Abstract: Apparatuses and methods for image processing are provided. The image processing apparatus performs area classification and object detection in an image, and includes a feature map generator configured to generate the feature map of the input image using the neural network, and an image processor configured to classify the areas and to detect the objects in the image using the generated feature map.

Abstract: Disclosed is an apparatus and method to train an autonomous driving model. The apparatus includes a driver information collection processor configured to collect driver information while a vehicle is being driven. The apparatus also includes a sensor information collection processor configured to collect sensor information from a sensor installed in the vehicle while the vehicle is being driven, and a model training processor configured to train the autonomous driving model based on the driver information and the sensor information.

Abstract: An electronic device comprises a camera; a sensor configured to sense a motion; and one or more processors, wherein the one or more processors are configured to: sequentially acquire a plurality of images using the camera and acquire motion information of the plurality of images using the sensor, during a specified time; create a panoramic image with a first image sub-set comprising a portion of the plurality of images and a second image sub-set comprising another portion of the plurality of images, and moving picture data related to the panoramic image; and determine whether to correct at least a partial section of the moving picture data using a particular image from the second image sub-set that corresponds to the at least the partial section of the moving picture data, based on the frame rate of the at least the partial section of the moving picture data.

Abstract: Apparatuses and methods for image processing are provided. The image processing apparatus performs area classification and object detection in an image, and includes a feature map generator configured to generate the feature map of the input image using the neural network, and an image processor configured to classify the areas and to detect the objects in the image using the generated feature map.

Abstract: Apparatuses and methods for image processing are provided. The image processing apparatus performs area classification and object detection in an image, and includes a feature map generator configured to generate the feature map of the input image using the neural network, and an image processor configured to classify the areas and to detect the objects in the image using the generated feature map.

Abstract: A tomography method for generating a computed tomography (CT) image, including generating a first tomography image based on first raw data corresponding to a received X-ray comprising acquired photons; determining second raw data by generating a second tomography image having an increased resolution in comparison with the first tomography image and performing forward projection on the second tomography image; determining third raw data based on a first parameter, the first raw data, and the second raw data; and generating a third tomography image based on the third raw data, wherein the determining of the third raw data may be based on information about a distribution of the acquired photons, the information being included in at least one from among the first raw data and the second raw data.

Abstract: Disclosed are methods and apparatuses for object recognition using an artificial neural network. An object recognition apparatus includes an adjacent pixel setter configured to set the neighboring pixel pairs in the image frame, each neighboring pixel pair including first pixel and one or more second pixels adjacent to the first pixel, a labeler configured to label the first pixel using deep neural network-based model based on probability density function value of the neighboring pixel pairs, and an object recognizer configured to recognize an object based on the labeled first pixel.

Abstract: Disclosed is an apparatus and method to train an autonomous driving model. The apparatus includes a driver information collection processor configured to collect driver information while a vehicle is being driven. The apparatus also includes a sensor information collection processor configured to collect sensor information from a sensor installed in the vehicle while the vehicle is being driven, and a model training processor configured to train the autonomous driving model based on the driver information and the sensor information.

Abstract: An electronic device comprises a camera; a sensor configured to sense a motion; and one or more processors, wherein the one or more processors are configured to: sequentially acquire a plurality of images using the camera and acquire motion information of the plurality of images using the sensor, during a specified time; create a panoramic image with a first image sub-set comprising a portion of the plurality of images and a second image sub-set comprising another portion of the plurality of images, and moving picture data related to the panoramic image; and determine whether to correct at least a partial section of the moving picture data using a particular image from the second image sub-set that corresponds to the at least the partial section of the moving picture data, based on the frame rate of the at least the partial section of the moving picture data.

Abstract: Disclosed is an apparatus and method to train an autonomous driving model. The apparatus includes a driver information collection processor configured to collect driver information while a vehicle is being driven. The apparatus also includes a sensor information collection processor configured to collect sensor information from a sensor installed in the vehicle while the vehicle is being driven, and a model training processor configured to train the autonomous driving model based on the driver information and the sensor information.

