← Back to Patent Explorer
US4926490A Expired / Lapsed US ⏱️ 0.0 years remaining

Method and apparatus for recognizing characters on a document

Assignee: International Business Machines Corp
•
Filing: 1988-04-15
•
Granted: 1990-05-15
•
Expires: 2008-04-15
📄 Original PDF 🌐 Google Patents 🔄 Sync Now

Abstract

Abstract A method and apparatus for recognizing characters on a document, even if the document is skewed or not aligned with the axis of a typical segmentation apparatus such as a scanner. A plurality of rectangles are formed surrounding respective character images, with position data for each rectangle stored in a first table in which plural position data of the rectangles are arranged in order from the left-most rectangle to the right-most rectangle in the X direction of the XY coordinates of the image buffer. By determining the rectangles belonging to one character row in the first list and calculating the positions of the bottom left corners of the rectangles, skew of the document is calculated. Vertical positions of the rectangles compensated by the skew in the Y direction are calculated to transfer the position data of the rectangles belonging to the first character row to a second table. The image data surrounded by the rectangles specified by the position data in the second list are sequentially supplied to a character recognition unit.

Inventors

  • 👤 Takashi Mano

Bibliographic Details

Application Number —
Jurisdiction US
Data Source google_patents
Last Synchronized 2026-10-25 09:17
CPC Classifications
G; G06; G06V; G06V30/00; G06V30/10; G06V30/14; G06V30/146; G06V30/1475; G06V30/1478

