-
公开(公告)号:US20230400406A1
公开(公告)日:2023-12-14
申请号:US18332096
申请日:2023-06-09
Inventor: Jong Ok KIM , Dong Keun HAN
IPC: G01N21/27 , G06V10/143 , G06V10/764 , G06V20/70 , G06V10/77
CPC classification number: G01N21/27 , G06V10/143 , G06V10/764 , G06V20/70 , G06V10/7715 , G01N2021/1765
Abstract: Disclosed are a material classification apparatus and method based on a multi-spectral NIR band. A material classification apparatus based on a multi-spectral NIR band includes: an input unit configured to acquire a multi-band NIR image of a target; an attention module configured to generate a spatio-spectral correlation map considering spatial information on the multi-band NIR image and a correlation between each band; and a classification model unit configured to analyze the spatio-spectral correlation map and output a material classification label for the target.
-
公开(公告)号:US20240161243A1
公开(公告)日:2024-05-16
申请号:US18221989
申请日:2023-07-14
Inventor: Jong Ok KIM , Tae Hyun KIM , Jeong Hyeok PARK
IPC: G06T5/50
CPC classification number: G06T5/50 , G06T2207/10024 , G06T2207/10048 , G06T2207/10152 , G06T2207/20081 , G06T2207/20084 , G06T2207/20221
Abstract: Disclosed are a low-light image improvement apparatus and method. The low-light image improvement apparatus includes: an image component decomposition network module that analyzes a light image, a low-light image, and a mid-light image to decompose reflectance and illumination, respectively, wherein the mid-light image is generated using the light image and the low-light image; and a component improvement network module configured to include a mid-teacher network model that extracts a first feature map with improved reflectance and illumination of the mid-light image using the reflectance and illumination of the light image and a student network module that distills the extracted first feature map and then extracts a second feature map for the reflectance and illumination of the low-light image based on the distilled first feature map and acquires an image with improved light by reflecting a structural component of a multi-band near-infrared image in the second feature map.
-
公开(公告)号:US20220159165A1
公开(公告)日:2022-05-19
申请号:US17666063
申请日:2022-02-07
Inventor: Jong Ok KIM , Jun Sang YOO
Abstract: Disclosed is an image processing method and apparatus. The image processing method includes receiving an image including frames captured over time in a light environment including an alternating current (AC) light, extracting AC pixels corresponding to the AC light from pixels in the image, estimating visual spaces of the AC pixels based on values of the AC pixels in the frames, estimating information of the AC light included in the image based on the visual spaces, and processing the image based on the information of the AC light.
-
公开(公告)号:US20230078522A1
公开(公告)日:2023-03-16
申请号:US17720626
申请日:2022-04-14
Inventor: Junsang YU , Jong Ok KIM , Kang Kyu LEE
IPC: G06V10/145 , G06V10/82 , G06V10/56
Abstract: A device with image processing includes: an image acquirer configured to acquire a plurality of images each having a different brightness; and one or more processors configured to extract an illumination map for an input image of the images and an illuminant color of the input image from the input image and temporal correlation information of the plurality of images, based on an illumination extraction model.
-
公开(公告)号:US20200374443A1
公开(公告)日:2020-11-26
申请号:US16860385
申请日:2020-04-28
Inventor: Jong Ok KIM , Jun Sang YOO
Abstract: Disclosed is an image processing method and apparatus. The image processing method includes receiving an image including frames captured over time in a light environment including an alternating current (AC) light, extracting AC pixels corresponding to the AC light from pixels in the image, estimating visual spaces of the AC pixels based on values of the AC pixels in the frames, estimating information of the AC light included in the image based on the visual spaces, and processing the image based on the information of the AC light.
-
公开(公告)号:US20240144640A1
公开(公告)日:2024-05-02
申请号:US18193780
申请日:2023-03-31
Inventor: Jong Ok KIM , Jeong Won HA , Dong Keun HAN
CPC classification number: G06V10/60 , G06V10/7715 , G06V10/82
Abstract: Provided is a method and an apparatus for processing an image based on a neural network. The method includes forming an input image set by combining a visible light image and an infrared image, estimating an illuminant map representing an illuminant configuration of the input image set and a confidence score map representing a correlation between the visible light image and the infrared image, using a neural network model, and determining illuminant information of the visible light image based on the illuminant map and the confidence score map.
-
公开(公告)号:US20240119633A1
公开(公告)日:2024-04-11
申请号:US18375696
申请日:2023-10-02
Inventor: Jong Ok KIM , Tae Sung PARK
CPC classification number: G06T7/90 , G06T5/001 , G06T7/0002 , G06T7/40 , G06T2207/10048 , G06T2207/20081 , G06T2207/30168
Abstract: The method for converting a near-infrared image into an RGB image includes: (a) receiving near-infrared image data to be converted into an RGB image and inputting the received data to the first network; (b) extracting, by the first network, feature data of a near-infrared image from the input near-infrared image data; and (c) outputting, by the first network, an estimated RGB image, which enables to convert the received near-infrared image data into an RGB image, using the extracted feature data of the near-infrared image, wherein the first network performs knowledge distillation learning by receiving knowledge, which enables to mimic the behavior of extracting the feature data of the near-infrared image and the feature data of the RGB image, from the second network which has received as input data not only near-infrared image data as learning data but also RGB image data taken at the same time as the near-infrared image.
-
-
-
-
-
-