Method, apparatus and program product for searching knots in wood

• US 7,778,458 B2
• Filed: 05/16/2006
• Issued: 08/17/2010
• Est. Priority Date: 05/18/2005
• Status: Active Grant

• Current Assignee: Meinan Machinery Works, Inc.
• Original Assignee: Meinan Machinery Works, Inc.
• Inventors: Hiraoka, Noriyuki
• Primary Examiner(s): Ahmed; Samir A.
• Assistant Examiner(s): Li; Ruiping
• Application Number:
  US11/383,631
• Publication Number:
  US 20060262972A1
• Time in Patent Office: 1,554 Days
• Field of Search: 382/110
• US Class Current: 382/141
• CPC Class Codes: B07C 5/14 Sorting timber or logs , e.g. tree trunks, beams, planks or the like
• CPC Class Codes: B07C 5/3422 using video scanning devices, e.g. TV-cameras
• CPC Class Codes: G01N 21/8986 Wood
• CPC Class Codes: G01N 33/46 Wood
• CPC Class Codes: G06T 2207/30161 Wood; Lumber
• CPC Class Codes: G06T 7/0004 Industrial image inspection
• CPC Class Codes: G06T 7/64 of convexity or concavity
• 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

The photographing means of the present apparatus photographs a piece of wood, while the image processing means calculates degrees of circularity from the photographed images of the piece of wood, and detects images with significant degrees of circularity as knots. In addition, the image processing means 1 clips a portion including a knot from the photographed image of the piece of wood, deems a portion clipped at a predetermined threshold among the color spaces of each pixel of the clipped portions to be a blackened portion, and determines black portions with a high proportion of a number of pixels of the blackened portion to the number of pixels of the clipped portion of the knot as dead knots.

Claims

1. A method executed by a programmed processor for searching knots in wood, the method comprising:

photographing a piece of wood by a photographing unit;

performing a first calculation comprising calculating degrees of circularity of each figure in the photographed images of the piece of wood and setting at least one figure comprising a circularity corresponding to a knot candidate;

clipping a partial image including said knot candidate from said at least one figure;

varying threshold levels of gray value for said clipped partial image such that an image is obtained at each of said threshold levels, said image including said knot candidate;

performing a second calculation, said second calculation comprising calculating a degree of circularity and stability of said knot candidate at each of said threshold levels;

identifying one of said images from said plurality of images comprising a selected threshold level, said selected threshold level corresponding to a level at which said circularity and said size stability of said knot candidate is a maximum value with respect to said circularity and said size stability values of said knot candidate in said other images;

determining a configuration of said knot candidate at said selected threshold level;

detecting said knot candidate as a knot when said degree of said circularity of said knot candidate is greater than a predetermined circularity degree at said selected threshold level.

2. The method according to claim 1, wherein:

said second calculation sets a value table to hold a value associated with each pixel of said photographed image, wherein said second calculation comprises calculating a coefficient corresponding to said degree of circularity of said figure of said knot candidate for each image of each of said threshold levels and said second calculation comprises accumulating said calculated coefficients to values of said value table associated with said pixels forming said figure; and

said determining a configuration step includes specifying specific values of said value table that exceed a predetermined value and determining, as said figure of said knot candidate, a figure generated with said pixels associated with said specific values of said value table after accumulating said coefficients in said second calculation.

3. The method according to claim 1, further comprising:

determining a portion with pixels clipped at a predetermined threshold from a color space as a blackened portion based on the pixels of the partial image; and

determining said knot candidate as a dead knot, said knot candidate having a high proportion of the number of pixels of the blackened portion to the number of pixels thereof.

4. The method according to claim 1, further comprising

performing smoothing on color shadings that are larger than knots on the photographed image of the piece of wood, and

wherein the calculating calculates degrees of circularity from the smoothed images and deems a figure with a high degree of circularity to be the knot candidate.

13. The method according to claim 3, wherein said step of determining said portion of pixels as a blackened portion includes calculating a deviation of each of said pixels of said partial images in said color space and determining said blackened portion based on a portion with pixels deviating from a predetermined threshold in said color space.

14. The method according to claim 1, further comprising the steps of:

providing a distributing means for sorting one or more pieces of wood;

sorting at least one said piece of wood based on said degree of circularity of said knot candidate with said distributing means.

