公开(公告)号：US20240312193A1

公开(公告)日：2024-09-19

申请号：US18339075

申请日：2023-06-21

Applicant: Samsung Display Co., Ltd.

Inventor： Qisen Cheng ,  Shuhui Qu ,  Kaushik Balakrishnan ,  Janghwan Lee

IPC: G06V10/80 ,  G06N3/0455 ,  G06T7/00

CPC classification number: G06V10/803 ,  G06N3/0455 ,  G06T7/0004 ,  G06T2207/20081

Abstract: A method may include providing a data set including rows of data. The rows of data may include at least one row of unpaired modality including a first modality, and at least one row of paired modality may include both the first modality and a second modality. The method may further include imputing, by a modality-specific encoder, the at least one row of unpaired modality by interpolating embeddings from the second modality of the paired modality; training, in a latent space, the modality-specific encoder based on the imputation for unimodal prediction and bimodal prediction; and generating a confidence value for the unimodal prediction and the bimodal prediction.

公开(公告)号：US20230316084A1

公开(公告)日：2023-10-05

申请号：US18207005

申请日：2023-06-07

Applicant: Samsung Display Co., Ltd.

Inventor： Janghwan Lee

IPC: G06N3/088 ,  G06N3/045 ,  G06N3/047

CPC classification number: G06N3/088 ,  G06N3/045 ,  G06N3/047

Abstract: A system and method for classifying products. A processor generates first and second instances of a first classifier, and trains the instances based on an input dataset. A second classifier is trained based on the input, where the second classifier is configured to learn a representation of a latent space associated with the input. A first supplemental dataset is generated in the latent space, where the first supplemental dataset is an unlabeled dataset. A first prediction is generated for labeling the first supplemental dataset based on the first instance of the first classifier, and a second prediction is generated for labeling the first supplemental dataset based on the second instance of the first classifier. Labeling annotations are generated for the first supplemental dataset based on the first prediction and the second prediction. A third classifier is trained based on at least the input dataset and the annotated first supplemental dataset.

公开(公告)号：US20230267600A1

公开(公告)日：2023-08-24

申请号：US17728882

申请日：2022-04-25

Applicant: Samsung Display Co., Ltd.

Inventor： Shuhui Qu ,  Qisen Cheng ,  Janghwan Lee

IPC: G06T7/00 ,  G06N3/04

CPC classification number: G06T7/001 ,  G06N3/0454 ,  G06N3/0481 ,  G06T2207/20081 ,  G06T2207/20084

Abstract: A system including: a memory, an encoder, a decoder, and a processor, the processor being connected to the memory, the encoder, and the decoder. The system is configured to: receive, at the encoder, an input image, divide, by the encoder, the input image into a plurality of image patches, select, by the encoder, codes corresponding to the plurality of image patches of the input image, from a codebook including the codes. The system is further configured to determine, by the encoder, an assigned code matrix including the codes corresponding to the plurality of image patches of the input image, receive, by the decoder, the assigned code matrix from the encoder. The system is further configured to generate, by the decoder, a reconstructed image based on the assigned code matrix.

公开(公告)号：US11710045B2

公开(公告)日：2023-07-25

申请号：US16682815

申请日：2019-11-13

Applicant: Samsung Display Co., Ltd.

Inventor： Janghwan Lee

IPC: G06N3/04 ,  G06N3/08 ,  G06N3/088 ,  G06N3/045 ,  G06N3/047

CPC classification number: G06N3/088 ,  G06N3/045 ,  G06N3/047

Abstract: A system and method for classifying products. A processor generates first and second instances of a first classifier, and trains the instances based on an input dataset. A second classifier is trained based on the input, where the second classifier is configured to learn a representation of a latent space associated with the input. A first supplemental dataset is generated in the latent space, where the first supplemental dataset is an unlabeled dataset. A first prediction is generated for labeling the first supplemental dataset based on the first instance of the first classifier, and a second prediction is generated for labeling the first supplemental dataset based on the second instance of the first classifier. Labeling annotations are generated for the first supplemental dataset based on the first prediction and the second prediction. A third classifier is trained based on at least the input dataset and the annotated first supplemental dataset.

公开(公告)号：US20210319546A1

公开(公告)日：2021-10-14

申请号：US16938812

申请日：2020-07-24

Applicant: Samsung Display Co., Ltd.

Inventor： Yan Kang ,  Janghwan Lee ,  Shuhui Qu ,  Jinghua Yao ,  Sai MarapaReddy

IPC: G06T7/00 ,  G06K9/62 ,  G06N3/08 ,  G06N3/04 ,  G06N20/20

Abstract: A system for manufacturing defect classification is presented. The system includes a first neural network receiving a first data as input and generating a first output, a second neural network receiving a second data as input and generating a second output, wherein first neural network and the second neural network are trained independently from each other, and a fusion neural network receiving the first output and the second output and generating a classification. The first data and the second data do not have to be aligned. Hence, the system and method of this disclosure allows various type of data that are collected during manufacturing to be used in defect classification.

