Patents by Inventor Chang Kyu Choi

Chang Kyu Choi has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).

  • Patent number: 10540768
    Abstract: A method of segmenting an object from an image includes receiving an input image including an object; generating an output image corresponding to the object from the input image using an image model; and extracting an object image from the output image.
    Type: Grant
    Filed: July 22, 2016
    Date of Patent: January 21, 2020
    Assignees: SAMSUNG ELECTRONICS CO., LTD., INSTITUTE OF AUTOMATION CHINESE ACADEMY OF SCIENCES
    Inventors: Byungin Yoo, Jungbae Kim, Chang Kyu Choi, Jaejoon Han, Yongzhen Huang, Liang Wang
  • Patent number: 10534901
    Abstract: Provided is a user authentication method and apparatus that obtains first environmental information indicating an environmental condition in which an input image of a user is captured, extracts a first feature vector from the input image, selects a second feature vector including second environmental information that matches the first environmental information from enrolled feature vectors in an enrollment database (DB), and authenticates the user based on the first feature vector and the second feature vector.
    Type: Grant
    Filed: March 15, 2018
    Date of Patent: January 14, 2020
    Assignee: Samsung Electronics Co., Ltd.
    Inventors: Jihye Kim, Jinwoo Son, Chang Kyu Choi, Jae-Joon Han
  • Patent number: 10528846
    Abstract: A method to analyze a facial image includes: inputting a facial image to a residual network including residual blocks that are sequentially combined and arranged in a direction from an input to an output; processing the facial image using the residual network; and acquiring an analysis map from an output of an N-th residual block among the residual blocks using a residual deconvolution network, wherein the residual network transfers the output of the N-th residual block to the residual deconvolution network, and N is a natural number that is less than a number of all of the residual blocks, and wherein the residual deconvolution network includes residual deconvolution blocks that are sequentially combined, and the residual deconvolution blocks correspond to respective residual blocks from a first residual block among the residual blocks to the N-th residual block.
    Type: Grant
    Filed: October 27, 2017
    Date of Patent: January 7, 2020
    Assignee: Samsung Electronics Co., Ltd.
    Inventors: Youngsung Kim, Byungin Yoo, Deheng Qian, Hui Zhang, Chang Kyu Choi, He Zheng, Jae-Joon Han, Jingtao Xu, Tianchu Guo
  • Publication number: 20200005146
    Abstract: A lightened neural network, method, and apparatus, and recognition method and apparatus implementing the same. A neural network includes a plurality of layers each comprising neurons and plural synapses connecting neurons included in neighboring layers. Synaptic weights with values greater than zero and less than a preset value of a variable a, which is greater than zero, may be at least partially set to zero. Synaptic weights with values greater than a preset value of a variable b, which is greater than zero, may be at least partially set to the preset value of the variable b.
    Type: Application
    Filed: September 9, 2019
    Publication date: January 2, 2020
    Applicant: Samsung Electronics Co., Ltd.
    Inventors: Changyong SON, Jinwoo SON, Byungin YOO, Chang Kyu CHOI, Jae-Joon HAN
  • Publication number: 20190370940
    Abstract: A processor-implemented method of generating feature data includes: receiving an input image; generating, based on a pixel value of the input image, at least one low-bit image having a number of bits per pixel lower than a number of bits per pixel of the input image; and generating, using at least one neural network, feature data corresponding to the input image from the at least one low-bit image.
    Type: Application
    Filed: May 8, 2019
    Publication date: December 5, 2019
    Applicant: Samsung Electronics Co., Ltd.
    Inventors: Chang Kyu CHOI, Youngjun KWAK, Seohyung LEE
  • Publication number: 20190370533
    Abstract: A three-dimensional (3D) image-based facial verification method and apparatus is provided. The facial verification method may include capturing a facial image of a 3D face of a user, determining an occluded region in the captured facial image by comparing the captured facial image and an average facial image, generating a synthetic image by synthesizing the captured facial image and the average facial image based on the occluded region, and verifying the user based on the synthetic image.
    Type: Application
    Filed: May 30, 2019
    Publication date: December 5, 2019
    Applicant: SAMSUNG ELECTRONICS CO., LTD.
    Inventors: Seungju HAN, Minsu KO, Jaejoon HAN, Chang Kyu CHOI
  • Publication number: 20190347550
    Abstract: Disclosed is a processor-implemented data processing method in a neural network. A data processing apparatus includes at least one processor, and at least one memory configured to store instructions to be executed by the processor and a neural network, wherein the processor is configured to, based on the instructions, input an input activation map into a current layer included in the neural network, output an output activation map by performing a convolution operation between the input activation map and a weight quantized with a first representation bit number of the current layer, and output a quantized activation map by quantizing the output activation map with a second representation bit number based on an activation quantization parameter.