Claims Analysis

Total Claims: 15
Claim 1
Independent Claim 150 words
A method for recognizing characters on a document comprising steps of: storing an image of said document in an image storage means: detecting position of rectangles in XY coordinates of said image storage means, which contact outer boundaries of character images, respectively in plural character rows stored in said image storage means, to generate position data representing said positions of said rectangles; forming a list in which said position data of the rectangles are arranged in the order from one end to the other end along the direction of X axis of said XY coordinates; detecting a range in Y axis for one character row based upon Y axis information of said position data of said rectangles in said list; and fetching said character images stored in said image storage means by using said position data of said rectangles which fall into said range, to recognize said fetched character images.
Claim 2
Independent Claim 150 words
A method for recognizing characters on a document comprising steps of: storing an image of said document in an image storage means: detecting position of rectangles in XY coordinates of said image storage means, which contact outer boundaries of character images, respectively in plural character rows stored in said image storage means, to generate position data representing said positions of said rectangles; forming a list in which said position data of the rectangles are arranged in the order from one end to the other end along the direction of X axis of said XY coordinates; detecting a range in Y axis for one character row based upon Y axis information of said position data of said rectangles in said list; and fetching said character images stored in said image storage means by using said position data of said rectangles which fall into said range, to recognize said fetched character images.
Claim 3
Independent Claim 210 words
A method for recognizing characters on a document comprising steps of: storing image data representing image of said document in image storage means; detecting positions of rectangles in the XY coordinates of said image storage means, which contact outer boundaries of each character image in plural character rows stored in said image storage means to generate position data representing said positions of said rectangles: storing said position data of said rectangles to form a first list in which plural position data of said rectangles are arranged in the order from one end to the other end in a direction of X axis of said XY coordinates; determining the position data of a predetermined number of rectangles belonging to one character row to detect a skew of said document in said XY coordinates; generating a virtual position of each rectangle by correcting the position in Y axis of said XY coordinates of each rectangle in said first list by said skew to transfer said position data of said rectangles belonging to the first character row from said first list to a second list; and supplying from said image storage means to a character recognition means said image data surrounded by said rectangles specified by said position data in said second list.
Claim 4
Independent Claim 210 words
A method for recognizing characters on a document comprising steps of: storing image data representing image of said document in image storage means; detecting positions of rectangles in the XY coordinates of said image storage means, which contact outer boundaries of each character image in plural character rows stored in said image storage means to generate position data representing said positions of said rectangles: storing said position data of said rectangles to form a first list in which plural position data of said rectangles are arranged in the order from one end to the other end in a direction of X axis of said XY coordinates; determining the position data of a predetermined number of rectangles belonging to one character row to detect a skew of said document in said XY coordinates; generating a virtual position of each rectangle by correcting the position in Y axis of said XY coordinates of each rectangle in said first list by said skew to transfer said position data of said rectangles belonging to the first character row from said first list to a second list; and supplying from said image storage means to a character recognition means said image data surrounded by said rectangles specified by said position data in said second list.
Claim 5
Dependent Claim 73 words
A method for recognizing characters in a document according to claim 2, wherein said step of detecting positions of rectangles includes: a step of generating rectangles each of which contacts outer boundaries of discrete images of said document stored in said image storage means, and a step of determining as to whether each rectangle has a size which falls into a predetermined size range settled for said characters and symbols to be recognized.
Claim 6
Dependent Claim 33 words
A method for recognizing characters in a document according to claim 2, wherein said position data represents the positions of top, bottom, left and right edges of said rectangle in said XY coordinates.
Claim 7
Dependent Claim 88 words
A method for recognizing characters on a document according to claim 2, wherein said step of determining the position data includes a step of searching said first list to detect said predetermined number of rectangles, with a bottom left corner of one rectangle being located within a predetermined distance in said X and Y axes from a bottom left corner of the preceding rectangle, and a step of performing calculations of the positions of bottom left corners of said detected rectangles to detect said skew of said document.
Claim 8
Dependent Claim 166 words
A method for recognizing characters on a document according to claim 2, wherein said step of generating virtual position includes a step of sequentially reading said position data of said rectangles in said first list in said arranged order, a step of generating virtual position of each rectangle by correcting the position in said Y axis of each rectangle in said first list by said skew, a step of storing in a register the virtual position of said rectangle located at the highest position on said document, a step of sequentially reading again said position data of said rectangles in said first list, a step of generating said virtual position of said rectangle, a step of determining as to whether said generated virtual position falls into a predetermined range from said virtual position stored in said register, a step of transferring said position data of said rectangle in said first list, said generated virtual position of which falls into said predetermined range, to said second list.
Claim 9
Dependent Claim 117 words
A character recognition apparatus includes: image storage means for storing image of a document; means for detecting positions of rectangles each of which contacts outer boundaries of each of plural character images stored in said image storage means to generate position data representing said position; means for arranging said rectangles in the order from one end to the other end in a direction of X axis based upon X axis information of said position data; means for selecting rectangles belonging to a character row based upon Y axis information of said ordered rectangles: and means for fetching character images from said image storage means by using said position data of said rectangles to recognize said character images.
Claim 10
Dependent Claim 117 words
A character recognition apparatus includes: image storage means for storing image of a document; means for detecting positions of rectangles each of which contacts outer boundaries of each of plural character images stored in said image storage means to generate position data representing said position; means for arranging said rectangles in the order from one end to the other end in a direction of X axis based upon X axis information of said position data; means for selecting rectangles belonging to a character row based upon Y axis information of said ordered rectangles: and means for fetching character images from said image storage means by using said position data of said rectangles to recognize said character images.
Claim 11
Dependent Claim 56 words
A character recognition apparatus of the type described in claim 7, wherein said means for detecting positions of rectangles determines as to whether a size of each rectangles falls into a scope of sizes of said characters and symbols to be recognized, and means for generating position data of rectangles falling into said scope of sizes.
Claim 12
Dependent Claim 34 words
A character recognition apparatus of the type described in to claim 7, wherein said position data represent upper, bottom, left and right edges of said rectangles in XY coordinates of said image storage means.
Claim 13
Dependent Claim 63 words
A character recognition apparatus of the type described in claim 7, wherein said means for arranging said rectangles including a first table memory storing a first list which stores said position data of said rectangles of plural character rows of said document in the order from one end to the other end in said direction of said X axis of said XY coordinates.
Claim 14
Dependent Claim 213 words
A character recognition apparatus of the type described in claim 7, wherein said means for selecting rectangles sequentially includes means for reading said position data of said rectangles of said first list in said arranged order, means for detecting a predetermined number of rectangles, in which a bottom left corner of one rectangle is located within predetermined distances in said X and Y directions from a bottom left corner of the preceding rectangle. means for detecting a skew of said document based upon the positions of bottom left corners of said detected rectangles, means for sequentially reading again said position data of said rectangles of said first list in said arranged order to generate a virtual position of each rectangle which is a Y axis position corrected by said skew, means for storing a virtual position located at a highest position of said document into a register, means for sequentially reading again said position data of said first list in said arranged order to generate said virtual positions of said rectangles, means for determining whether said generated virtual positions falls into a predetermined range from said virtual position in said register, and means for transferring said position data of rectangle having said virtual position falling into said predetermined range to a second list.
Claim 15
Dependent Claim 39 words
A character recognition apparatus of the type described in claim 7, wherein said means for selecting rectangles sequentially reads said position data from said second list to said character images surrounded by said rectangles and recognizes said character images.

References Cited (Backward Citations)

No citation records indexed.

USPTO Annuity & Maintenance Windows

Annuity Stage Window Opens Payment Deadline Surcharge Period Until Estimated Fee Status
3.5 Years (Year 4) 1993-05-14 1993-11-13 1994-05-15 $2000.00 Window Closed / Lapsed
7.5 Years (Year 8) 1997-05-14 1997-11-13 1998-05-15 $3760.00 Window Closed / Lapsed
11.5 Years (Year 12) 2001-05-14 2001-11-13 2002-05-15 $7700.00 Window Closed / Lapsed

Assigned Categories & Tags

No categories assigned to this patent yet.

Assign Category Tag