Abstract: An object detection method and an object detection apparatus for detecting an object based on multi-features are provided. The object detection method includes: obtaining first-sensor data from a first sensor and obtaining second-sensor data from a second sensor, wherein the first sensor is a different type of sensor than the second sensor; extracting a first feature from the first-sensor data and extracting a second feature from the second-sensor data; determining a target feature-type by inputting the first and second features to a feature-type selection model which, based thereon, predicts the target feature-type; determining a target feature to be used for object detection according to the determined target feature-type; and determining an object detection result based on the determined target feature.

Abstract: A liveness detection method and apparatus, and a facial verification method and apparatus are disclosed. The liveness detection method includes detecting a face region in an input image, measuring characteristic information of the face region, adjusting the measured characteristic information in response to the characteristic information not satisfying a condition, and performing a liveness detection on the face region with the adjusted characteristic information upon the measured characteristic information not satisfying the condition.

Abstract: An electronic device includes a display panel including a first region and a second region spaced apart from the first region, in which the first region includes an element region, a transmissive region disposed adjacent to the element region, a copy element region spaced apart from the element region and partially surrounded by the transmissive region, and a bridge region connected to the copy element region and the element region. The display panel includes a plurality of light emitting elements disposed in the element region and a copy light emitting element that operates in synchronization with one of the plurality of light emitting elements and that is disposed in the copy element region, where the copy element region overlaps a center of a transmissive edge that defines the transmissive region.

Abstract: Disclosed is an object recognition method and object recognition apparatus. The object recognition method may include detecting an object region comprising an object in an input image, determining scores corresponding to regions of the object region, determining weights based on the scores and detection information of the object region, determining a final score based on the scores and the determined weights, and determining a result of recognizing the object based on the final score.

Abstract: A display panel includes a substrate including a transmissive area, a transistor over the substrate and adjacent to the transmissive area, a light-emitting diode electrically connected to the transistor, a bottom metal layer disposed between the substrate and the transistor and overlapping the transistor, and a plurality of inorganic insulation layers between the bottom metal layer and the light-emitting diode. An opening penetrating at least one of the inorganic insulation layers overlaps the bottom metal layer and thereby, an electronic device with improved image quality of the display panel may be implemented by preventing light emitted from components from entering thin-film transistors.

Abstract: A device and method with object recognition is included. In one general aspect, an electronic device includes a camera sensor configured to capture a first image of a scene, the camera sensor is configured to perform at least one type of physical camera motion relative to the electronic device, the at least one type of physical camera motion includes rolling, panning, tilting, or zooming the camera sensor relative to the electronic device, and a processor configured to control the camera sensor to perform a physical motion of the physical camera motion type based on detecting an object in the first image, acquire a second image captured using the camera sensor as adjusted based on the performed physical motion, and recognize the object in the second image.

Abstract: A method and apparatus for detecting a liveness based on a phase difference are provided. The method includes generating a first phase image based on first visual information of a first phase, generating a second phase image based on second visual information of a second phase, generating a minimum map based on a disparity between the first phase image and the second phase image, and detecting a liveness based on the minimum map.

Abstract: A method and apparatus for detecting a liveness based on a phase difference are provided. The method includes generating a first phase image based on first visual information of a first phase, generating a second phase image based on second visual information of a second phase, generating a minimum map based on a disparity between the first phase image and the second phase image, and detecting a liveness based on the minimum map.

Abstract: An apparatus with image segmentation includes: one or more processors configured to: obtain a second image based on a first segmentation label corresponding to a first image; generate a composite image by composing an image of an object corresponding to an object class of the first image among objects comprised by the second image with the first image; and train an image segmentation model based on the composite image, the first image, and the second image.

Abstract: A processor-implemented method with pose estimation includes: receiving an image, instance queries for object identification, and joint queries for joint identification; generating first heat maps associated with objects and second heat maps associated with joints in parallel based on the image, the instance queries, and the joint queries; and estimating respective joint information of a plurality of objects included in the image by combining the first heat maps and the second heat maps.

Abstract: An apparatus and method for processing an image are provided. The apparatus includes: one or more processors; memory storing instructions configured to, when executed by the one or more processors, cause the one or more processors to: detect objects in the image; determine region of interest (ROI) scores of the respective detected objects; determine whether to display icons for the respective objects based on the respective ROI scores; display an image processing user interface including at least a portion of the image and the icons; and receive an input selecting an icon from among the icons displayed with the user interface, and in response perform image processing based on the selected icon.

