Seed analysis
A method of analyzing seeds including acquiring, using an X-ray machine, X-ray images of the seeds. Analyzing the X-ray images to determine a parameter of each of the seeds. Comparing a parameter determined from analyzing the X-ray image of one seed to a parameter determined from analyzing the X-ray image of another seed. Arranging the seeds relative to each other based on the seed parameters.
1. A method of analyzing seeds, the method comprising:
acquiring, using an X-ray machine, X-ray images of the seeds;
analyzing the X-ray images to determine a parameter of each of the seeds;
comparing a parameter determined from analyzing the X-ray image of one seed to a parameter determined from analyzing the X-ray image of another seed; and
arranging the seeds relative to each other based on the seed parameters;
wherein analyzing the X-ray images comprises determining, using a controller, a numerical X-ray absorption value of the seeds from the acquired X-ray images to quantify a degree of damage of the seeds, the X-ray absorption value being selectable from at least three different values.
2. The method of claim 1 , wherein analyzing the X-ray images comprises analyzing the X-ray images using a machine learning program on a controller to determine the parameters of each of the seeds.
3. The method of claim 1 , further comprising treating the seeds with a contrast agent.
4. The method of claim 1 , wherein arranging the seeds comprises arranging, using the controller, each of the seeds based on the X-ray absorption value of the seeds.
5. The method of claim 3 , wherein the X-ray images are acquired after the seeds are treated with the contrast agent.
6. The method of claim 5 , further comprising acquiring, using the X-ray machine, X-ray images of the seeds prior to treating the seeds with the contrast agent.
7. The method of claim 1 , further comprising weighing the seeds.
8. The method of claim 1 , further comprising placing the seeds in a container of water to remove dirt and debris from the seeds.
9. The method of claim 3 , further comprising filtering the seeds after the seeds are treated with the contrast agent.
10. The method of claim 9 , further comprising placing the filtered seeds in an oven to dry the seeds.
11. The method of claim 3 , wherein the seeds are treated with the contrast agent during a seed production process, the method further comprising using the determined parameters to remove damaged seeds from the seed production process.
12. The method of claim 1 , wherein acquiring X-ray images of the seeds comprises acquiring the X-ray images with a continuous-flow X-ray imaging and sorting system, the method further comprising automatically sorting the seeds based on the determined parameter for each seed using the continuous-flow X-ray imaging and sorting system.
13. A method of analyzing seeds, the method comprising:
acquiring, using an X-ray machine, X-ray images of the seeds;
analyzing the X-ray images to determine a parameter of each of the seeds; and
categorizing each seed into one of at least two categories based on the parameters determined from analyzing the X-ray images of the seeds;
wherein analyzing the X-ray images comprises determining, using a controller, a numerical X-ray absorption value of the seeds from the acquired X-ray images to quantify a degree of damage of the seeds, the X-ray absorption value being selectable from at least three different values.
14. The method of claim 13 , wherein analyzing the X-ray images comprises analyzing the X-ray images using a machine learning program on a controller to determine the parameters of each of the seeds.
15. The method of claim 14 , wherein the steps of acquiring the X-ray images, analyzing the X-ray images, and categorizing each seed is done in a training routine to train the machine learning program to learn classification rules to determine the parameters of the seeds.
16. The method of claim 15 , further comprising acquiring, using an X-ray machine, X-ray images of a different set of seeds, analyzing the X-ray images of the different set of seeds to determine a parameter of each of the seeds in the different set of seeds based on the classification rules learned in the training routine, and categorizing each seed in the different set of seeds into one of at least two categories based on the parameters determined from analyzing the X-ray images of the different set of seeds.
17. The method of claim 16 , wherein the different set of seeds is obtained from a sample of seeds taken from a seed production process.
18. The method of claim 13 , further comprising arranging, using the controller, each of the seeds relative to each other based on the X-ray absorption value of the seeds.
19. The method of claim 1 , wherein the numerical X-ray absorption value is a percentage value on a scale from 0% to 100%.
20. The method of claim 11 , wherein the seeds are treated with contrast agent after acid delinting and before seed drying.