Patents by Inventor Seok-bong YOO
Seok-bong YOO 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: 11727533Abstract: A method for generating a super resolution image may comprise up-scaling an input low resolution image; determining a directivity for each patch included in the up-scaled image; selecting an orientation-specified neural network or an orientation-non-specified neural network according to the directivity of the patch; applying the selected neural network to the patch; and obtaining a super resolution image by combining one or more patches output from the orientation-specified neural network and the orientation-non-specified neural network.Type: GrantFiled: August 12, 2020Date of Patent: August 15, 2023Assignee: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTEInventors: Seok Bong Yoo, Mi Kyong Han
-
Patent number: 11532075Abstract: A display apparatus is provided. The display apparatus includes an input interface, a first storage, a display, and a processor. Pixel values corresponding to a predetermined number of lines in an image input through the input interface are stored in the first storage. The processor acquires a first patch of a predetermined size by sampling a number of pixel values located in an outer region of a matrix centering about a specific pixel value from among the pixel values stored in the first storage, acquires a high-frequency component for the specific pixel value based on the acquired first patch, and processes the input image based on the high-frequency component. The display displays the processed image.Type: GrantFiled: June 17, 2021Date of Patent: December 20, 2022Assignee: SAMSUNG ELECTRONICS CO., LTD.Inventors: Hyung-jun Lim, Seok-bong Yoo, Tae-gyoung Ahn, Young-su Moon, Seong-hoon Choi
-
Patent number: 11430090Abstract: A method for removing compressed Poisson noises in an image, based on deep neural networks, may comprise generating a plurality of block-aggregation images by performing block transform on low-frequency components of an input image; obtaining a plurality of restored block-aggregation images by inputting the plurality of block-aggregation images into a first deep neural network; generating a low-band output image from which noises for the low-frequency components are removed by performing inverse block transform on the plurality of restored block-aggregation images; and generating an output image from which compressed Poisson noises are removed by adding the low-band output image to a high-band output image from which noises for high-frequency components of the input image are removed.Type: GrantFiled: August 6, 2020Date of Patent: August 30, 2022Assignee: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTEInventors: Seok Bong Yoo, Mi Kyong Han
-
Patent number: 11393427Abstract: An image processing apparatus includes: a signal receiver configured to receive an input image; an image processor configured to process the input image and generate an output image; a storage configured to store a first patch corresponding to a first pixel of the input image; and a controller configured to control the image processor to generate the output image by applying the first patch stored in the storage to the first pixel.Type: GrantFiled: April 13, 2020Date of Patent: July 19, 2022Assignee: SAMSUNG ELECTRONICS CO., LTD.Inventors: Seok-bong Yoo, Hyung-jun Lim, Gi-yeong Gim, Young-su Moon, Tae-gyoung Ahn
-
Publication number: 20210312598Abstract: A display apparatus is provided. The display apparatus includes an input interface, a first storage, a display, and a processor. Pixel values corresponding to a predetermined number of lines in an image input through the input interface are stored in the first storage. The processor acquires a first patch of a predetermined size by sampling a number of pixel values located in an outer region of a matrix centering about a specific pixel value from among the pixel values stored in the first storage, acquires a high-frequency component for the specific pixel value based on the acquired first patch, and processes the input image based on the high-frequency component. The display displays the processed image.Type: ApplicationFiled: June 17, 2021Publication date: October 7, 2021Applicant: SAMSUNG ELECTRONICS CO., LTD.Inventors: Hyung-jun LIM, Seok-bong YOO, Tae-gyoung AHN, Young-su MOON, Seong-hoon CHOI
-
Patent number: 11062430Abstract: A display apparatus is provided. The display apparatus includes an input interface, a first storage, a display, and a processor. Pixel values corresponding to a predetermined number of lines in an image input through the input interface are stored in the first storage,. The processor acquires a first patch of a predetermined size by sampling a number of pixel values located in an outer region of a matrix centering about a specific pixel value from among the pixel values stored in the first storage, acquires a high-frequency component for the specific pixel value based on the acquired first patch, and processes the input image based on the high-frequency component. The display displays the processed image.Type: GrantFiled: December 3, 2019Date of Patent: July 13, 2021Assignee: SAMSUNG ELECTRONICS CO., LTD.Inventors: Hyung-jun Lim, Seok-bong Yoo, Tae-gyoung Ahn, Young-su Moon, Seong-hoon Choi
