Pattern detection method
First Claim
1. A method of pattern detection comprising the steps of:
- obtaining an image of an object;
converting the image obtained into two-dimensional image data P(X, Y) at points (X, Y), wherein X and Y denote coordinates existing along two directions perpendicular to one another;
setting operation reference points Cs (Xm, Yn) in two dimensions spaced from each other by a step size which is smaller than a size of the image of the object, wherein Xm and Yn denote m-th and n-th coordinates existing along two directions and m and n denote integral numbers;
providing a two-dimensional template having a size smaller than the image of the object and having weights T(xi, yi) at a plurality of points (xi, yi) wherein xi and yi denote x and y coordinates of an i-th point and i denotes an integral number;
setting a position reference point of the template T(xi, yi) at each of the operation reference points Cs (Xm, Yn);
calculating a weighted sum of the image data P(X, Y) by using the template T(xi, yi) for each of the operation reference points Cs (Xm, Yn);
determining the operation reference points Cs (Xm, Yn) as being candidate points when the weighted sum thereof is larger than a predetermined value;
grouping the candidate points into candidate groups comprising a plurality of adjacent candidate points, wherein the candidate groups sufficiently define a representative contour of the object; and
determining a position of the object based on positions of the candidate groups.
1 Assignment
0 Petitions
Accused Products
Abstract
When an image of an object is recognized, a template having a size smaller than the object is used. First, operation reference points Cs (Xm, Yn) are set at steps smaller than lengths along the X and Y directions of an image of an object to be recognized, and a template T(xi, yi) is set at the operation reference points Cs (Xm, Yn). Then, an equation, ##EQU1## is operated based on the template T(xi, yi) and the image data P(X, Y). Next, candidate points are determined as points having M(Xm, Yn) larger than a reference value. Then, a position of the image of the object is determined according to the candidate points. Even if an image to be recognized is inclined, the position and the slope of the image can be detected at a fast speed even for image data with noise.
-
Citations
8 Claims
-
1. A method of pattern detection comprising the steps of:
-
obtaining an image of an object; converting the image obtained into two-dimensional image data P(X, Y) at points (X, Y), wherein X and Y denote coordinates existing along two directions perpendicular to one another; setting operation reference points Cs (Xm, Yn) in two dimensions spaced from each other by a step size which is smaller than a size of the image of the object, wherein Xm and Yn denote m-th and n-th coordinates existing along two directions and m and n denote integral numbers; providing a two-dimensional template having a size smaller than the image of the object and having weights T(xi, yi) at a plurality of points (xi, yi) wherein xi and yi denote x and y coordinates of an i-th point and i denotes an integral number; setting a position reference point of the template T(xi, yi) at each of the operation reference points Cs (Xm, Yn); calculating a weighted sum of the image data P(X, Y) by using the template T(xi, yi) for each of the operation reference points Cs (Xm, Yn); determining the operation reference points Cs (Xm, Yn) as being candidate points when the weighted sum thereof is larger than a predetermined value; grouping the candidate points into candidate groups comprising a plurality of adjacent candidate points, wherein the candidate groups sufficiently define a representative contour of the object; and determining a position of the object based on positions of the candidate groups. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8)
-
Specification