Image recognition edge detection method and system

• US 4,969,202 A
• Filed: 03/31/1988
• Issued: 11/06/1990
• Est. Priority Date: 03/31/1988
• Status: Expired due to Term

• Current Assignee: Honeywell Incorporated (Honeywell International Inc.)
• Original Assignee: Honeywell Incorporated (Honeywell International Inc.)
• Inventors: Groezinger, John L.
• Primary Examiner(s): Moore, David K.
• Assistant Examiner(s): Mancuso, Joseph
• Application Number:
  US07/175,715
• Time in Patent Office: 950 Days
• Field of Search: 382/22, 382/52, 382/27, 382/30, 382/50, 382/53
• US Class Current: 382/199
• CPC Class Codes: G06V 10/46 Descriptors for shape, contour or point-related descriptors, e.g. scale invariant feature transform [SIFT] or bags of words [BoW]; Salient regional features colour feature extraction G06V10/56

Abstract

A system and method for determining and representing the edges of an object in an image frame formed of a two dimensional array of pixels represented by a first array of values, each value representing the gray scale of a separate pixel in the image frame. A second two dimensional array of values is produced comprising a first value for each pixel whose gray scale value is less than or equal to the threshold value and a second value for each pixel whose gray scale value is greater than the threshold value. Square groupings of four values in the second array of values are examined and a third two dimensional array of values is produced to correspond to the arrangement of the square groupings of four adjacent pixels, each of the values in the third array having a third value if diagonally located values of the grouping are the same, and having a fourth value if the diagonally located values of the grouping are different.

Claims

1. In a system in which an image frame formed of a two dimensional array of pixels is represented by a first plurality of values, each value representing the gray scale of a separate pixel in the image frame, means for determining the edges of an object in the image frame, comprising:

means for determining a gray scale threshold value;

means for producing a second plurality of values comprising a first value for each pixel whose gray scale value has a predetermined relationship to the threshold value and a second value for each pixel whose gray scale value does not have the predetermined relationship to the threshold value; and

means for examining groups of values in the second plurality of values, the groups corresponding to square groupings of four adjacent pixels, each group including first and second pairs of values corresponding to pairs of pixels located along orthogonal diagonals respectively of a square grouping of four adjacent pixels, and producing a two dimensional array of values arranged to correspond to the arrangement of the square groupings of four adjacent pixels, each value in the array having either a third or fourth value, said means for examining compares one value in a pair with the other value in said pair, said comparison being performed in both pairs, the third value occurring only if both values in said first pair are the same and both values in said second pair are the same, whereby the fourth values are arranged to represent the edges of the object in the image frame.

2. The system of claim 1 wherein the means for producing a second plurality of values produces the first value for each pixel whose gray scale value is less than or equal to the threshold value, and produces the second value for each pixel whose gray scale value is greater than the threshold value.

3. The system of claim 2 wherein said means for examining groups of values in the second plurality of values sequentially examines groups corresponding to successive square groupings of four adjacent pixels.

4. The system of claim 3 in which said means for determining a gray scale threshold value determines the gray scale threshold value by examining the gray scale values of all pixels in the array of pixels and establishes the gray scale threshold value as the median value of the gray scale values of the pixels.

5. A method for determining and representing the edges of an object in an image frame formed of a two dimensional array of pixels represented by a first plurality of values, each value representing the gray scale of a separate pixel in the image frame, the method comprising the steps of:

determining a gray scale threshold value based o the gray scale values of the pixels;

producing a plurality of values comprising a first value for each pixel whose gray scale value has a predetermined relationship to the threshold value and a second value for each pixel whose gray scale value does not have the predetermined relationship to the threshold value; and

examining groups of values in the second plurality of values corresponding to square groupings of four adjacent pixels, each group including first and second pairs of values corresponding to pairs of pixels located along orthogonal diagonals respectively of a square grouping of four adjacent pixels and producing a two dimensional array of values arranged to correspond to the arrangement of the square groupings of four adjacent pixels by comparing one value in a pair with the other value in said pair, said comparison being done for each pair, each value in the array having either a third or fourth value, the third value occurring only if both values in the first pair are the same and both values in the second pair are the same, whereby the fourth values are arranged to represent the edges of the object in the image frame.

6. The method of claim 5 wherein the step of producing a second plurality of values produces the first value for each pixel whose gray scale value is less than or equal to the threshold value, and produces the second value for each pixel whose gray scale value is greater than the threshold value.

7. The method of claim 6 wherein the step of determining a gray scale threshold value comprises:

examining the gray scale values of all pixels in the two dimensional array of pixels; and

establishing the median gray scale value of the pixels as the gray scale threshold value.

8. The method of claim 7 wherein the step of examining groups of values in the second plurality of values comprises sequentially examining successive square groupings of four adjacent pixels.

9. The method of claim 7 wherein the step of determining a gray scale threshold value further comprises:

sequentially comparing the gray scale values of individual pixels in the two dimensional array of pixels with stored intermediate maximum and minimum values;

setting the intermediate maximum value equal to the gray scale value of a pixel if the gray scale value thereof is greater than the previous intermediate maximum value;

setting the intermediate minimum value equal to the gray scale value of a pixel if the gray scale value thereof is less than the previous intermediate minimum value; and

establishing the median of the final intermediate maximum and minimum values as the gray scale threshold value.