Unpaired image-to-image translation using a generative adversarial network (gan)
AssigneeThe Boeing Company
InventorsNick Shadbeh Evans, Jasper Patrick Corleis, Amir Afrasiabi
Life of this patent
Estimating the term…
Abstract
An apparatus for identifying objects receives a dataset comprising an image having first real image features; trains a neural network to recognize the first real image features in the received dataset; and performs a synthetic image augmentation to generate synthetic image features corresponding to the first real image features in the received dataset using the neural network. The synthetic image augmentation allows for improved training of a computer vision function for recognizing second real image features, corresponding to the synthetic image features, in a real-world environment.
Claims20
An apparatus for identifying objects, the apparatus comprising:
- a processor configured to execute instructions stored on a memory;
- and
- the memory storing computer-readable instructions that, when executed by the processor, cause the processor to:
- receive a dataset comprising an image having first real image features,
- train a neural network to recognize the first real image features in the received dataset, and
- perform a synthetic image augmentation to generate synthetic image features corresponding to the first real image features in the received dataset using the neural network, such that the synthetic image augmentation allows for training of a computer vision function for recognizing second real image features, corresponding to the synthetic image features, in a real-world environment.
A method for identifying objects, the method comprising:
- receiving a dataset comprising an image having first real image features,
- training a neural network to recognize the first real image features in the received dataset, and
- performing a synthetic image augmentation to generate synthetic image features corresponding to the first real image features in the received dataset using the neural network, such that the synthetic image augmentation allows for improved training of a computer vision function for recognizing second real image features, corresponding to the synthetic image features, in a real-world environment.
A computer program product, comprising a computer usable medium having a computer readable program code embodied therein, the computer readable program code adapted to be executed, to implement a method to identify objects, the method comprising:
- receiving a dataset comprising an image having first real image features,
- training a neural network to recognize the first real image features in the received dataset, and
- performing a synthetic image augmentation to generate synthetic image features corresponding to the first real image features in the received dataset using the neural network, such that the synthetic image augmentation allows for improved training of a computer vision function for recognizing second real image features, corresponding to the synthetic image features, in a real-world environment.
Dependencies are inferred from the claim text.