CPC G06V 10/776 (2022.01) [G06V 10/24 (2022.01); G06V 10/82 (2022.01)] | 24 Claims |
1. A control method of an image signal processor for an artificial neural network, the control method comprising:
acquiring an image;
generating image characteristic data corresponding to the image; and
determining an image correction parameter for improving an inference accuracy of an artificial neural network model based on the image characteristic data and an inference accuracy profile of at least one artificial neural network model,
wherein the inference accuracy profile is determined based on a plurality of image datasets, the plurality of image datasets being step-by-step modulated with respect to the image characteristic data.
|