    Type: Application
    Filed: April 30, 2019
    Publication date: November 14, 2019
    Applicant: SAMSUNG ELECTRONICS CO., LTD.
    Inventors: Sangil JUNG, Changyong SON, Seohyung LEE, Jinwoo SON, Chang Kyu CHOI
  • Patent number: 10477111
    Abstract: A display apparatus includes a sensor panel configured to sense a first incident light, which is incident to the sensor panel subsequent to passing through a display, and configured to at least partially block transmission of light through the sensor panel. The display apparatus further includes a controller configured to selectively control the display to pass the first incident light toward the sensor panel, and configured to control the display to pass light out of the display to display an image. The sensor panel includes a first sensor unit and a second sensor unit configured to sense the incident first light, and the first sensor unit and the second sensor unit include respective unit color filters having different color filters.
    Type: Grant
    Filed: January 12, 2017
    Date of Patent: November 12, 2019
    Assignee: Samsung Electronics Co., Ltd.
    Inventors: Sung Joo Suh, Chang Kyu Choi, Kwon Ju Yi, Du Sik Park
  • Publication number: 20190332851
    Abstract: A face verifying method and apparatus. The face verifying method includes detecting a face region from an input image, generating a synthesized face image by combining image information of the face region and reference image information, based on a determined masking region, extracting one or more face features from the face region and the synthesized face image, performing a verification operation with respect to the one or more face features and predetermined registration information, and indicating whether verification of the input image is successful based on a result of the performed verification operation.
    Type: Application
    Filed: July 11, 2019
    Publication date: October 31, 2019
    Applicant: Samsung Electronics Co., Ltd.
    Inventors: Seungju HAN, Minsu KO, Deoksang KIM, Chang Kyu CHOI, Jaejoon HAN
  • Patent number: 10452977
    Abstract: A lightened neural network, method, and apparatus, and recognition method and apparatus implementing the same. A neural network includes a plurality of layers each comprising neurons and plural synapses connecting neurons included in neighboring layers. Synaptic weights with values greater than zero and less than a preset value of a variable a, which is greater than zero, may be at least partially set to zero. Synaptic weights with values greater than a preset value of a variable b, which is greater than zero, may be at least partially set to the preset value of the variable b.
    Type: Grant
    Filed: July 20, 2017
    Date of Patent: October 22, 2019
    Assignee: Samsung Electronics Co., Ltd.
    Inventors: Changyong Son, Jinwoo Son, Byungin Yoo, Chang Kyu Choi, Jae-Joon Han
  • Patent number: 10452976
    Abstract: A neural network recognition method includes obtaining a first neural network that includes layers and a second neural network that includes a layer connected to the first neural network, actuating a processor to compute a first feature map from input data based on a layer of the first neural network, compute a second feature map from the input data based on the layer connected to the first neural network in the second neural network, and generate a recognition result based on the first neural network from an intermediate feature map computed by applying an element-wise operation to the first feature map and the second feature map.
    Type: Grant
    Filed: March 20, 2017
    Date of Patent: October 22, 2019
    Assignee: Samsung Electronics Co., Ltd.
    Inventors: Byungin Yoo, Youngsung Kim, Youngjun Kwak, Chang Kyu Choi
  • Patent number: 10445546
    Abstract: An authentication method and corresponding apparatus includes obtaining iris images, and constituting an enroll set including iris codes and mask codes corresponding to the iris images. The authentication method and corresponding apparatus also include generating a synthesized code including a synthesized iris code and a synthesized mask code based on correlations between the iris codes included in the enroll set in block units.
    Type: Grant
    Filed: August 10, 2017
    Date of Patent: October 15, 2019
    Assignee: Samsung Electronics Co., Ltd.
    Inventors: Jihye Kim, Sungjoo Suh, Hyunjeong Lee, Chang Kyu Choi
  • Publication number: 20190294907
    Abstract: At least some example embodiments disclose a device and a method for generating a synthetic image and a different-angled image and eliminating noise. The method may include receiving input images, extracting feature values corresponding to the input images using an image learning model, the image learning model permitting an input and an output to be identical and generating a synthetic image based on the feature values corresponding to the input images using the image learning model.