5. An apparatus for searching knots in wood, comprising:

a photographing unit for photographing pieces of wood;

an image processing unit, said image processing unit being programmed for;

performing a first calculation comprising calculating degrees of circularity of each figure in the photographed images of the piece of wood and setting at least one figure comprising a circularity corresponding to a knot candidate;

clipping a partial image including said knot candidate from said at least one figure;

varying threshold levels of gray value for said clipped partial image such that an image is obtained at each of said threshold levels, said image including said knot candidate;

performing a second calculation, said second calculation comprising calculating a degree of circularity and stability of said knot candidate at each of said threshold levels;

selecting one of said images from said plurality of images, said one of said images comprising a selected threshold level, said selected threshold level corresponding to a level at which said circularity and said size stability of said knot candidate is a maximum value with respect to said circularity and said size stability values of said knot candidate in said other images;

determining a configuration of said knot candidate at said selected threshold level;

detecting said knot candidate as a knot when said degree of said circularity of said knot candidate is greater than a predetermined circularity degree at said selected threshold level.

6. The apparatus according to claim 5, wherein:

said second calculation sets a value table to hold a value associated with each pixel of said photographed image, wherein said second calculation comprises calculating a coefficient corresponding to said degree of circularity of said figure of said knot candidate for each image of each of said threshold levels and said second calculation comprises accumulating said calculated coefficients to values of said value table associated with said pixels forming said figure; and

said determining a configuration step includes specifying specific values of said value table that exceed a predetermined value and determining, as said figure of said knot candidate, a figure generated with said pixels associated with said specific values of said value table after accumulating said coefficients in said second calculation.

7. The apparatus according to claim 5, wherein the image processing unit:

determines a portion with pixels clipped at a predetermined threshold from a color space as a blackened portion based on the pixels of said partial image; and

determines, as dead knots, black portions with a high proportion of a number of pixels of the blackened portion to the number of pixels of the knot candidate.

8. The apparatus according to claim 5, further comprising

a smoothing unit for performing smoothing on color shadings that are larger than knots on the photographed images of the piece of wood and

wherein the image processing unit calculates degrees of circularity from the smoothed images and deems a figure with a high degrees of circularity to be the knot candidate.

15. The apparatus according to claim 5, further comprising:

a grading and distributing apparatus, said grading and distributing apparatus sorting at least one said piece of wood based on said degree of circularity of said knot candidate with said distributing means.

9. A non-transitory computer-readable storage medium storing a program for enabling a computer to function as an image processing apparatus comprising:

a unit programmed for;

performing a first calculation, said first calculation comprising calculating degrees of circularity of each figure in the photographed images of the piece of wood and setting at least one figure comprising a circularity corresponding to a knot candidate;

clipping a partial image including said knot candidate from said at least one figure;

varying threshold levels of gray value for said clipped partial image such that an image is obtained at each of said threshold levels, said image including said knot candidate;

performing a second calculation, said second calculation comprising calculating a degree of circularity and stability of said knot candidate at each of said threshold levels;

identifying one of said images from said plurality of images, said one of said images comprising a selected threshold level, said selected threshold level corresponding to a level at which said circularity and said size stability of said knot candidate is a maximum value with respect to said circularity and said size stability values of said knot candidate in said other images;

determining a configuration of said knot candidate at said selected threshold level;

detecting said knot candidate as a knot when said degree of said circularity of said knot candidate is greater than a predetermined circularity degree at said selected threshold level.

10. The non-transitory computer readable storage program according to claim 9, wherein:

said second calculation sets a value table to hold a value associated with each pixel of said photographed image, wherein said second calculation comprises calculating a coefficient corresponding to said degree of circularity of said figure of said knot candidate for each image of each of said threshold levels and said second calculation comprises accumulating said calculated coefficients to values of said value table associated with said pixels forming said figure; and

said determining a configuration step includes specifying specific values of said value table that exceed a predetermined value and determining, as said figure of said knot candidate, a figure generated with said pixels associated with said specific values of said value table after accumulating said coefficients in said second calculation.

11. The non-transitory computer-readable storage medium according to claim 9, wherein the unit determines a portion with pixels clipped at a predetermined threshold from a color space as a blackened portion based on the pixels of the partial image;

and determines, as dead knots, black portions with a high proportion of a number of pixels of the blackened portion to the number of pixels of the knot candidate.

12. The non-transitory computer readable storage program according to claim 9, further comprising:

a unit for performing smoothing on color shadings that are larger than knots on the photographed images of the piece of wood and

wherein the unit for calculating calculates degrees of circularity from the smoothed images and deems a figure with a high degree of circularity to be the knot candidate.

16. The non-transitory computer-readable storage medium according to claim 9, wherein at least one said piece of wood is sorted based on degree of circularity of said knot candidate.