least a portion of the stored image data of the unknown character are examined to recognize the character and any diacritical mark associated therewith. Also disclosed are video preprocessing techniques for segmenting the characters using profiles thereof, inclusive-bit-coding to separate characters based upon differences in size, justification of the extracted diacritical mark image data, unique encoding of the recognition results, and post-processing verification for characters including diacritical marks.

Method and apparatus for character recognition accommodating diacritical

In the machine recognition of hand printed characters it is desirable that the characters be constrained to a uniform size. This may be accomplished by taking a relatively unconstrained hand printed character and, through simple logical processes involving eliminating and/or combining portions of the unconstrained character, obtain a constrained character of a specified size. To obtain this specified character, the unconstrained characters are stored in a video line buffer as a plurality of rows of binary bits. When a row character is located in the video line buffer a process of vertical and horizontal consolidation is initiated. In the vertical consolidation, which is performed first, predetermined rows of the bits of the row character are selectively combined with other rows of stored bits or selected without change to reduce the height of the character to a predetermined desired height. Unselected rows are ignored. As the rows of bits are obtained during vertical consolidation, horizontal consolidation of each row is initiated. This consolidation is performed on a byte by byte basis so that each row is transformed in accordance with a predetermined relationship between the width of the row character and the desired width.

Growing community of inventors

Charlotte, NC, United States of America

Manthri S Narasimha