Browse Prior Art Database

Image Adjustment Using Optical Character Recognition

IP.com Disclosure Number: IPCOM000112978D
Original Publication Date: 1994-Jun-01
Included in the Prior Art Database: 2005-Mar-27
Document File: 2 page(s) / 44K

Publishing Venue

IBM

Related People

Nakano, K: AUTHOR

Abstract

Disclosed is a method for image data reduction method for Optical Character Recognition (OCR). OCR System recommends that recognized data by OCR is arranged just above/below image data in the view point of simplicity of modification as shown in Fig. 1.

This text was extracted from an ASCII text file.
This is the abbreviated version, containing approximately 70% of the total text.

Image Adjustment Using Optical Character Recognition

      Disclosed is a method for image data reduction method for
Optical Character Recognition (OCR).  OCR System recommends that
recognized data by OCR is arranged just above/below image data in the
view point of simplicity of modification as shown in Fig. 1.

      However, if the width of the recognition date does not equal to
the width of the image data, an operator using OCR must feel the
inconvenience, as shown in Fig.  2.

      Therefore, the OCR system adjusts horizontal and the vertical
size of the image data automatically, using character count of
recognition data, display resolution, image resolution.  This
disclosure describes the method of image data adjustment (called
image reduction ratio).

Rdv = dot count per 1 byte display character box in vertical
direction.(dots)
 Rdh = dot count per 1 byte display character box in horizontal
direction.(dots)
 Riv = dot count per image in vertical direction.(dots)
 Rih = dot count per image in horizontal direction .(dots)
 Himg = Hrec + DELTAv = height of image data
 Wimg = Wrec + DELTAh = width of image data
(note :  Hrec = height of recognized data, Wrec = width of
recognized data.  DELTAv/DELTAh is distance between recognized
data and image data)

Recognition data consists of character box.
 Wrec = (Wr + Gr) * N - Gr
 (note : Wr = Character box width,
 Gr = Character box gap, N = Character count)
 RAMDAh = reduction ratio in horizontal direct...