Apparatus and method for separating handwritten characters by line and word
First Claim
1. A computer system for locating a predetermined group of characters from a plurality of handwritten characters characterized by a plurality of spaced, horizontally aligned, vertical strokes, said characters being chosen from a digital pixel image consisting of foreground pixels and background pixels set forth in an array of columns and row, said foreground image pixels defining said characters, said computer system comprising:
- means for assigning each of said plurality of characters to one of a plurality of discrete character lines;
means for selecting a desired discrete character line from said plurality of discrete character lines;
scanning means for generating a digital data stream corresponding to individual pixels of said digital pixel image;
means for storing sequential portions of said digital data stream in a two-dimensional array;
means for recognizing from said stored data array contiguous foreground image pixels corresponding to vertical strokes and defining adjacent pairs thereof;
means for computing horizontal distances between members of said adjacent pairs of vertical strokes, and determining a histogram of occurrences of said distances and a first peak distance in said histogram, said first peak distance referred to as the interstroke distance;
means for grouping the plurality of characters together into blocks based on the interstroke distance and on a second or subsequent peak of said histogram corresponding to a wider horizontal distance between said characters, said characters being separated by the interstroke distance and said blocks being separated by the wider distance; and
means for selecting said predetermined group of characters from those grouped character blocks associated with said selected discrete character line by using said interstroke distance.
5 Assignments
0 Petitions
Accused Products
Abstract
A computer system and a method for a mail sorting operation in which the computer system determines the location of the ZIP code within a digital image of an address block from a piece of mail. An interstroke distance is calculated for the image and the strokes of the image are thinned to enhance vertical separation between the lines of the address block. A medial axis for each line is determined and the medial axis is superimposed upon the digital image. A bleeding operation is conducted on the digital image from the medial axis at which data bits that do not connect to the medial axis are notated as punctuation and interlinear connected strokes are then divided between the two lines. The last line which is determined to be large enough to contain a ZIP code based on bounding box size is then selected. Alternate splits of words are formed and the best split is selected in which the last formed group is detected to be the ZIP code.
47 Citations
3 Claims
-
1. A computer system for locating a predetermined group of characters from a plurality of handwritten characters characterized by a plurality of spaced, horizontally aligned, vertical strokes, said characters being chosen from a digital pixel image consisting of foreground pixels and background pixels set forth in an array of columns and row, said foreground image pixels defining said characters, said computer system comprising:
-
means for assigning each of said plurality of characters to one of a plurality of discrete character lines; means for selecting a desired discrete character line from said plurality of discrete character lines; scanning means for generating a digital data stream corresponding to individual pixels of said digital pixel image; means for storing sequential portions of said digital data stream in a two-dimensional array; means for recognizing from said stored data array contiguous foreground image pixels corresponding to vertical strokes and defining adjacent pairs thereof; means for computing horizontal distances between members of said adjacent pairs of vertical strokes, and determining a histogram of occurrences of said distances and a first peak distance in said histogram, said first peak distance referred to as the interstroke distance; means for grouping the plurality of characters together into blocks based on the interstroke distance and on a second or subsequent peak of said histogram corresponding to a wider horizontal distance between said characters, said characters being separated by the interstroke distance and said blocks being separated by the wider distance; and means for selecting said predetermined group of characters from those grouped character blocks associated with said selected discrete character line by using said interstroke distance. - View Dependent Claims (2, 3)
-
Specification