Showing papers on "Intelligent word recognition published in 1980"

Automatic recognition of handprinted characters—The state of the art

Abstract: Based on a study of the extensive literature in handprint recognition, this paper presents a survey in this challenging field. Recognition algorithms, data bases, character models, and handprint standards are examined. Achievements in the recognition of handprinted numerals, alphanumerics, Fortran, and Katakana characters are analyzed and compared. Data quality and constraints, as well as human and machine factors are also described. Characteristics, problems, and actual results on on-line recognition of handprinted characters for different applications are discussed. New emphases and directions are suggested.

Optical character reading method

Abstract: PURPOSE:To improve the read accuracy, by deciding a subset from a result of recognition by a recognition dictionary, to every character-string partitioned by a blank or a specific symbol in a read field, and recognizing the character- string again by use of a recognition dictionart containing said subset only. CONSTITUTION:A video signal obtained by scanning a chaacter entered or printed in a slip 1, by a scanning part 2 is applied to a pre-processing part 6, the video signal is binary-coded by the pre-processing part 6, and a character pattern is supplied to a recognition part 6. In this recognition part 7, the character pattern is recognized by referring to a recognition dictionary 8, and its recognition result is provided to a control part 9. subsequently, a character-string 3 of alphanumeric and a character-string 4 of ''Katakana'' (square form of Japanese syllabary), which are partitioned by one blank are entered in a read field 2 of the slip 1. The field 2 of this slip 1 is recognized by use of a recognition dictionary containing both of the whole character-strings in the recognition part 7, a subset is decided by said recognition result, subsequently the character-strings are recognized again by use of a recognition dictionary containing the subset only, and the read accuracy is improved.

The global and analytic view of word recognition

Abstract: • A submitted manuscript is the author's version of the article upon submission and before peer-review. There can be important differences between the submitted version and the official published version of record. People interested in the research are advised to contact the author for the final version of the publication, or visit the DOI to the publisher's website. • The final author version and the galley proof are versions of the publication after peer review. • The final published version features the final layout of the paper including the volume, issue and page numbers.

Information processing method and device for word recognition

Abstract: Digital information processing method for recognising words from a text by digital comparison, character by character, with a model-word in which the comparing of a character (a'3) of the word with the character (a3) of equal rank of the model-word is accompanied by comparing the preceding character (a2) of the word and by comparing the following character (a4) of the word with the said character of the model-word. Device for implementing this method.

Reduction of minimum word-boundary gap lengths in isolated word recognition

Abstract: In this paper, we describe an isolated-word recognition system which challenges the assumption that only connected word recognition can provide high-speed data entry. In previously available isolated-word recognizers, the entry rate was not only limited by the user's ability to speak words in isolation, but by the requirement to leave relatively large gaps between words in order for the system to use gap length to discriminate word boundary gaps from intra-word stop-gaps. The new isolated-word recognition algorithm greatly reduces the minimum acceptable word-boundary gap length by using correlation scores and dynamic programming string matching to discriminate between the two kinds of gaps. Reliable word recognition results are obtained even with word-boundary gaps which are a fraction of the length of typical stop-gaps, and the effective digit entry rate is about twice that of previous isolated-word recognition systems.