-
Publication number: 20210049741Abstract: A method for generating a super resolution image may comprise up-scaling an input low resolution image; determining a directivity for each patch included in the up-scaled image; selecting an orientation-specified neural network or an orientation-non-specified neural network according to the directivity of the patch; applying the selected neural network to the patch; and obtaining a super resolution image by combining one or more patches output from the orientation-specified neural network and the orientation-non-specified neural network.Type: ApplicationFiled: August 12, 2020Publication date: February 18, 2021Applicant: Electronics and Telecommunications Research InstituteInventors: Seok Bong YOO, Mi Kyong HAN
-
Publication number: 20210042887Abstract: A method for removing compressed Poisson noises in an image, based on deep neural networks, may comprise generating a plurality of block-aggregation images by performing block transform on low-frequency components of an input image; obtaining a plurality of restored block-aggregation images by inputting the plurality of block-aggregation images into a first deep neural network; generating a low-band output image from which noises for the low-frequency components are removed by performing inverse block transform on the plurality of restored block-aggregation images; and generating an output image from which compressed Poisson noises are removed by adding the low-band output image to a high-band output image from which noises for high-frequency components of the input image are removed.Type: ApplicationFiled: August 6, 2020Publication date: February 11, 2021Applicant: Electronics and Telecommunications Research InstituteInventors: Seok Bong YOO, Mi Kyong HAN
-
Patent number: 10846830Abstract: Disclosed is a display apparatus including: a signal receiver configured to receive an image signal; a display configured to display an image; a processor configured to: calculate a change degree and a change direction of pixel value differences between at least one first pixel and two or more second pixels of an image, and change a pixel value of the first pixel based on the pixel value difference which is relatively small among the pixel value differences obtained by the calculated change degree and the calculated change direction. According to this, it is possible to enhance the image details without generating or and increasing of the noises.Type: GrantFiled: May 18, 2018Date of Patent: November 24, 2020Assignee: SAMSUNG ELECTRONICS CO., LTD.Inventors: Hyung-jun Lim, Seok-bong Yoo, Tae-gyoung Ahn, Young-su Moon, Seong-hoon Choi
-
Publication number: 20200243040Abstract: An image processing apparatus includes: a signal receiver configured to receive an input image; an image processor configured to process the input image and generate an output image; a storage configured to store a first patch corresponding to a first pixel of the input image; and a controller configured to control the image processor to generate the output image by applying the first patch stored in the storage to the first pixel.Type: ApplicationFiled: April 13, 2020Publication date: July 30, 2020Applicant: SAMSUNG ELECTRONICS CO., LTD.Inventors: Seok-bong Yoo, Hyung-jun Lim, Gi-yeong Gim, Young-su Moon, Tae-gyoung Ahn
-
Publication number: 20200175653Abstract: Disclosed is a display apparatus including: a signal receiver configured to receive an image signal; a display configured to display an image; a processor configured to: calculate a change degree and a change direction of pixel value differences between at least one first pixel and two or more second pixels of an image, and change a pixel value of the first pixel based on the pixel value difference which is relatively small among the pixel value differences obtained by the calculated change degree and the calculated change direction. According to this, it is possible to enhance the image details without generating or and increasing of the noises.Type: ApplicationFiled: May 18, 2018Publication date: June 4, 2020Applicant: SAMSUNG ELECTRONICS CO., LTD.Inventors: Hyung-jun LIM, Seok-bong YOO, Tae-gyoung AHN, Young-su MOON, Seong-hoon CHOI
-
Patent number: 10650779Abstract: An image processing apparatus includes: a signal receiver configured to receive an input image; an image processor configured to process the input image and generate an output image; a storage configured to store a first patch corresponding to a first pixel of the input image; and a controller configured to control the image processor to generate the output image by applying the first patch stored in the storage to the first pixel.Type: GrantFiled: September 5, 2017Date of Patent: May 12, 2020Assignee: SAMSUNG ELECTRONICS CO., LTD.Inventors: Seok-bong Yoo, Hyung-jun Lim, Gi-yeong Gim, Young-su Moon, Tae-gyoung Ahn
-
