Abstract: In the present disclosure, a method and a device for region of interest-based image encoding/decoding for machine vision may include extracting region of interest information in an image, performing an object tracking between frames based on the region of interest information, varying a resolution for each region of interest, and encoding an image with the region of interest information.

Abstract: Provided are face image generation method and device for generating a controllable talking face image.

Abstract: Disclosed herein is a method for generating a depth map from multi-view images, the method including receiving multi-view images and parameters thereof; generating an initial depth map, an initial normal map, and an initial reliability map for the multi-view images; performing selection of multiple initial vertices and triangulation based on the initial depth map and the initial normal map and generating depth values and normal values for the result of triangulation; performing regularization based on triangulation, selecting additional vertices in the initial depth map, and generating additional depth values and additional normal values based on the additional vertices and regularization; and refining the initial depth map into a refined depth map by replacing depth values and normal values having reliability below a preset level in the initial depth map and the initial normal map with the additional depth values and the additional normal values.

Abstract: A substrate cleaning apparatus may include a steam injector configured to clean a substrate, a steam supplier configured to supply a steam, and a gas supplier configured to supply a gas. The steam injector may include a drive unit configured to move horizontally, a plate on the drive unit, and a plurality of nozzles on the plate. The plate may include a temperature sensor, a first pressure sensor, and a second pressure sensor. Each of the plurality of nozzles may be connected to the steam supplier and the gas supplier. The plurality of nozzles may be arranged in one direction from a planar viewpoint.

Abstract: Disclosed herein are a method, an apparatus and a storage medium for image encoding/decoding using a segmentation map. A feature vector for an image may be extracted using a segmentation map. The image may be encoded using the segmentation map and the feature vector. An output stream from an encoding apparatus may include a video stream and a feature stream. An input stream to a decoding apparatus may include a video stream and a feature stream. The image may be reconstructed using a reconstructed segmentation map and a reconstructed feature vector.

Abstract: A non-uniform super-resolution method, device, and recording medium of an image of the present disclosure may include an image separation unit which separates an input image into a high-quality region and a low-quality region based on a quality map image, an image quality conversion unit which acquires a converted high-quality region by converting image quality of the high-quality region, and a first image combination unit which combines the converted high-quality region and the low-quality region to transmit them to a super-resolution network.

Abstract: An image encoding/decoding method, device and recording medium based sed on multiple compression levels disclosure may include extracting a region of interest for machine vision from an input image, determining a compression level of the region of interest, and encoding the compression level of the region of interest.

Abstract: An object-based image encoding/decoding method and device of the present disclosure may include an image partition step which partitions an image to obtain a first object region, a region scaling step which scales the first object region based on a scaling factor of the first object region to obtain a second objection region, a region merging step which merges the second object region with at least one of an object region different from the second object region or a non-object region to obtain a merged image, and an image reconstruction step which reconstructs the merged image.

Abstract: An image encoding method includes detecting at least one attention region from an original image, acquiring a reconstructed picture for the original image, generating residual data between a first attention region in the original image and a second attention region corresponding to the first attention region in the reconstructed picture, and encoding the residual data.

Abstract: Disclosed herein are an image processing method and apparatus for machine vision. The image processing method for machine vision includes generating an image with machine-unrecognizable distortion based on an input image, and encoding the image with machine-unrecognizable distortion.

Abstract: Disclosed herein is a method for compressing an image for machine vision, the method including detecting objects in an input image using an object detection network, generating a foreground image including bounding boxes corresponding to the objects and a background image, which is an image acquired by excluding the bounding boxes from the input image, encoding the foreground image and the background image, and decoding the encoded foreground image and the encoded background image.

Abstract: Disclosed herein is a method for generating a depth map from multi-view images, the method including receiving multi-view images and parameters thereof; generating an initial depth map, an initial normal map, and an initial reliability map for the multi-view images; performing selection of multiple initial vertices and triangulation based on the initial depth map and the initial normal map and generating depth values and normal values for the result of triangulation; performing regularization based on triangulation, selecting additional vertices in the initial depth map, and generating additional depth values and additional normal values based on the additional vertices and regularization; and refining the initial depth map into a refined depth map by replacing depth values and normal values having reliability below a preset level in the initial depth map and the initial normal map with the additional depth values and the additional normal values.

Abstract: Disclosed herein are a method, an apparatus and a storage medium for image encoding/decoding using a segmentation map. A feature vector for an image may be extracted using a segmentation map. The image may be encoded using the segmentation map and the feature vector. An output stream from an encoding apparatus may include a video stream and a feature stream. An input stream to a decoding apparatus may include a video stream and a feature stream. The image may be reconstructed using a reconstructed segmentation map and a reconstructed feature vector.

Abstract: An apparatus and method for providing physiological state information are provided. The apparatus includes a wearable electronic device. The wearable electronic device includes a sensor module configured to measure motion of the wearable electronic device, a display configured to provide a user interface (UI) including movable particles displayed on the display, and a processor configured to reduce the number of the displayed movable particles based on the measured motion of the wearable device.

Abstract: Provided is a method of removing noise from a sparse depth map. The method includes setting, as nodes, sample points in a sparse depth map including depth information at a certain position of an image plane, constructing a mesh by connecting the set nodes, and removing noise from the meshed node, based on connection information between the meshed node and neighboring nodes adjacent thereto and color information about a color image corresponding to the sparse depth map. A depth value is allocated to each of the sample points.

Abstract: An evaluation system of block copolymer patterns includes a supplier, a plurality of analyzers, and a homopolymer interference remover. The supplier provides a sample including a block copolymer and a homopolymer. The analyzers measure a molecular weight of the block copolymer in the sample, measure a preliminary block ratio, the preliminary block ratio corresponding to a total ratio in the sample of each block in the block copolymer, and selectively measure a ratio of the homopolymer in the sample. The homopolymer interference remover subtracts the ratio of the homopolymer from the preliminary block ratio.

Abstract: A conductivity detector includes a flow channel, an electrode arrangement, and a detector. The flow channel has a tube shape with a channel diameter through which a solution including ion components flows. The electrode arrangement is on the flow channel and includes at least an anode and at least a cathode. The anode and cathode are spaced apart by an electrode gap less than or equal to the channel diameter. The detector is connected to the electrode arrangement to detect electrical conductivity of the ion components.

Abstract: A method of encoding and reconstructing a depth image using color image information includes segmenting a color image and a depth image corresponding to the color image into block units, selecting a position of a pixel sampling value from each block of the depth image using the color image information, and encoding the pixel sampling value of the selected position as depth information.

Abstract: Disclosed is a pipe cover. The pipe cover has coupling units provided at both ends thereof and is disposed so as to surround a post structure by combining the coupling unit of one unit cover with the coupling unit of another unit cover.

Abstract: An electronic device is provided The electronic device includes an input unit configured to receive a selection on an object theme including at least one object from a user, an information collection unit configured to collect information corresponding to the object theme, a storage unit configured to divide the collected information into variable information or invariable information and store the information, and a display unit, when new variable information is collected according to a user instruction for reselecting the object theme, configured to add an object to an image by using the stored information and the new variable information and display the image.