Back to results
US 2020/0090008 A1Published application
Image processing apparatus and method based on deep learning and neural network learning
AssigneeSamsung Electronics Co., Ltd.
InventorsHyun Jin CHOI, Chang Hyun KIM, Eun Soo SHIM, Dong Hwa LEE, Ki Hwan CHOI
Life of this patent
Estimating the term…
Abstract
Apparatuses and methods for image processing are provided. The image processing apparatus performs area classification and object detection in an image, and includes a feature map generator configured to generate the feature map of the input image using the neural network, and an image processor configured to classify the areas and to detect the objects in the image using the generated feature map.
Claims18
An apparatus for image processing, the apparatus comprising:
- one or more processors configured to:
- generate a feature map for an image using a trained machine learning model;
- generate pixel label information for the image by segmenting the generated feature map;
- and
- classify classes of the image using the feature map and the pixel label information.
2 more elements
A processor-implemented method, the method comprising:
- generating a feature map for an image using a trained machine learning model;
- generating pixel label information for the image by segmenting the generated feature map;
- and
- classifying classes of the image using the feature map and the pixel label information.
1 more element
Dependencies are inferred from the claim text.