Method of detecting the position of an object pattern in an image

• US 5,226,095 A
• Filed: 05/26/1992
• Issued: 07/06/1993
• Est. Priority Date: 11/04/1988
• Status: Expired due to Fees

• Current Assignee: Matsushita Electric Industrial Company Limited (Panasonic Holdings Corporation)
• Original Assignee: Matsushita Electric Industrial Company Limited (Panasonic Holdings Corporation)
• Inventors: Okumura, Kazumasa, Mizuoka, Seiji
• Primary Examiner(s): Moore, David K.
• Assistant Examiner(s): Fox, David
• Application Number:
  US07/890,323
• Time in Patent Office: 406 Days
• Field of Search: 382/48, 382/22, 382/27, 382/30, 382/34, 382/8
• US Class Current: 382/151
• CPC Class Codes: G06T 2207/30148 Semiconductor; IC; Wafer
• CPC Class Codes: G06T 7/70 Determining position or orientation of objects or cameras camera calibration G06T7/80

Abstract

A method in which the position of an object pattern in an image can be accurately detected is disclosed. The method comprises the steps of: (a) preparing a reference pattern which has a pattern and a background which are composed of pixels each having a value regarding the brightness or gradation; (b) dividing the image into a plurality of sections; (c) selecting arbitrarily an area having two or more of the sections; (d) obtaining the brightness data from each of the sections; (e) obtaining a sum of products of the value of each pixel and the brightness data of each section corresponding to the pixel; (f) moving the area to another position in the image; (g) repeating steps (d) to (f); and (h) deciding that the area from which the sum having an extreme value is obtained is the one containing the object pattern.

Claims

1. A method of detecting the position of an object pattern in an image, comprising the steps of:

(a) preparing two or more reference patterns which have a foreground pattern and a background, said foreground pattern and background being composed of one or more pixels each having a value of 1, 0 or -1 regarding the brightness wherein the total of said values is zero, the shape obtained from said foreground patterns when said reference patterns are arranged in a predetermined geometrical or positional relationship corresponding to said object pattern, the brightness value of each pixel of said foreground pattern being different from that of each pixel of said background, a portion of each of said reference patterns being designated as a specific portion, such that pixels having a value of 0 are not positioned between pixels having a value of 1 and pixels having a value of -1;

(b) storing said positional relationship;

(c) dividing said image into a plurality of sections;

(d) selecting arbitrarily an area having two or more of said sections, the shape of said area corresponding to that of said reference pattern;

(e) obtaining brightness data from each of said sections;

(f) obtaining a sum of products of the brightness value of each pixel of both said reference pattern and other reference patterns and the brightness data of each section corresponding to the pixel;

(g) moving said area to another position in said image;

(h) repeating steps (e) to (g);

(i) selecting two or more portions from which the sum having an extreme value or a value adjacent to said extreme value is obtained, for both said reference pattern and other reference patterns;

(j) obtaining the position in each of said selected portions which corresponds to said specific part or said other specific part;

(k) obtaining the positional relationships in each pair of said obtained positions;

(l) obtaining the pair having the positional relationship which is closest to said stored positional relationship; and

(m) deciding that the area which corresponds to said obtained pair is the one containing said object pattern.

2. A method according to claim 1 wherein said extreme value is the largest value among said obtained sums.

3. A method according to claim 1 wherein said extreme value is the smallest value among said obtained sums.