Computer-readable storage medium, image recognition apparatus, image recognition system, and image recognition method

• US 8,705,868 B2
• Filed: 07/29/2011
• Issued: 04/22/2014
• Est. Priority Date: 02/24/2011
• Status: Active Grant

• Current Assignee: Nintendo Company Limited
• Original Assignee: Nintendo Company Limited
• Inventors: Osako, Satoru
• Primary Examiner(s): CHANG, JON CARLTON
• Application Number:
  US13/194,559
• Publication Number:
  US 20120219227A1
• Time in Patent Office: 998 Days
• Field of Search: None
• US Class Current: 382/199
• CPC Class Codes: G06T 2207/20012 Locally adaptive
• CPC Class Codes: G06T 2207/20164 Salient point detection; Corner detection
• CPC Class Codes: G06T 7/12 Edge-based segmentation
• CPC Class Codes: G06T 7/13 Edge detection
• CPC Class Codes: G06T 7/136 involving thresholding
• CPC Class Codes: G06V 10/44 Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components

Abstract

First, a difference between a pixel value of a first pixel in an image and a pixel value of a second pixel is calculated, the second pixel placed a predetermined number of pixels away from the first pixel. Then, when the difference is equal to or greater than a predetermined value, an edge determination threshold is calculated on the basis of: the pixel value of the first pixel or a pixel value of a pixel near the first pixel; and the pixel value of the second pixel or a pixel value of a pixel near the second pixel. Then, an edge pixel corresponding to an edge present between the first pixel and the second pixel is detected by comparing the edge determination threshold with a pixel value of each pixel placed between the first pixel and the second pixel.

Claims

1. A non-transitory computer-readable storage medium having stored thereon an image recognition program which, when execute by a computer of an information processing apparatus, causes the computer to perform operations comprising:

calculating a difference between a pixel value of a first pixel in an image and a pixel value of a second pixel located a predetermined number of pixels away from the first pixel;

when the difference is equal to or greater than a reference value, calculating an edge determination threshold on the basis of the pixel value of the first pixel or a pixel value of a pixel near the first pixel, and the pixel value of the second pixel or a pixel value of a pixel near the second pixel; and

detecting an edge pixel corresponding to an edge present between the first pixel and the second pixel, by comparing the edge determination threshold with pixel values of respective pixels located between the first pixel and the second pixel.

2. The non-transitory computer readable storage medium according to claim 1, wherein the operations further comprise:

detecting a local maximum value from among the pixel values of one of the first pixel and the second pixel having a larger pixel value and pixel values of pixels around the pixel having the larger pixel value; and

calculating the edge determination threshold on the basis of the detected local maximum value.

3. The non-transitory computer-readable storage medium according to claim 2, wherein

the detecting the local maximum value includes sequentially determining a large/small relationship between pixel values of two adjacent pixels, starting from the one of the first pixel and the second pixel having the larger pixel value in a direction opposite to the pixel having the smaller pixel value.

4. The non-transitory computer-readable storage medium according to claim 1, wherein

the operations further comprise:

determining whether or not a pixel value of a specific near pixel satisfies a predetermined condition, the specific near pixel placed a predetermined number of pixels away from one of the first pixel and the second pixel having a smaller pixel value in a direction opposite to the pixel having the larger pixel value; and

when the determining has determined that the predetermined condition is satisfied, calculating the edge determination threshold on the basis of the pixel value of the specific near pixel.

5. The non-transitory computer-readable storage medium according to claim 4, wherein the operations further comprise

when the pixel value of the one of the first pixel and the second pixel having the smaller pixel value is smaller than the pixel value of the specific near pixel, and a difference between the pixel value of the specific near pixel and the pixel value of the one of the first pixel and the second pixel having the larger pixel value, or the pixel near the pixel having the larger pixel value, is equal to or greater than the reference value, determining that the predetermined condition is satisfied.

6. The non-transitory computer-readable storage medium according to claim 1, wherein

the operations further include calculating, as the edge determination threshold, an average value of the pixel value of the first pixel or the pixel near the first pixel, and the pixel value of the second pixel or the pixel near the second pixel.

7. The non-transitory computer-readable storage medium according to claim 1, the image recognition program causing the computer to perform operations further comprising:

on the basis of the edge determination threshold, detecting another edge pixel in a portion different from a part of the edge corresponding to the detected edge pixel.

8. The non-transitory computer-readable storage medium according to claim 7, wherein the operations further comprise

detecting, from among a plurality of pixels adjacent to an already detected edge pixel, a new edge pixel continuous with the edge pixel on the basis of the edge determination threshold.

9. The non-transitory computer-readable storage medium according to claim 7, the image recognition program causing the computer to perform further operations comprising:

determining whether or not the detected new edge pixel coincides with any of already detected edge pixels, wherein

when the determining has determined a predetermined number of consecutive times that the detected new edge pixel coincides with any of the already detected edge pixels, suspending a process of sequentially detecting a new edge pixel.

