Marker processing method, marker processing device, marker, object having a marker, and marker processing program

• US 8,526,668 B2
• Filed: 07/09/2010
• Issued: 09/03/2013
• Est. Priority Date: 07/31/2009
• Status: Expired due to Fees

• Current Assignee: Seiko Epson Corporation (Seiko Group)
• Original Assignee: Seiko Epson Corporation (Seiko Group)
• Inventors: Inazumi, Mitsuhiro
• Primary Examiner(s): Allison, Andrae S
• Application Number:
  US12/833,250
• Publication Number:
  US 20110026762A1
• Time in Patent Office: 1,152 Days
• Field of Search: 382/100, 382139-140, 382/294, 235/456, 235/454, 235/494, 235/460, 235/470, 235/465, 235/566, 235/462.33
• US Class Current: 382/100
• CPC Class Codes: G06K 19/06037 multi-dimensional coding
• CPC Class Codes: G06K 7/1443 locating of the code in an image
• 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

A marker processing method includes: (a) binarizing a shot image; (b) labeling one or more constituents of the image detected based on the image binarized in step (a); (c) obtaining a region centroid of each of the constituents corresponding to the respective labels processed in step (b); (d) obtaining a degree of overlap of the region centroids of the constituents corresponding respectively to the labels, obtained in step (c); and (e) detecting a marker based on the degree of overlap of the region centroids obtained in step (d).

Claims

1. A marker processing method comprising:

(a) binarizing an image including a marker to generate a binarized image;

(b) labeling one or more constituents of the image based on the binarized image to generate labeled constituents;

(c) obtaining a region centroid of each of the labeled constituents;

(d) obtaining a degree of overlap of the region centroids of the labeled constituents; and

(e) detecting the marker based on the degree of overlap of the region centroids, wherein the marker is detected if the degree of overlap of the region centroids is one of equal to and larger than 3.

2. The marker processing method according to claim 1, further comprising:

(f) identifying a type of the marker detected in step (e) using at least one of the degree of overlap of the region centroids obtained in step (d), an area ratio between the labeled constituents of the marker, and a size ratio between the labeled constituents of the marker.

3. The marker processing method according to claim 1, wherein the marker includes at least three of the constituents having a common centroid.

4. A marker processing device comprising:

a binarization section that binarizes an image including a marker to generate a binarized image;

a labeling section that detects one or more constituents of the image based on the binarized image and that labels the constituents to generate labeled constituents;

a region centroid obtaining section that obtains a region centroid of each of the labeled constituents;

a region centroid multiplicity obtaining section that obtains a degree of overlap of the region centroids of the labeled constituents; and

a marker determination section that detects a marker based on the degree of overlap of the regions centroids, wherein the marker is detected if the degree of overlap of the regions centroids is one of equal to and larger than 3.