Method and apparatus for recognition of discontinuous text

• US 4,680,805 A
• Filed: 11/17/1983
• Issued: 07/14/1987
• Est. Priority Date: 11/17/1983
• Status: Expired due to Fees

• Current Assignee: Texas Instruments, Inc.
• Original Assignee: Texas Instruments, Inc.
• Inventors: Scott, Warner C.
• Primary Examiner(s): Boudreau, Leo H.
• Assistant Examiner(s): NOT, DEFINED
• Application Number:
  US06/552,956
• Time in Patent Office: 1,335 Days
• Field of Search: 382/21, 382/22, 382/60
• US Class Current: 382/197
• CPC Class Codes: G06V 30/10 Character recognition
• CPC Class Codes: G06V 30/182 by coding the contour of the pattern

Abstract

Circumnavigation using an increased test cell domain may be used to collect data from discontinuous characters stored in a bit map such as those printed by a dot matrix printer. The test cell domain is increased to locate a pixel and consider it a portion of the same character if it is within the minimum permissable pixel gap range. The sequence of testing must be designed to read each possible pixel and not enter an endless loop during the circumnavigation. One sequence of testing is to begin testing those cells in the column adjacent to the reference cell beginning of the cell in the row adjacent to the reference cell and testing cells adjacent to the most recently tested cell along the entire column until the desired number of cells in that column according to the minimum permissable pixel gap range have been tested. Each column adjacent to the most recently tested is tested in the described sequence until the desired number of columns have been tested to permit the minimum permissable gap spacing. The last set of cells tested are in the same row as the reference cell beginning at the cell adjacent to the reference cell and testing each cell adjacent to the most recently read cell. This is a method by which discontinuous text such as dot matrix print or poor quality print may be recognized. An apparatus for carrying out the method of this invention includes an optical scanner, memory, template reference characters and an output device to provide the ASCII code of the recognized sample character.

Claims

1. The method of character recognition comprising:

(a) storing data representative of a sample character having individual pixels in the sample character,

(b) locating a starting pixel on the periphery of said sample character,

(c) storing the starting pixel as a reference pixel,

(d) testing pixels starting on a pixel located in a column and a row adjacent to the column and row of the starting pixel and testing all pixels in that adjacent column for K number of pixels, K being variable and greater than 1;

(e) testing each pixel in the next adjacent column to the just tested column starting on a pixel in a row adjacent to the row of the reference pixel, performing the testing for K columns,

(f) testing each pixel in the same row as the reference pixel, performing the testing for K pixels in that same row,

(g) stopping the testing of steps d-f whenever a black pixel is located, storing it as the reference pixel and repeating steps d-h,

(h) when steps d-f have been completed and no black cell has been located rotating the reference coordinates 90 degrees so as to present a new set of columns and rows, the old rows now being columns and the old columns now being rows with respect to the reference cell and repeating steps d-h,

(i) stopping the testing when the beginning pixel has been returned to as the starting pixel,

(j) recognizing the sample character, and;

(k) outputting an indication of the identity of the sample character.

2. The method according to claim 1 wherein K is 2.

3. The method according to claim 1 wherein K is increased and steps b-k of claim 1 are repeated on the same sample character in the event the sample character is not recognized on the first attempt.

4. The method according to claim 1 wherein K is decreased and steps b-k of claim 1 are repeated on the same sample character in the event the sample character is not recognized on the first attempt.

5. The method according to claim 1 wherein the maximum number of test cells from a single reference pixel and single compass heading is determined by the equation, ##EQU2## where TC_max is the maximum number of test cells from a single compass heading and N is the pixel gap tolerance.