Method and system for digital image analysis of ear traits

• US 8,073,235 B2
• Filed: 08/13/2007
• Issued: 12/06/2011
• Est. Priority Date: 08/13/2007
• Status: Active Grant

• Current Assignee: Pioneer Hi-Bred International (Corteva, Inc.)
• Original Assignee: Pioneer Hi-Bred International (Corteva, Inc.)
• Inventors: Hausmann, Neil Jonathan, Abadie, Tabare E., Cooper, Mark, Lafitte, Honor Renee, Schussler, Jeffrey R.
• Primary Examiner(s): Lu, Tom Y
• Application Number:
  US11/891,776
• Publication Number:
  US 20090046890A1
• Time in Patent Office: 1,576 Days
• Field of Search: 382/141
• US Class Current: 382/141
• CPC Class Codes: G06T 2207/30004 Biomedical image processing
• CPC Class Codes: G06T 7/0002 Inspection of images, e.g. flaw detection
• CPC Class Codes: G06T 7/0012 Biomedical image inspection

Abstract

A method of evaluating one or more kernels of an ear of maize using digital imagery includes acquiring a digital image of the one or more kernels of the ear of maize, processing the digital image to estimate at least one physical property of the one or more kernels of the ear of maize from the digital image, and evaluating the at least one kernel of maize using the estimate of the at least one physical property of the at least one kernel of maize.

Claims

1. A method for using image processing in screening maize to determine the maize more likely to exhibit stress tolerance and/or those less likely to exhibit stress tolerance, the method comprising:

acquiring images of kernels of maize;

processing the images of the kernels of maize;

extracting from the images of the kernels of maize estimates of a phenotype associated with stress tolerance for each of the kernels of maize;

relating the estimate of the phenotype from a first subset of the kernels of maize to estimates from a second subset of the kernels of maize;

determining variation between the first subset and the second subset;

selecting for kernels with stress tolerance relative to other kernels.

2. The method of claim 1 wherein the first subset consists of kernels of maize grown in a single plot.

3. The method of claim 1 wherein the second subset consists of kernels of maize grown in a single plot.

4. The method of claim 1 wherein the second subset consists of kernels of maize grown from multiple plots.

5. The method of claim 1 wherein the phenotype is number of kernels per ear.

6. The method of claim 1 wherein the phenotype is a proportion of kernels aborted.

7. The method of claim 1 wherein the phenotype is kernel size distribution within an ear.

26. The method of claim 1, further comprising incorporating the method into a breeding, a production, or an evaluation program.

8. A method for using image processing in screening maize to determine the maize more likely to exhibit stress tolerance and/or those less likely to exhibit stress tolerance, the method comprising:

acquiring images of ears of maize;

processing the images of the ears of maize;

extracting from the images of the ears of maize estimates of an ear component phenotype associated with stress tolerance for each of the ears of maize;

relating the estimate of the ear component phenotype from a first subset of the ears of maize to estimates from a second subset of the ears of maize;

determining variation between the first subset and the second subset;

selecting for ears with stress tolerance relative to other ears.

9. The method of claim 8 wherein the first subset consists of ears of maize grown in a single plot.

10. The method of claim 8 wherein the second subset consists of ears of maize grown in a single plot.

11. The method of claim 8 wherein the second subset consists of ears of maize grown from multiple plots.

12. The method of claim 8 wherein the ear component phenotype is number of kernels per ear.

13. The method of claim 8 wherein the ear component phenotype is a proportion of kernels aborted.

14. The method of claim 8 wherein the ear component phenotype is kernel size distribution within the ear.

27. The method of claim 8, further comprising incorporating the method into a breeding, a production, or an evaluation program.

15. A method of counting kernels on an ear of maize, comprising:

providing a digital image of the ear of maize;

extracting a filled kernel area from the ear of maize using a predetermined color palette;

applying a filter to the digital image to enhance the center of each kernel of the ear of maize;

counting the number of kernels on the ear of maize represented in the digital image;

providing to a user an output related to the number of kernels on the ear.

16. The method of claim 15 wherein the digital image of the ear of maize is acquired under controlled lighting conditions.

17. The method of claim 16 wherein the predetermined color palette is related to the controlled lighting conditions.

18. The method of claim 15 further comprising comparing the number of kernels to a manually counted number of physical kernels.

19. The method of claim 15 further comprising monitoring variability in number of kernels from plant to plant.

20. The method of claim 19 further comprising determining a proportion of kernels aborted.

21. The method of claim 19 further comprising determining kernel size distributions within ears.

22. The method of claim 19 further comprising determining within-plot variability.

23. The method of claim 15 further comprising picking the ear of maize.

24. The method of claim 15 further comprising shelling the ear of maize.

28. The method of claim 15, further comprising incorporating the method into a breeding, a production, or an evaluation program.

25. A system for evaluating ears of maize, comprising:

a picker adapted for picking ears of maize;

an image sensor adapted to image the ears of maize after picking to provide digital imagery of the ears of maize;

an image processing component adapted to process the digital imagery to determine physical properties of the ear of maize;

a sheller adapted for shelling the ears of maize;

a conveyor to convey the ears of maize from the picker to the sheller,

wherein the physical properties include number of kernels on each of the ears of maize, and wherein the image processing component is adapted for extracting a filled kernel area from the ear of maize using a predetermined color palette, applying a filter to the digital image to enhance a center of each kernel of the ear of maize, and counting number of kernels on the ear of maize represented in the digital image.