    Type: Application
    Filed: June 11, 2019
    Publication date: September 26, 2019
    Applicants: Samsung Electronics Co., Ltd., Korea Advanced Institute of Science and Technology
    Inventors: Byungin YOO, Jun Ho YIM, Jun Mo KIM, Hee Chul JUNG, Chang Kyu CHOI, Jaejoon HAN
  • Publication number: 20190294241
    Abstract: A method and apparatus for a user interface using a gaze interaction is disclosed. The method for the user interface using the gaze interaction may include obtaining an image including eyes of a user, estimating a gaze position of the user, using the image including the eyes of the user, and determining whether to activate a gaze adjustment function for controlling a device by a gaze of the user, based on the gaze position of the user with respect to at least one toggle area on a display.
    Type: Application
    Filed: June 12, 2019
    Publication date: September 26, 2019
    Applicant: Samsung Electronics Co., Ltd.
    Inventors: Chang Kyu CHOI, Sung Joo SUH, Joon Ah PARK, Du Sik PARK
  • Publication number: 20190279052
    Abstract: A method of recognizing a feature of an image may include receiving an input image including an object; extracting first feature information using a first layer of a neural network, the first feature information indicating a first feature corresponding to the input image among a plurality of first features; extracting second feature information using a second layer of the neural network, the second feature information indicating a second feature among a plurality of second features, the indicated second feature corresponding to the first feature information; and recognizing an element corresponding to the object based on the first feature information and the second feature information.
    Type: Application
    Filed: May 30, 2019
    Publication date: September 12, 2019
    Applicant: Samsung Electronics Co., Ltd.
    Inventors: Seungju HAN, Sungjoo Suh, Jaejoon Han, Chang Kyu Choi
  • Patent number: 10395112
    Abstract: A device and method of recognizing an iris is provided. An iris recognition device may determine a threshold brightness using a histogram of a reference area from an iris image and exclude a target pixel from iris recognition in a candidate area based on the determined threshold brightness.
    Type: Grant
    Filed: August 9, 2017
    Date of Patent: August 27, 2019
    Assignee: Samsung Electronics Co., Ltd.
    Inventors: Hyunjeong Lee, Jihye Kim, Sungjoo Suh, Chang Kyu Choi
  • Patent number: 10395098
    Abstract: A method of converting a vector corresponding to an input image includes receiving input vector data associated with an input image including an object; and converting the received input vector data into feature data based on a projection matrix having a fixed rank, wherein a first dimension of the input vector data is higher than a second dimension of the feature data.
    Type: Grant
    Filed: September 19, 2016
    Date of Patent: August 27, 2019
    Assignees: SAMSUNG ELECTRONICS CO., LTD., NORTHEASTERN UNIVERSITY
    Inventors: Wonjun Hwang, Sungjoo Suh, Jaejoon Han, Chang Kyu Choi, Yun Fu, Zhengming Ding, Ming Shao
  • Patent number: 10387716
    Abstract: A method and apparatus for recognizing a facial expression is provided. The method of recognizing the facial expression includes extracting a feature from an input image, extracting a feature from a reference image, and recognizing a user facial expression based on a difference between the feature of the input image and the feature of the reference image.
    Type: Grant
    Filed: March 23, 2017
    Date of Patent: August 20, 2019
    Assignee: Samsung Electronics Co., Ltd.
    Inventors: Youngsung Kim, Byungin Yoo, Youngjun Kwak, Chang Kyu Choi
  • Patent number: 10387714
    Abstract: A face verifying method and apparatus. The face verifying method includes detecting a face region from an input image, generating a synthesized face image by combining image information of the face region and reference image information, based on a determined masking region, extracting one or more face features from the face region and the synthesized face image, performing a verification operation with respect to the one or more face features and predetermined registration information, and indicating whether verification of the input image is successful based on a result of the performed verification operation.
    Type: Grant
    Filed: February 5, 2018
    Date of Patent: August 20, 2019
    Assignee: Samsung Electronics Co., Ltd.
    Inventors: Seungju Han, Minsu Ko, Deoksang Kim, Chang Kyu Choi, Jaejoon Han
  • Publication number: 20190251436
    Abstract: A processing method using a neural network includes generating output maps of a current layer of the neural network by performing a convolution operation between input maps of the current layer and weight kernels of the current layer, determining a lightweight format for the output maps of the current layer based on a distribution of at least a portion of activation data being processed in the neural network, and lightening activation data corresponding to the output maps of the current layer to have a low bit width based on the determined lightweight format.
    Type: Application
    Filed: February 12, 2019
    Publication date: August 15, 2019
    Applicant: SAMSUNG ELECTRONICS CO., LTD.
    Inventors: ChangYong SON, Jinwoo SON, Sangil JUNG, Chang Kyu CHOI, Jae-Joon HAN