Publication number: 20200104982Abstract: A display apparatus is provided. The display apparatus includes an input interface, a first storage, a display, and a processor. Pixel values corresponding to a predetermined number of lines in an image input through the input interface are stored in the first storage,. The processor acquires a first patch of a predetermined size by sampling a number of pixel values located in an outer region of a matrix centering about a specific pixel value from among the pixel values stored in the first storage, acquires a high-frequency component for the specific pixel value based on the acquired first patch, and processes the input image based on the high-frequency component. The display displays the processed image.Type: ApplicationFiled: December 3, 2019Publication date: April 2, 2020Applicant: SAMSUNG ELECTRONICS CO., LTD.Inventors: Hyung-jun LIM, Seok-bong YOO, Tae-gyoung AHN, Young-su MOON, Seong-hoon CHOI
-
Patent number: 10515440Abstract: A display apparatus is provided. The display apparatus includes an input interface, a first storage, a display, and a processor. Pixel values corresponding to a predetermined number of lines in an image input through the input interface are stored in the first storage. The processor acquires a first patch of a predetermined size by sampling a number of pixel values located in an outer region of a matrix centering about a specific pixel value from among the pixel values stored in the first storage, acquires a high-frequency component for the specific pixel value based on the acquired first patch, and processes the input image based on the high-frequency component. The display displays the processed image.Type: GrantFiled: July 5, 2018Date of Patent: December 24, 2019Assignee: SAMSUNG ELECTRONICS CO., LTD.Inventors: Hyung-jun Lim, Seok-bong Yoo, Tae-gyoung Ahn, Young-su Moon, Seong-hoon Choi
-
Publication number: 20190066274Abstract: A display apparatus is provided. The display apparatus includes an input interface, a first storage, a display, and a processor. Pixel values corresponding to a predetermined number of lines in an image input through the input interface are stored in the first storage. The processor acquires a first patch of a predetermined size by sampling a number of pixel values located in an outer region of a matrix centering about a specific pixel value from among the pixel values stored in the first storage, acquires a high-frequency component for the specific pixel value based on the acquired first patch, and processes the input image based on the high-frequency component. The display displays the processed image.Type: ApplicationFiled: July 5, 2018Publication date: February 28, 2019Applicant: SAMSUNG ELECTRONICS CO., LTD.Inventors: Hyung-jun LIM, Seok-bong YOO, Tae-gyoung AHN, Young-su MOON, Seong-hoon CHOI
-
Publication number: 20180068634Abstract: An image processing apparatus includes: a signal receiver configured to receive an input image; an image processor configured to process the input image and generate an output image; a storage configured to store a first patch corresponding to a first pixel of the input image; and a controller configured to control the image processor to generate the output image by applying the first patch stored in the storage to the first pixel.Type: ApplicationFiled: September 5, 2017Publication date: March 8, 2018Applicant: SAMSUNG ELECTRONICS CO., LTD.Inventors: Seok-bong YOO, Hyung-jun LIM, Gi-yeong GIM, Young-su MOON, Tae-gyoung AHN
-
Patent number: 8644636Abstract: A method and apparatus for removing an image blocking artifact by using a transformation coefficient are provided. The method includes: detecting a first blocking artifact which is in a flat region of the input image; removing the first blocking artifact using a number of low frequency coefficients from among transformation coefficients for each transformation block of a plurality of transformation blocks of the input image, based on a result of detecting the first blocking artifact; detecting an edge region of the input image; and removing a second blocking artifact, which is in an edge region of an intermediate image obtained from the removing of the first blocking artifact of the input image, based on the detected edge region in the input image.Type: GrantFiled: January 5, 2012Date of Patent: February 4, 2014Assignees: Samsung Electronics Co., Ltd., Korea Advanced Institute of Science and TechnologyInventors: Gun-shik Shin, Jong-beom Ra, Se-hyeok Park, Seok-bong Yoo, Jae-hyun Kim, Kyu-ha Choi
-
Publication number: 20120177301Abstract: A method and apparatus for removing an image blocking artifact by using a transformation coefficient are provided. The method includes: detecting a first blocking artifact which is in a flat region of the input image; removing the first blocking artifact using a number of low frequency coefficients from among transformation coefficients for each transformation block of a plurality of transformation blocks of the input image, based on a result of detecting the first blocking artifact; detecting an edge region of the input image; and removing a second blocking artifact, which is in an edge region of an intermediate image obtained from the removing of the first blocking artifact of the input image, based on the detected edge region in the input image.Type: ApplicationFiled: January 5, 2012Publication date: July 12, 2012Applicants: KOREA ADVANCED INSTITUTE OF SCIENCE & TECHNOLOGY, SAMSUNG ELECTRONICS CO., LTD.Inventors: Gun-shik SHIN, Jong-beom RA, Se-hyeok PARK, Seok-bong YOO, Jae-hyun KIM, Kyu-ha CHOI