公开(公告)号：US11887348B2

公开(公告)日：2024-01-30

申请号：US17341469

申请日：2021-06-08

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Jiwon Baek ,  Seong-Jin Park ,  Seungju Han ,  Insoo Kim ,  Jaejoon Han

IPC: G06V40/16 ,  G06V10/24 ,  G06T7/73 ,  G06N3/08 ,  G06F18/214

CPC classification number: G06V10/242 ,  G06F18/214 ,  G06N3/08 ,  G06T7/73 ,  G06V40/171 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/30201

Abstract: A processor-implemented image processing method and apparatus are provided. The image processing method includes receiving an input image and rotation information associated with the input image, generating a feature vector of the input image based on pose information corresponding to the input image, generating an assistant feature vector which represents a target component according to a pose corresponding to the rotation information, based on the feature vector, the pose information, and the rotation information, and generating a target image which has the pose corresponding to the rotation information based on the feature vector and the assistant feature vector.

公开(公告)号：US11967124B2

公开(公告)日：2024-04-23

申请号：US17322976

申请日：2021-05-18

Applicant: SAMSUNG ELECTRONICS CO., LTD. ,  SNU R&DB FOUNDATION

Inventor： Seong-Jin Park ,  Hyun Oh Song ,  Gaon An ,  Seungju Han

IPC: G06K9/00 ,  G06F18/21 ,  G06F18/214 ,  G06F18/24 ,  G06N3/094 ,  G06V10/30 ,  G06V10/764 ,  G06V10/774 ,  G06V10/82

CPC classification number: G06V10/30 ,  G06F18/214 ,  G06F18/217 ,  G06F18/24 ,  G06N3/094 ,  G06V10/764 ,  G06V10/774 ,  G06V10/82

Abstract: A method and apparatus for classification using a neural network. A classification apparatus includes at least one processor and a memory. The memory is configured to store a classifier and a preprocessor including a defensive noise generator. The at least one processor generates defensive noise from an input image through the defensive noise generator in the preprocessor, generates a combined image by combining the input image and the defensive noise, and outputs a classification result by inputting the combined image to the classifier.

公开(公告)号：US12039449B2

公开(公告)日：2024-07-16

申请号：US17119381

申请日：2020-12-11

Applicant: SAMSUNG ELECTRONICS CO., LTD. ,  Korea Advanced Institute of Science and Technology

Inventor： Seong-Jin Park ,  Sung Ju Hwang ,  Seungju Han ,  Insoo Kim ,  Jiwon Baek ,  Jaejoon Han

IPC: G06N3/08 ,  G06F17/18 ,  G06F18/10 ,  G06F18/213 ,  G06F18/2415 ,  G06F18/2431 ,  G06N3/082 ,  G06V10/44 ,  G06V10/764 ,  G06V10/774 ,  G06V40/16

CPC classification number: G06N3/082 ,  G06F17/18 ,  G06F18/10 ,  G06F18/213 ,  G06F18/2415 ,  G06F18/2431 ,  G06N3/08 ,  G06V10/454 ,  G06V10/764 ,  G06V10/774 ,  G06V40/168 ,  G06V40/174

Abstract: A processor-implemented neural network method includes: extracting, by a feature extractor of a neural network, a plurality of training feature vectors corresponding to a plurality of training class data of each of a plurality of classes including a first class and a second class; determining, by a feature sample generator of the neural network, an additional feature vector of the second class based on a mean vector and a variation vector of the plurality of training feature vectors of each of the first class and the second class; and training a class vector of the second class included in a classifier of the neural network based on the additional feature vector and the plurality of training feature vectors of the second class.

公开(公告)号：US11810397B2

公开(公告)日：2023-11-07

申请号：US17208048

申请日：2021-03-22

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Jiwon Baek ,  Seong-Jin Park ,  Seungju Han ,  Insoo Kim ,  Jaejoon Han

IPC: G06V40/16 ,  G06T7/73 ,  G06V10/75 ,  G06N3/04 ,  G06N3/08 ,  G06T3/40 ,  G06T3/60 ,  G06T9/00 ,  G06F18/214

CPC classification number: G06V40/172 ,  G06F18/214 ,  G06N3/04 ,  G06N3/08 ,  G06T3/40 ,  G06T3/60 ,  G06T7/73 ,  G06T9/002 ,  G06V10/751 ,  G06V40/171 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/30201

Abstract: A processor-implemented facial image generating method includes: determining a first feature vector associated with a pose and a second feature vector associated with an identity by encoding an input image including a face; determining a flipped first feature vector by flipping the first feature vector with respect to an axis in a corresponding space; determining an assistant feature vector based on the flipped first feature vector and rotation information corresponding to the input image; determining a final feature vector based on the first feature vector and the assistant feature vector; and generating an output image including a rotated face by decoding the final feature vector and the second feature vector based on the rotation information.

公开(公告)号：US11636577B2

公开(公告)日：2023-04-25

申请号：US16867749

申请日：2020-05-06

Applicant: Samsung Electronics Co., Ltd.

Inventor： Seong-Jin Park ,  Jiwon Baek ,  Seungju Han ,  Minsu Ko ,  Solae Lee ,  Hana Lee

IPC: G06K9/00 ,  G06T5/00 ,  G06T7/33 ,  G06F3/01 ,  G06T7/60 ,  G06V40/16 ,  G06V40/40

Abstract: A processor-implemented method with blur estimation includes: acquiring size information of an input image; resizing the input image to generate a target image of a preset size; estimating a blur of the target image; and estimating a blur of the input image based on the size information of the input image.

公开(公告)号：US11341365B2

公开(公告)日：2022-05-24

申请号：US16913205

申请日：2020-06-26

Applicant: Samsung Electronics Co., Ltd.

Inventor： Seong-Jin Park ,  Insoo Kim ,  Seungju Han ,  Jiwon Baek ,  Ju Hwan Song ,  Jaejoon Han

IPC: G06K9/62 ,  G06N3/04 ,  G06N3/08

Abstract: A processor-implemented neural network method includes: determining, using a neural network, a feature vector based on a training image of a first class among a plurality of classes; determining, using the neural network, plural feature angles between the feature vector and class vectors of other classes among the plurality of classes; determining a margin based on a class angle between a first class vector of the first class and a second class vector of a second class, among the class vectors, and a feature angle between the feature vector and the first class vector; determining a loss value using a loss function including an angle with the margin applied to the feature angle and the plural feature angles; and training the neural network by updating, based on the loss value, either one or both of one or more parameters of the neural network and one or more of the class vectors.