外文摘要：NOVELTY - The method (200) involves determining whether an image segment of a crop image within first region satisfies leaf creasing criteria based on edges that are located within the image segment by a processor. Determination is made whether the image segment satisfies color criteria symptomatic of discoloration caused by a potato virus by the processor. Determination is made whether the image segment displays symptoms of potato virus based on whether the image segment satisfies the leaf creasing criteria and the color criteria by the processor.
 
USE - Method for detecting a potato virus in a crop image for infected plants in large crop fields.
 
ADVANTAGE - The method enables preventing spreading of the potato virus and reducing crop yield loss due to the potato virus. The method enables testing enough samples to reliably detect the potato virus across whole plantation. The method enables allowing an entire crop field to be analyzed for the potato virus on a regular basis.
 
主权项：CLAIMS:
1. A method of detecting a potato virus in a crop image depicting at least one potato plant, the method comprising: storing the crop image in a memory; identifying, by a processor, a first region of the crop image, the first region depicting potato plant leaves, wherein the first region is exclusive of a second region of the crop image, the second region depicting non-leaf imagery; identifying, by the processor, a plurality of edges within the first region; determining, by the processor, whether an image segment of the crop image within the first region satisfies one or more leaf creasing criteria based on the edges that are located within the image segment, wherein the leaf creasing criteria are symptomatic of leaf creasing caused by the virus; determining, by the processor, whether the image segment satisfies one or more color criteria symptomatic of discoloration caused by the virus; and determining, by the processor, whether the segment displays symptoms of potato virus based on whether the image segment satisfies one or more of the leaf creasing criteria and the color criteria.
2. The method of claim 1 , further comprising: determining, by the processor, whether the crop image contains potato virus based on a quantum of image segments within the crop image that are identified as displaying symptoms of potato virus.
3. The method of any one of claims 1-2, wherein: the one or more leaf creasing criteria include a threshold minimum quantum of edges within the image segment.
4. The method of any one of claims 1 -3, wherein: the one or more leaf creasing criteria include one or more line criteria, and determining whether the image segment satisfies the line criteria comprises identifying lines within the segment defined by the edges. 5. The method of claim 4, wherein: the one or more line criteria include a threshold minimum quantum of lines.
6. The method of any one of claims 1-5, wherein: the one or more leaf creasing criteria include one or more contour criteria, and determining whether the image segment satisfies the contour criteria comprises identifying contours within the image segment defined by the edges.
7. The method of claim 6, wherein: the one or more contour criteria include whether every contour within the segment has an area not exceeding a threshold maximum area. 8. The method of any one of claims 1 -7, wherein: the one or more color criteria include one or more value ranges of Euclidian distances in a color cone between two average color channel values.
9. The method of any one of claims 1-8, wherein: identifying the first region comprises creating a first mask based on a magenta channel of the crop image or of an image generated from the crop image.
10. The method of claim 9, wherein: identifying the first region further comprises creating a second mask based on one or more predetermined threshold color channel value ranges.
11 . A computer-readable medium comprising instructions executable by a processor, wherein the instructions when executed configure the processor to: store the crop image in a memory; identify a first region of the crop image, the first region depicting potato plant leaves, wherein the first region is exclusive of a second region of the crop image, the second region depicting non-leaf imagery; identify a plurality of edges within the first region; determine whether an image segment of the crop image within the first region satisfies one or more leaf creasing criteria based on the edges that are located within the image segment, wherein the leaf creasing criteria are symptomatic of leaf creasing caused by a potato virus; determine whether the image segment satisfies one or more color criteria symptomatic of discoloration caused by the virus; and determine whether the segment displays symptoms of potato virus based on whether the image segment satisfies one or more of the leaf creasing criteria and the color criteria. 12. The computer-readable medium of claim 1 1 , wherein the instructions when executed further configure the processor to: determine whether the crop image contains potato virus based on a quantum of image segments within the crop image that are identified as displaying symptoms of potato virus. 13. The computer-readable medium of any one of claims 11-12, wherein: the one or more leaf creasing criteria include a threshold minimum quantum of edges within the image segment.