公开(公告)号：US20210319270A1

公开(公告)日：2021-10-14

申请号：US16938857

申请日：2020-07-24

Applicant: Samsung Display Co., Ltd.

Inventor： Shuhui Qu ,  Janghwan Lee ,  Yan Kang ,  Jinghua Yao ,  Sai MarapaReddy

IPC: G06K9/62 ,  G06N3/08 ,  G06N3/04

Abstract: A method and a system are presented for controlling a performance of a fusion model. The method includes obtaining a first set and a second set of candidate models for a first and second neural networks, respectively. Each of the first and second set of candidate models is pre-trained with a first source and a second source, respectively. For each possible pairing of one candidate model from the first neural network and one candidate model from the second neural network, a model distance Dm is determined. A subset of possible pairings of one first candidate model and one second candidate model is selected based on the model distance Dm between them. Using the subset of possible parings, the first neural network and the second neural network are combined to generate two branches for a fusion model neural network.

公开(公告)号：US20190258890A1

公开(公告)日：2019-08-22

申请号：US15956667

申请日：2018-04-18

Applicant: Samsung Display Co., Ltd.

Inventor： Janghwan Lee

IPC: G06K9/46 ,  G06K9/62

Abstract: A system and method for identifying line Mura defects on a display. The system is configured to generate a filtered image by preprocessing an input image of a display using at least one filter. The system then identifies line Mura candidates by converting the filtered image to a binary image, counting line components along a slope in the binary image, and marking a potential candidate location when the line components along the slope exceed a line threshold. Image patches are then generated with the candidate locations at the center of each image patch. The image patches are then classified using a machine learning classifier.

公开(公告)号：US20180183840A1

公开(公告)日：2018-06-28

申请号：US15405185

申请日：2017-01-12

Applicant: Samsung Display Co., Ltd.

Inventor： Janghwan Lee

IPC: H04L29/06 ,  H04W8/00 ,  H04W4/00 ,  H04W76/02 ,  G06F3/0488

CPC classification number: H04L65/1069 ,  H04L65/4069 ,  H04W4/20 ,  H04W4/80 ,  H04W8/005 ,  H04W76/10 ,  H04W84/12

Abstract: A system and method for screen mirroring and casting using a near field communication connection to initialize a wireless connection between a client device and a server device. The client device is initially placed in proximity of a near field communication antenna connected to the server device. This proximity triggers the establishing of a near field communication connection, through which setup parameters for a wireless connection are sent, by the server device, to the client device. The wireless connection is then established and used to send video data to the server device, which displays the corresponding video images on a display. The server device may also send user input data to the client device.

公开(公告)号：US20170091160A1

公开(公告)日：2017-03-30

申请号：US15215512

申请日：2016-07-20

Applicant: SAMSUNG DISPLAY CO. LTD.

Inventor： Janghwan Lee ,  Ning Lu

IPC: G06F17/22 ,  G06F17/21 ,  H04L29/08 ,  G06F17/27

Abstract: A virtual device for processing Web-based content to be displayed on a remote rendering device includes: a processor implemented by one or more cloud resources; and a memory, and the memory stores instructions that, when executed, cause the processor to: receive the content; detect an attribute of the remote rendering device and process the content according to the detected attribute; analyze the content to construct a render tree corresponding to the content; prepare render tree data for rendering by the remote rendering device, the render tree data corresponding to the constructed render tree; and transmit the render tree data over a communication network to the remote rendering device.

公开(公告)号：US11922301B2

公开(公告)日：2024-03-05

申请号：US16442298

申请日：2019-06-14

Applicant: Samsung Display Co., Ltd.

Inventor： Janghwan Lee

IPC: G06N3/08 ,  G06F18/21 ,  G06F18/214 ,  G06F18/2431 ,  G06N3/008 ,  G06N20/00 ,  G06N20/10 ,  G06N20/20

CPC classification number: G06N3/08 ,  G06F18/2155 ,  G06F18/217 ,  G06F18/2431 ,  G06N3/008 ,  G06N20/00 ,  G06N20/10 ,  G06N20/20

Abstract: A system and method for classification. In some embodiments, the method includes forming a first training dataset and a second training dataset from a labeled input dataset; training a first classifier with the first training dataset; training a variational auto encoder with the second training dataset, the variational auto encoder comprising an encoder and a decoder; generating a third dataset, by feeding pseudorandom vectors into the decoder; labeling the third dataset, using the first classifier, to form a third training dataset; forming a fourth training dataset based on the third dataset; and training a second classifier with the fourth training dataset.