Electronic apparatus, method for processing image and computer-readable recording medium
AssigneeSamsung Electronics Co., Ltd.
InventorBongjoe KIM
Life of this patent
Estimating the term…
Abstract
The disclosure relates to an artificial intelligence (AI) system utilizing a machine learning algorithm, and application thereof. In particular, an electronic apparatus according to the disclosure includes a memory storing a trained artificial intelligence model, and a processor configured to acquire a plurality of feature values by inputting an input image to the artificial intelligence model. The trained artificial intelligence model applies each of a plurality of filters to a plurality of feature maps extracted from the input image and includes a pooling layer for acquiring feature values for the plurality of feature maps to which each of the plurality of filters is applied.
Claims19
An electronic apparatus comprising:
- a memory storing a trained artificial intelligence model including a pooling layer having a plurality of filters;
- and
- a processor configured to use the trained artificial intelligence model to:
- obtain a plurality of feature maps from an input image, and
- identify a plurality of feature values of the input image by applying the plurality of filters of the pooling layer to the obtained plurality of feature maps of the input image.
A method comprising:
- receiving an input image;
- and
- using a trained artificial intelligence model to:
- obtain a plurality of feature maps from an input image, and
- identify a plurality of feature values of the input image by applying a plurality of filters of a pooling layer of the trained artificial intelligence model to the obtained plurality of feature maps of the input image.
A non-transitory computer-readable recording medium including a program that, when executed on at least one processor, performs a method including:
- receiving an input image;
- and
- using a trained artificial intelligence model to:
- obtain a plurality of feature maps from an input image, and
- identify a plurality of feature values of the input image by applying a plurality of filters of a pooling layer of the trained artificial intelligence model to the obtained plurality of feature maps of the input image.
Dependencies are inferred from the claim text.