Pattern recognition apparatus

• US 4,972,499 A
• Filed: 03/28/1989
• Issued: 11/20/1990
• Est. Priority Date: 03/29/1988
• Status: Expired due to Term

• Current Assignee: Kabushiki Kaisha Toshiba (Toshiba Corporation)
• Original Assignee: Kabushiki Kaisha Toshiba (Toshiba Corporation)
• Inventors: Kurosawa, Yoshiaki
• Primary Examiner(s): Moore, David K.
• Assistant Examiner(s): COUSO, YON JUNG
• Application Number:
  US07/329,871
• Time in Patent Office: 602 Days
• Field of Search: 382/38, 382/13, 382/9, 382/30, 382/36, 382/22, 382/34
• US Class Current: 382/227
• CPC Class Codes: G06V 30/248 involving plural approaches, e.g. verification by template match; Resolving confusion among similar patterns, e.g. "O" versus "Q" G06V30/242 takes precedence

Abstract

A pattern recognition apparatus has a contour segmentation unit for dividing an input pattern into segments, a characteristic extraction unit for extracting characteristics of the input segments, and a reference unit for storing characteristic data of reference patterns. The reference unit includes a main reference and a detailed matching reference. The main reference stores partial pattern characteristic data representing the characteristics of segments of each reference pattern. The detailed matching reference stores detailed characteristic data of each reference pattern together with a program for specifying an operation procedures thereof. A matching processor sequentially compares and collates the input pattern with the reference patterns to find out that standard pattern with which the input pattern is matched with the highest similarity. When the input pattern is matched with several reference patterns, a detailed recognition unit performs a detailed recognition process using the detailed characteristic data of these reference patterns to finally select the correct one from among the reference patterns. The main reference additionally stores identification marks to identify specific reference segments necessary to acquired the above detailed characteristic data.

Claims

1. An apparatus for automatically recognizing an input pattern, comprising:

(a) contour segmentation means for segmenting a detected contour line of an input pattern into an array of input contour segments;

(b) characteristic extraction means for extracting a line characteristic of each of said input contour segments;

(c) reference storage means for storing characteristic data of standard patterns, said reference storage means having,

main reference storage means for storing partial pattern characteristic data representing line characteristics of an array of reference contour segments of each of said standard patterns, and

detailed matching reference storage means for storing detailed line characteristic data of each array of said standard patterns together with a program for specifying an operation sequence of said detailed characteristic data; and

(d) matching processor means, connected to said characteristic extraction means and said main reference storage means, for extracting a primary matching process in which said input contour pattern is sequentially compared and collated with said standard contour patterns to find out that standard pattern with which said input pattern is matched with highest similarity;

(e) detailed recognition means, connected to said matching processor means and said detailed matching reference storage means, for executing a secondary recognition process in such a manner that, when said input contour pattern is matched in its line characteristic with several standard contour patterns, said detailed recognition means executes a detailed recognition process using said detailed characteristic data of partial patterns of input patterns corresponding to specific partial patterns said standard patterns to select a correct standard contour pattern from among said matched standard contour patterns,

said main reference storage means additionally storing identification marks for identifying specific reference contour segments necessary to acquire said detailed characteristic data, said marks absolutely identifying the partial patterns corresponding to the specific reference segments regardless of the sequence of appearance thereof in the array of said input segments.

2. The apparatus according to claim 1, wherein said identification marks include code data.