10. The non-transitory computer-readable storage medium according to claim 7, wherein the operations further comprise:

on the basis of the edge determination threshold, repeatedly detecting edge pixels continuous with the edge corresponding to the detected edge pixel;

detecting an area specified by the detected edge pixels.

11. The non-transitory computer-readable storage medium according to claim 1, wherein the operations further comprise

when a pixel value of a pixel around one of the first pixel and the second pixel having a larger pixel value is larger than the pixel value of the pixel having the larger pixel value, calculating the edge determination threshold on the basis of the pixel value of the pixel around the pixel having the larger pixel value.

12. The non-transitory computer-readable storage medium according to claim 1, wherein the operations further comprise:

repeatedly acquiring images; and

calculating a difference between the pixel value of the first pixel in the repeatedly acquired images and the pixel value of the second pixel placed a predetermined number of pixels away from the first pixel.

13. The non-transitory computer-readable storage medium according to claim 1, wherein

the operations further comprise acquiring the image from a capturing device connected to the information processing apparatus.

14. An image recognition apparatus comprising:

a memory; and

at least one processor communicatively coupled to the memory and configured to perform operations comprising;

calculating a difference between a pixel value of a first pixel in an image and a pixel value of a second pixel located a predetermined number of pixels away from the first pixel;

when the difference is equal to or greater than a reference value, calculating an edge determination threshold on the basis of the pixel value of the first pixel or a pixel value of a pixel near the first pixel, and the pixel value of the second pixel or a pixel value of a pixel near the second pixel; and

detecting an edge pixel corresponding to an edge present between the first pixel and the second pixel, by comparing the edge determination threshold with pixel values of respective pixels located between the first pixel and the second pixel.

15. An image recognition method comprising:

calculating a difference between a pixel value of a first pixel in an image and a pixel value of a second pixel located a predetermined number of pixels away from the first pixel;

when the difference is equal to or greater than a reference value, calculating an edge determination threshold on the basis of the pixel value of the first pixel or a pixel value of a pixel near the first pixel, and the pixel value of the second pixel or a pixel value of a pixel near the second pixel; and

detecting an edge pixel corresponding to an edge present between the first pixel and the second pixel, by comparing the edge determination threshold with pixel values of respective pixels located between the first pixel and the second pixel.

16. An image recognition system comprising:

at least one camera; and

at least one processor communicatively coupled to the at least one camera, and configured to perform operations comprising;

receiving an image captured by the camera;

calculating a difference between a pixel value of a first pixel in the image and a pixel value of a second pixel located a predetermined number of pixels away from the first pixel;

when the difference is equal to or greater than a reference value, calculating an edge determination threshold on the basis of;

the pixel value of the first pixel or a pixel value of a pixel near the first pixel, and the pixel value of the second pixel or a pixel value of a pixel near the second pixel; and

detecting an edge pixel corresponding to an edge present between the first pixel and the second pixel, by comparing the edge determination threshold with pixel values of respective pixels located between the first pixel and the second pixel.

17. An image recognition system including an image recognition apparatus and a marker, the image recognition apparatus comprising:

a capturing section for capturing an image including the marker; and

at least one processor configured to perform operations comprising;

receiving the image from the capturing section;

calculating a difference between a pixel value of a first pixel in the image and a pixel value of a second pixel located a predetermined number of pixels away from the first pixel;

when the difference is equal to or greater than a reference value, calculating an edge determination threshold on the basis of the pixel value of the first pixel or a pixel value of a pixel near the first pixel, and the pixel value of the second pixel corresponding to the first pixel or a pixel value of a pixel near the second pixel; and

detecting an edge pixel corresponding to an edge present between the first pixel and the second pixel, by comparing the edge determination threshold with pixel values of respective pixels located between the first pixel and the second pixel.

18. An image recognition apparatus comprising:

a memory; and

a processing system communicatively coupled to the memory and configured to perform operations comprising;

calculating a difference between a pixel value of a first pixel in an image and a pixel value of a second pixel located in a same row or column as the first pixel and being predetermined number of pixels away from the first pixel;

when the difference is equal to or greater than a predetermined value, calculating an edge determination threshold on the basis of a first local maximum pixel value determined from a first group of pixels including the first pixel and one or more pixels proximate to the first pixel and located in the same row or column and a second local maximum pixel value determined from a second group of pixels including the second pixel and one or more pixels proximate to the second pixel and located in the same row or column; and

detecting an edge pixel corresponding to an edge present between the first pixel and the second pixel, by comparing the edge determination threshold with pixel values of respective pixels located between the first pixel and the second pixel in the same row or column.