Detection of plant diseases with multi-stage, multi-scale deep learning

1. A computer system comprising:

a classification model management server computer configured, by instructions, to:

receive a new image from a user device;

apply a first digital model to a plurality of first regions within the new image for classifying each of the plurality of first regions within the new image into a class of a first set of classes corresponding to a first plurality of plant diseases, a healthy condition, or a combination of a second plurality of plant diseases;

apply a second digital model to one or more second regions within the new image for classifying each of the one or more second regions within the new image into a class of a second set of classes corresponding to the second plurality of plant diseases, the one or more second regions each corresponding to a combination of multiple first regions of the plurality of first regions, the multiple first regions each further being classified into the class corresponding to the combination of the second plurality of plant diseases; and

transmit classification data related to the class of the first set of classes and the class of the second set of classes for each of the plurality of first regions and each of the one or more second regions to the user device.

2. The computer system of claim 1 , wherein the classification model management server computer is configured, by the instructions, as part of applying the first digital model, to:

resize the new image according to a first image size to obtain a first updated image; and

extract the plurality of first regions from the first updated image using a sliding window with a predetermined first stride.

3. The computer system of claim 1 , wherein the classification model management server computer is configured, by the instructions, as part of applying the second digital model, to:

mask each of the plurality of first regions in the new image that is classified into a class corresponding to one of the first plurality of plant diseases or a healthy condition to obtain a masked image;

resize the masked image according to the second image size to obtain a second updated image; and

extract the one or more second regions from the second updated image using a sliding window with a predetermined second stride.

4. The computer system of claim 1 , wherein the classification model management server computer is configured, by the instructions, as part of applying the second digital model, to:

resize a portion of a combination of multiple first regions of the plurality of first regions to obtain the one or more second regions.

5. The computer system of claim 1 , wherein the classification model management server computer is further configured, by the instructions, to:

compute a total size of the plurality of first regions and the one or more second regions classified into each of the first set of classes and the second set of classes; and

determine a dominant class of the first set of classes and the second set of classes such that the total size of the plurality of first regions and the one or more second regions classified into the dominant class is largest, the classification data including information regarding the dominant class.

6. The computer system of claim 1 , wherein the first digital model and/or the second digital model include(s) a convolutional neural network (CNN) or a decision tree.

7. The computer system of claim 1 , wherein the first plurality of plant diseases includes Common Rust, Eyespot, Southern Rust, or Gray Leaf Spot at an early stage, and the second plurality of plant diseases includes Goss's Wilt, Northern Leaf Blight, or Gray Leaf Spot at a late stage.

8. The computer system of claim 1 , wherein the instructions include model execution instructions, and wherein the classification model management server computer is further configured, by model construction instructions, to:

obtain a first training set from at least a first photo showing a first symptom of one of the first plurality of plant diseases, a second photo showing no symptom, and a third photo showing a partial second symptom of one of the second plurality of plant diseases, the first training set including a label of the class of the first set of classes for each of a first set of areas in the first photo, the second photo, or the third photo, the first, second, and third photos corresponding to similarly-sized fields of view;

build the first digital model from the first training set;

obtain a second training set from at least a fourth photo showing the second symptom, the second training set including a label of the class of the second set of classes for each of a second set of areas in the fourth photo; and

build the second digital model from the second training set.

9. The computer system of claim 8 , wherein the classification model management server computer is configured, by the model construction instructions, as part of obtaining the first training set, to:

identify a size of a sliding window;

determine a first scaling factor;

determine a first image size based on the size of the sliding window and the first scaling factor; and

resize the first photo, the second photo, or the third photo according to the first image size to obtain a first resized photo, a second resize photo, or a third resized photo.

10. The computer system of claim 9 , wherein the first training set is obtained from a specific photo showing a third symptom of one of the first plurality of plant diseases and a fourth symptom of one of the second plurality of plant diseases, the fourth symptom overlapping with the third symptom.

11. The computer system of claim 10 , wherein the classification model management server computer is configured, by the model construction instructions, as part of obtaining the second training set, to:

determine a second scaling factor smaller than the first scaling factor;

determine a second image size based on the size of the sliding window and the second scaling factor; and

resize the fourth photo according to the second image size to obtain a fourth resized photo.

12. The computer system of claim 11 , wherein the classification management server computer is further configured, by the model construction instructions, to:

determine a first stride and a second stride smaller than the first stride;

wherein the classification management server computer is configured, by the model construction instructions, as part of obtaining the first training set, to:

extract a first set of areas from the first resized photo, the second resized photo, or the third resized photo using the sliding window with the first stride; and

wherein the classification model management server is configured, by the model construction instructions, as part of obtaining the second training set, to:

extract a second set of areas from the fourth resized photo using the sliding window with the second stride.

13. The computer system of claim 12 , wherein ones of the second set of areas overlap with other ones of the second set of areas.