EP0138079A2
Expired / Lapsed
EP
⏱️ 0.0 years remaining
Character recognition apparatus and method for recognising characters associated with diacritical marks
Assignee: International Business Machines Corp
•
Filing: 1984-09-17
•
Granted: —
•
Expires: 2004-09-17
Abstract
Abstract The invention relates to character recognition apparatus, for recognising unknown characters of a known character set, some of the characters having diacritical marks associated therewith, which includes storage means for storing character data of an unknown character which may be associated with a diacritical mark, and recognition means for examining the stored character data in order to recognise unknown characters. The recognition means comprises extracting means for extracting from the stored character data the character data corresponding to a predetermined portion of the character which is the expected location of a diacritical mark, and examining means for examining the extracted diacritical mark character data and the rest of the stored character data of the unknown character in order to recognise the unknown character and any diacritical mark associated therewith. The invention also relates to a method of recognising unknown characters using apparatus of the above type.
Inventors
- 👤 Gregory Martin Bednar
- 👤 George Bernard Fryer
- 👤 Manthri Selvapullai Narasimha
Bibliographic Details
Application Number
—
Jurisdiction
EP
Data Source
google_patents
Last Synchronized
2026-10-29 05:12
CPC Classifications
G; G06; G06V; G06V10/00; G06V10/10; G06V10/70; G06V30/00; G06V30/10; G06V30/14; G06V30/148; G06V30/15
Claims Analysis
Total Claims: 15
Claim 1
Independent Claim
127 words
Character recognition apparatus, for recognising unknown characters of a known character set, some of the characters having diacritical marks associated therewith, including storage means for storing character data of an unknown character which may be associated with a diacritical mark, and recognition means for examining the stored character data in order to recognise unknown characters, cnaracterised in that said recognition means comprises extracting means for extracting from the stored character data the character data corresponding to a predetermined portion of the character which is the expected location of a diacritical mark, and examining means for examining the extracted diacritical mark character data and the rest of the stored character data of the unknown character in order to recognise the unknown character and any diacritical mark associated therewith.
Claim 2
Dependent Claim
127 words
Character recognition apparatus, for recognising unknown characters of a known character set, some of the characters having diacritical marks associated therewith, including storage means for storing character data of an unknown character which may be associated with a diacritical mark, and recognition means for examining the stored character data in order to recognise unknown characters, cnaracterised in that said recognition means comprises extracting means for extracting from the stored character data the character data corresponding to a predetermined portion of the character which is the expected location of a diacritical mark, and examining means for examining the extracted diacritical mark character data and the rest of the stored character data of the unknown character in order to recognise the unknown character and any diacritical mark associated therewith.
Claim 3
Dependent Claim
31 words
Apparatus as claimed in Claim 1 characterised in that said extracting means comprises means for justifying the extracted diacritical mark character data and means for storing the extracted and justitied data.
Claim 4
Dependent Claim
37 words
Apparatus as claimed in Claim 2 characterised in that said means for for justnying the extracted diacritical mark character data comprises means tor justifying said data in a direction away from the rest of the unknown character.
Claim 5
Dependent Claim
54 words
Apparatus as claimed in Claim 1 tor recognising unknown characters printed in a line and including means tor representing said characters by character line data, characterised in that said apparatus comprises segmentation means for segmenting said character line data to obtain character data of the individual unknown characters and any diacritical marks associated therewith.
Claim 6
Dependent Claim
58 words
Apparatus as claimed in Claim 4 characterised in that said segmentation means comprises means for generating a character line protile in a direction parallel to the line of unknown of unknown characters and any diacritical marks associated therewith and means for separating said profile into segments each segment representing an unknown character including any diacritical marks associated therewith.
Claim 7
Dependent Claim
78 words
Apparatus as claimed in Claim 5 characterised in that said said means for generating a character line profile comprises scanning means for scanning said line of characters along a plurality of parallel scan lines, means for generating sets ot character line data, and means for logically combining corresponding portions of said sets of character line data using an OR function so that the logically combined sets of character line data represents character widths and horizontal separations between characters.
Claim 8
Dependent Claim
194 words
Apparatus as claimed in Claim 5 characterised in that said segmentation means comprises a) means for testing said profile for gaps between characters using proposed segmentation points at predetermined initial intervals and establishing as natural segmentation points those proposed segmentation points that coincide with gaps, b) means for moving in one direction by controlled amounts those proposed segmentation points not coinciding with gaps between characters, and means for testing the protile for other gaps at the moved proposed segmentation points and establishing as the natural segmentation points those moved proposed segmentation points that coincide with the gaps, c) means for moving in the opposite direction by controlled amounts those proposed segmentation points not coinciding with gaps between characters and means for testing the profile for other gaps at the moved proposed segmentation points and establishing as the natural segmentation point those moved proposed segmentation points that coincide with the gaps and d) means for establishing the proposed segmentation points as segmentation points for profiles not divided at a gap between characters, whereby the individual portions of the profile between the segmentation points define the size of the separated individual segments of the unknown characters.
Claim 9
Dependent Claim
46 words
Apparatus as claimed in Claim 5 characterised in that said apparatus comprises means for measuring the generated profile segments of the unknown characters to distinguish larger characters which can be associated with a diacritical mark from smaller characters which cannot be associated with a diacritical mark.
Claim 10
Dependent Claim
54 words
Apparatus as claimed in Claim 8 characterised in that said means for measuring a profile segment of a character comprises means for generating an inclusive-bit-encoded word representative of the size of the character profile segment, and means for testing a given bit in said word in order to distinguish larger characters from smaller characters.
Claim 11
Dependent Claim
25 words
Apparatus as claimed in Claim 1 characterised in that said examining means examines the un-normalised diacritical mark data in order to recognise said diacritical mark.
Claim 12
Dependent Claim
38 words
Apparatus as claimed in Claim 10 characterised in that said examining comprises means for normalising the rest of the stored said character data and means for examining said normalised character data in order to recognise said unknown character.
Claim 13
Dependent Claim
34 words
Apparatus as claimed in Claim 1 characterised in that said apparatus comprises means for verifying that any recognised diacritical mark is correctly associated with a character that can be associated with a diacritical mark.
Claim 14
Independent Claim
117 words
A method of recognising unknown characters of a known character set, some of the characters having diacritical marks associated therewith, including the steps of storing character data of an unknown character which may be associated with a diacritical mark, and examining the stored character data in order to recognise unknown characters, characterised in that said examination process comprises extracting trom said stored character data the character data corresponding to a predetermined portion of the character which is the expected location of a diacritical mark, and examining said extracted diacritical mark character data and the rest of the stored character data of said unknown character in order to recognise said unknown character and any diacritical mark associated therewith.
Claim 15
Independent Claim
117 words
A method of recognising unknown characters of a known character set, some of the characters having diacritical marks associated therewith, including the steps of storing character data of an unknown character which may be associated with a diacritical mark, and examining the stored character data in order to recognise unknown characters, characterised in that said examination process comprises extracting trom said stored character data the character data corresponding to a predetermined portion of the character which is the expected location of a diacritical mark, and examining said extracted diacritical mark character data and the rest of the stored character data of said unknown character in order to recognise said unknown character and any diacritical mark associated therewith.
References Cited (Backward Citations)
US3710321A
Cited
USPTO Annuity & Maintenance Windows
Maintenance schedule is calculated for granted US utility patents.