Abstract: A tomography method for generating a computed tomography (CT) image, including generating a first tomography image based on first raw data corresponding to a received X-ray comprising acquired photons; determining second raw data by generating a second tomography image having an increased resolution in comparison with the first tomography image and performing forward projection on the second tomography image; determining third raw data based on a first parameter, the first raw data, and the second raw data; and generating a third tomography image based on the third raw data, wherein the determining of the third raw data may be based on information about a distribution of the acquired photons, the information being included in at least one from among the first raw data and the second raw data.

Abstract: Apparatuses and methods for image processing are provided. The image processing apparatus performs area classification and object detection in an image, and includes a feature map generator configured to generate the feature map of the input image using the neural network, and an image processor configured to classify the areas and to detect the objects in the image using the generated feature map.

Abstract: Disclosed is an apparatus and method to train an autonomous driving model. The apparatus includes a driver information collection processor configured to collect driver information while a vehicle is being driven. The apparatus also includes a sensor information collection processor configured to collect sensor information from a sensor installed in the vehicle while the vehicle is being driven, and a model training processor configured to train the autonomous driving model based on the driver information and the sensor information.

Abstract: Disclosed are methods and apparatuses for object recognition using an artificial neural network. An object recognition apparatus includes an adjacent pixel setter configured to set the neighboring pixel pairs in the image frame, each neighboring pixel pair including first pixel and one or more second pixels adjacent to the first pixel, a labeler configured to label the first pixel using deep neural network-based model based on probability density function value of the neighboring pixel pairs, and an object recognizer configured to recognize an object based on the labeled first pixel.

Abstract: A nonvolatile memory device, including a first latch unit and a nonvolatile memory cell, and a method of writing data in a nonvolatile memory device are provided. The method includes receiving a first writing command or a second writing command from outside of the nonvolatile memory device, and writing first data stored in the first latch unit in the nonvolatile memory cell in response to the first or second writing command. The first data is retained in the first latch unit until the writing of the first data stored in the first latch unit in the nonvolatile memory cell is completed.

Abstract: A method performed at a terminal of a medical team user for changing a medicine-taking schedule includes generating a first medicine-taking schedule, transmitting the first medicine-taking schedule to a terminal of a patient, and receiving a medicine-taking schedule change request from the terminal of the patient. A further operation includes changing the first medicine-taking schedule to a second medicine-taking schedule when a time parameter of the first medicine-taking schedule is within a threshold value of a time parameter of the second medicine-taking schedule.

Abstract: Provided is an apparatus, system, and method related to displaying medicine-taking information, including displaying a first page received from a schedule management server on a display of a patient terminal, the first page including a medicine schedule associated with a particular medicine; displaying a second page separately from the first page on the display, the second page configured for inputting information related to pickup of the particular medicine associated with the medicine schedule; displaying a third page separately from the first page and the second page on the display, the third page including a detailed information button for displaying additional information related to the particular medicine; and transmitting input information for at least the first, second, or third page to the schedule management server.

Abstract: Provided is a medical care provider terminal, a patient terminal and a method for making a video call therebetween. The method may include receiving, at a medical care provider terminal, a video call request from a patient terminal, connecting, at the medical care provider, a video call to the patient terminal, and displaying patient-related information in a first region of a display of the medical care provider terminal and displaying a video call screen in a second region of the display. The video call screen may include a sharing region for sharing with the patient terminal at least one of a first video captured by a camera module connected to the patient terminal, a second video captured by a camera module connected to the medical care provider terminal, the patient-related information, or data input at the medical care provider terminal.

Abstract: A nonvolatile memory device, including a first latch unit and a nonvolatile memory cell, and a method of writing data in a nonvolatile memory device are provided. The method includes receiving a first writing command or a second writing command from outside of the nonvolatile memory device, and writing first data stored in the first latch unit in the nonvolatile memory cell in response to the first or second writing command. The first data is retained in the first latch unit until the writing of the first data stored in the first latch unit in the nonvolatile memory cell is completed.

Abstract: A method of programming a multi-level cells (MLC) commonly coupled to a word line in a non-volatile memory device includes shadow-programming first MLC to a first shadow state, shadow-programming second MLC to a second shadow state less than the first shadow state, and then main-programming the first MLC from the first shadow state to a first final state and main-programming the second MLC from the second shadow state to the second final state less than the first final state.