Image processing method
AssigneeCroda International PLC
InventorAlexander Vyacheslavovich Semenov
Life of this patent
Estimating the term…
Abstract
A method for processing images of seeds, the method comprising: inputting a seed image comprising at least a portion of a seed to a trained neural network to generate a value associated with the coverage of a coating on the seed; the trained neural network having been trained to generate a value associated with the coverage of coating on the seed using a plurality of training images each comprising at least a portion of a training seed, and wherein each training image is labelled with a value associated with the coverage of a coating on the training seed.
Claims15
A method for processing images of seeds, the method comprising:
- inputting a seed image comprising at least a portion of a seed to a trained neural network to generate a value associated with a quality or a non-binary degree of coverage of a coating on the seed,
- the trained neural network having been trained to generate the value associated with the quality or the non-binary degree of the coverage of the coating on the seed using a plurality of training images each comprising at least a portion of a training seed, and wherein each training image is labelled with a value associated with a quality or a non-binary degree of a coverage of a coating on the training seed, wherein
- a plurality of seed images generated from a same image or taken from a same sample are input to the trained neural network to generate a plurality of values associated with qualities or non-binary degrees of the coverage of coatings corresponding to the plurality of seed images, and an average of the plurality of values is taken.
A method for processing images of seeds, the method comprising:
- inputting a seed image comprising at least a portion of a seed to a trained neural network to generate a value associated with a quality or a non-binary degree of coverage of a coating on the seed,
- the trained neural network having been trained to generate the value associated with the quality or the non-binary degree of the coverage of the coating on the seed using a plurality of training images each comprising at least a portion of a training seed, and wherein each training image is labelled with a value associated with a quality or a non-binary degree of a coverage of a coating on the training seed, wherein
- the trained neural network is trained using first training images of training seeds comprising a coating of a first colour, and using second training images of training seeds comprising coatings of a second colour.
Dependencies are inferred from the claim text.