公开(公告)号：GB2312304B

公开(公告)日：1999-12-29

申请号：GB9608021

申请日：1996-04-18

Applicant: IBM

Inventor： UR SHMUEL ,  YAIR EYAL

IPC: B41J11/00 ,  B41J13/26

Abstract: A method is described for calibrating a printer and/or a scanner so that information can be printed at a desired location with respect to a sheet, the method comprising: storing a first set of markings as a first image in digital form; printing, using a printer to be calibrated, the first image on a sheet to form a printed sheet; scanning the printed sheet to generate a second image stored in digital form; comparing the first image and the second image, or an image derived from the second image, to determine a first transformation which maps the first set of markings in the second image, or the image derived from the second image, onto the first set of markings on the first image; storing parameters of the first transformation for subsequent use by applying the first transformation to information to be printed at the desired location. Using this method the bias transformations associated with a printer and/or a scanner can be accurately measured and stored for future use in printing. The method finds particular application in a system for enabling the filling in of preprinted forms.

公开(公告)号：GB2289969A

公开(公告)日：1995-12-06

申请号：GB9410369

申请日：1994-05-24

Applicant: IBM

Inventor： YAIR EYAL

IPC: G06K9/34

Abstract: Image processing apparatus is disclosed for segmenting an input image into image portions each containing a single character, the apparatus comprising identification logic for identifying connected components in the input image; classification logic, including a neural network, for determining into which of a number of predefined classes a connected component falls, at least one of said classes indicating that the connected component is most likely to be a single character; merging logic and splitting logic for merging and splitting the connected components. The merging and splitting logic and the classification logic are arranged to operate so that the connected components are iteratively merged and/or split and the resulting split and/or merged connected components reclassified by the classification logic until an image segmentation is achieved which meets a predefined criterion.