14. The computer-readable medium of any one of claims 11-13, wherein: the one or more leaf creasing criteria include one or more line criteria, and determining whether the image segment satisfies the line criteria comprises identifying lines within the segment defined by the edges.
15. The computer-readable medium of claim 14, wherein: the one or more line criteria include a threshold minimum quantum of lines.
16. The computer-readable medium of any one of claims 1 1-15, wherein: the one or more leaf creasing criteria include one or more contour criteria, and determining whether the image segment satisfies the contour criteria comprises identifying contours within the image segment defined by the edges.
17. The computer-readable medium of claim 16, wherein: the one or more contour criteria include whether every contour within the segment has an area not exceeding a threshold maximum area.
18. The computer-readable medium of any one of claims 11-17, wherein: the one or more color criteria include one or more value ranges of Euclidian distances in a color cone between two average color channel values.
19. The computer-readable medium of any one of claims 1 -18, wherein: identifying the first region comprises creating a first mask based on a magenta channel of the crop image or of an image generated from the crop image.
20. The computer-readable medium of claim 19, wherein: identifying the first region further comprises creating a second mask based on one or more predetermined threshold color channel value ranges.
21. A system for detecting potato virus in a crop image containing potato plants, the system comprising: a memory storing computer readable instructions and the crop image; and a processor configured to execute the computer readable instructions, the computer readable instructions configuring the processor to: identify a first region of the crop image, the first region depicting potato plant leaves, wherein the first region is exclusive of a second region of the crop image, the second region depicting non-leaf imagery; identify a plurality of edges within the first region; determine whether an image segment of the crop image within the first region satisfies one or more leaf creasing criteria based on the edges that are located within the image segment, wherein the leaf creasing criteria are symptomatic of leaf creasing caused by the virus; determine whether the image segment satisfies one or more color criteria symptomatic of discoloration caused by the virus; and determine whether the segment displays symptoms of potato virus based on whether the image segment satisfies one or more of the leaf creasing criteria and the color criteria.
22. The system of claim 21 , wherein the computer readable instructions further configure the processor to: determine whether the crop image contains potato virus based on a quantum of image segments within the crop image that are identified as displaying symptoms of potato virus.
23. The system of any one of claims 21-22, wherein: the one or more leaf creasing criteria include a threshold minimum quantum of edges within the image segment.
24. The system of any one of claims 21 -23, wherein: the one or more leaf creasing criteria include one or more line criteria, and determining whether the image segment satisfies the line criteria comprises identifying lines within the segment defined by the edges.
25. The system of claim 24, wherein: the one or more line criteria include a threshold minimum quantum of lines.
26. The system of any one of claims 21-25, wherein: the one or more leaf creasing criteria include one or more contour criteria, and determining whether the image segment satisfies the contour criteria comprises identifying contours within the image segment defined by the edges.
27. The system of claim 26, wherein: the one or more contour criteria include whether every contour within the segment has an area not exceeding a threshold maximum area.
28. The system of any one of claims 21-27, wherein: the one or more color criteria include one or more value ranges of Euclidian distances in a color cone between two average color channel values.
29. The system of any one of claim 21-28, wherein: identifying the first region comprises creating a first mask based on a magenta channel of the crop image or of an image generated from the crop image.
30. The system of claim 29, wherein: identifying the first region further comprises creating a second mask based on one or more predetermined threshold color channel value ranges.
 
申请号：WO2018068143-A1
专利号：WO2018068143-A1
公开/公告号：WO2018068143-A1
申请日：2017-10-12
公开/公告日：2018-04-19
申请/专利权人：MCCAIN FOODS LTD; RESSON AEROSPACE CORP
发明/设计人：BEHL, R;ROSS, W
分类号：A01C-001/00; A01G-013/00; G06T-007/12; G06T-007/13; G06T-007/90
点击下载：基于大田作物图像的马铃薯病毒检测方法