Abstract: An apparatus includes one or more processors configured to generate a plurality of feature maps having respective different resolutions based on an input image; and update, for each of the plurality of transformer layers, respective position estimation information comprising first position information of a respective bounding box corresponding to one object query and second position information of respective key points corresponding to the one object query, wherein each of the plurality of transformer layers includes a self-attention model configured to generate respective intermediate data by performing self-attention on respective content information on a feature of the input image; and a cross-attention model configured to generate respective output data by performing cross-attention on respective one or more feature maps among the plurality of feature maps and the respective generated intermediate data.

Abstract: An apparatus and a method of controlling a camera is provided. The apparatus includes a receiver configured to receive an image from an image sensor and a processor configured to detect a target object from the image, perform a first zoom adjustment operation of the camera including the image sensor based on whether the target object is changed and perform a second zoom adjustment of the camera based on a center point of the target object and a center point of the camera.

Abstract: A display apparatus includes a substrate including a component area including a transmission area, a main area outside the component area, and a bending area bent based on a bending axis, a buffer layer disposed on the substrate, a first semiconductor layer disposed on the buffer layer, and a first gate insulating layer overlapping the first semiconductor layer and including a 1-1st opening corresponding to the bending area, and a 1-1st through-hole exposing a portion of the first semiconductor layer. A first acute angle formed by an inner surface of the 1-1st opening with respect to an upper surface of the substrate is less than a first contact acute angle formed by an inner surface of the 1-1st through-hole with respect to the upper surface of the substrate.

Abstract: A display device includes: a substrate including a first display area including a plurality of first pixel areas and a plurality of transmission areas, and a second display area including a plurality of second pixel areas; a light blocking layer disposed in the first and second display areas on the substrate, wherein an opening overlapping each of the transmission areas is defined through the light blocking layer, and the opening has a planar shape including at least two adjacent curves having different radii of curvature from each other; and a plurality of pixels respectively disposed in the first and second pixel areas on the light blocking layer and each including a light emitting element.

Abstract: An electronic device includes a display panel with a first area including a transmissive area, an element area, and connection areas extending from the element area, and a second area. The display panel includes a first light emitting unit in the element area and including first, second, and third light emitting elements, and a first copy light emitting unit in the connection areas, including copy light emitting elements, and operating in synchronization with the first light emitting unit. The connection areas include a first connection area adjacent to the first light emitting element, a second connection area adjacent to the second light emitting element, and third and fourth connection areas adjacent to the third light emitting element. An emission color of the first light emitting element is different from an emission color of a first copy light emitting element of the copy light emitting elements in the first connection area.

Abstract: A light emitting display device includes a display area and a component area surrounded by the display area, the component area in which an optical element is disposed, wherein the display area includes a first normal pixel and a second normal pixel connected to a first data line and adjacent to opposite sides of the component area, respectively, and a third normal pixel and a fourth normal pixel connected to a second data line and positioned on the opposite sides of the component area, respectively, the component area includes a first unit pixel connected to the first data line and a bypass data line, the second data line and the bypass data line are formed of different conductive layers, respectively, and the second data line is connected to a bypass data line in the boundary area positioned between the display area and the component area.

Abstract: A liveness detection method and apparatus, and a facial verification method and apparatus are disclosed. The liveness detection method includes detecting a face region in an input image, measuring characteristic information of the face region, adjusting the measured characteristic information in response to the characteristic information not satisfying a condition, and performing a liveness detection on the face region with the adjusted characteristic information upon the measured characteristic information not satisfying the condition.

Abstract: An electronic device includes a display panel including a first area and a second area. The display panel includes a barrier layer including a first lower light blocking layer disposed in the first area and a second lower light blocking layer disposed in the second area, the first lower light blocking layer and the second lower light blocking layer disposed on a same layer and a circuit layer including a first pixel circuit disposed in the first area and a second pixel circuit disposed in the second area. The first pixel circuit includes a plurality of first-type transistors, the second pixel circuit includes a plurality of second-type transistors, the first lower light blocking layer entirely overlaps the first-type transistors, and the second lower light blocking layer overlaps some of the second-type transistors and does not overlap the other of the second-type transistors.

Abstract: Disclosed is a method and apparatus for testing a liveness, where the liveness test method includes receiving a color image and a photodiode (PD) image of an object from an image sensor comprising a pixel formed of a plurality of PDs, preprocessing the color image and the PD image, and determining a liveness of the object by inputting a result of preprocessing the color image and a result of preprocessing the PD image into a neural network.