Samsung Electronics Co., Ltd.

Hyoung Min Park

Kyoung Gu Woo

Jung Hoe Kim

Baek Hwan Cho

Hye Jin Kam

An apparatus and method of training a convolutional neural network (CNN) are provided. A method of training a CNN including a plurality of convolution layers stored in a memory involves approximating, using a processor, a convolution layer among the plurality of convolution layers using a low-rank approximation; reducing the number of output reconstruction filters of the approximated convolution layer; and modifying a structure of the CNN based on an approximation result and the reduced number of output reconstruction filters.

Convolution neural network training apparatus and method thereof

A nickname management apparatus includes a speech agent configured to recognize a speech of a user to obtain nickname information of a device, and a nickname manager configured to determine a device corresponding to the nickname information from one or more devices on a network, and register the named device based on the determination.

Nickname management method and apparatus

According to an aspect of an exemplary embodiment, an apparatus for avoiding region of interest (ROI) re-detection includes a detector configured to detect an ROI from an input medical image; a re-detection determiner configured to determine whether the detected ROI corresponds to a previously-detected ROI using pre-stored user determination information; and an ROI processor configured to perform a process for the detected ROI based on the determination.

Apparatus and method for avoiding region of interest re-detection

Disclosed are an image sampling apparatus and method. The image sampling apparatus includes a probe angular velocity detector configured to detect an angular velocity of a probe representing a change in an angle of the probe at a surface of an object, an image segmenter configured to receive the angular velocity and an image captured by the probe, and to segment the image into sub-regions based on the angular velocity, and a differential sampler configured to sample the sub-regions with a different sampling rate based on a position of a sub-region.

Growing community of inventors

Seoul, South Korea

Hyoung Min Park