公开(公告)号：DE10010621B4

公开(公告)日：2006-08-24

申请号：DE10010621

申请日：2000-03-03

Applicant: IBM

Inventor： FINKELSTEIN LEV ,  HEILPER ANDRE ,  WALACH EUGENE

IPC: G06K9/32

Abstract: A method for locating a structured field in a gray-scale image of an object, including choosing a plurality of anchor points in the image, each anchor point having a gray-scale value associated therewith. For each anchor point there is determined a horizontal variation dependent on a difference between the gray-scale value of the anchor point and the gray-scale value of a horizontally neighboring anchor point, and there is also determined a vertical variation dependent on a difference between the gray-scale value of the anchor point and the gray-scale value of a vertically neighboring anchor point. Those anchor points whose vertical and horizontal variations obey a first or a second predefined condition are defined as vertically or horizontally dominant respectively. One or more kernels are defined in the image, each such kernel comprising a group of anchor points n predetermined mutual proximity and satisfying a third predefined condition relating the number of vertically-dominant and horizontally-dominant anchor points in the group. The structured field in the image is located using one or more kernels.

公开(公告)号：DE10010621A1

公开(公告)日：2000-09-21

申请号：DE10010621

申请日：2000-03-03

Applicant: IBM

Inventor： FINKELSTEIN LEV ,  HEILPER ANDRE ,  WALACH EUGENE

IPC: G06K9/32

Abstract: Selects number of anchor points in image, each assigned gray scale value. Determines horizontal and vertical deviation for each point, which is dependent on difference between gray scale value of anchor point and gray scale value of neighboring horizontal or vertical anchor point. Defines anchor point as dominant if corresponds to predefined condition. In first processing stage a general search for regions of interest (ROI) is carried out. Dominance is determined (52) by selecting first number of anchor points each having corresponding intensity. Each anchor point has horizontal and vertical deviation calculated to determine vertical and horizontal dominant points used to determine (54) probable text containing positions in image. Second processing stage carries out second iteration with text regions of interest found in first stage, to improve recognition of text ROIs, delete ROIs falsely labelled and to assign order of precedence to text ROIs.