Abstract: A neural network optimizing device includes a performance estimating module that outputs estimated performance according to performing operations of a neural network based on limitation requirements on resources used to perform the operations of the neural network. A portion selecting module receives the estimated performance from the performance estimating module and selects a portion of the neural network which deviates from the limitation requirements. A new neural network generating module generates, through reinforcement learning, a subset by changing a layer structure included in the selected portion of the neural network, determines an optimal layer structure based on the estimated performance provided from the performance estimating module, and changes the selected portion to the optimal layer structure to generate a new neural network. A final neural network output module outputs the new neural network generated by the new neural network generating module as a final neural network.

Abstract: A semiconductor device is provided. The semiconductor device comprises a first memory unit including a first memory area, and a first logic area electrically connected to the first memory area, the first logic area including a cache memory and an interface port. The first memory unit executes a data transmission and reception operation with a memory unit adjacent to the first memory unit via the first interface port and the cache memory.

Abstract: An artificial neural network (ANN) system includes a processor, a virtual overflow detection circuit and a data format controller. The processor performs node operations with respect to a plurality of nodes included in each layer of an ANN to obtain a plurality of result values of the node operations and performs a quantization operation on the obtained plurality of result values based on a k-th fixed-point format for a current quantization of the each layer to obtain a plurality of quantization values. The virtual overflow detection circuit generates a virtual overflow information indicating a distribution of valid bit numbers of the obtained plurality of quantization values. The data format controller determines a (k+1)-th fixed-point format for a next quantization of the each layer based on the generated virtual overflow information. An overflow and/or an underflow are prevented efficiently by controlling the fixed-point format using the virtual overflow.

Abstract: An electronic device includes a first camera that obtains a first image, a second camera that obtains a second image having a disparity with the first image, a memory that stores a first calibration parameter, and a processor that calibrates at least one of the first image and the second image by using the first calibration parameter and composes the first image and the second image. The processor is configured to collect, if a specified event occurs, images obtained from the first camera and the second camera after the specified event occurs and store the collected images in the memory, to compute a second to calibration parameter based on the images obtained after the specified event occurs, if a specified condition is satisfied, and to update the first calibration parameter with the second calibration parameter.

Abstract: Image capturing methods and image capturing apparatuses are provided. The image capturing method may include setting a target position of a live view image, tacking a moving object from the live view image, estimating a position of the moving object by using information on the tracked moving object, and capturing a still image based on the estimated position when the moving object is positioned on the target position of the live view image.

Abstract: An electronic device includes a first camera that obtains a first image, a second camera that obtains a second image having a disparity with the first image, a memory that stores a first calibration parameter, and a processor that calibrates at least one of the first image and the second image by using the first calibration parameter and composes the first image and the second image. The processor is configured to collect, if a specified event occurs, images obtained from the first camera and the second camera after the specified event occurs and store the collected images in the memory, to compute a second to calibration parameter based on the images obtained after the specified event occurs, if a specified condition is satisfied, and to update the first calibration parameter with the second calibration parameter.

Abstract: An image photographing apparatus and an image photographing method are provided. The image photographing apparatus includes: a plurality of image capturers respectively comprising lenses having different focal distances and respectively configured to capture a plurality of images having different resolutions; a storage configured to store the plurality of images captured by the plurality of image capturers; an image processor configured to adjust properties of the plurality of images to correspond to each other; a controller configured to, in response to a magnification change command being input, control the image processor to synthesize the plurality of images of which the properties are adjusted and generate a synthesis image of a magnification changed according to the magnification change command; and a display configured to display the synthesis image.

Abstract: A method and apparatus for detecting an object is provided. The method includes recognizing a predetermined object from at least one of an image and a video and determining a position of the recognized object, displaying on the image or the video a location of a predetermined part of the recognized object, rearranging the displayed location of the predetermined part of the recognized object based on an input signal, and renewing the position of the recognized object based on a result of the rearranging of the displayed location of the predetermined part of the recognized object.

Abstract: An image photographing apparatus is provided. The image photographing apparatus includes a photographing unit configured to photograph a plurality of objects and a controller configured to determine a main object to be used as a reference for a photographing operation from among the plurality of objects, set a parameter for the photographing operation based on a motion of the main object, and control the photographing unit to photograph the plurality of objects using the parameter.

Abstract: Image capturing methods and image capturing apparatuses are provided. The image capturing method may include setting a target position of a live view image, tacking a moving object from the live view image, estimating a position of the moving object by using information on the tracked moving object, and capturing a still image based on the estimated position when the moving object is positioned on the target position of the live view image.

Abstract: An image photographing apparatus and an image photographing method are provided. The image photographing apparatus includes: a plurality of image capturers respectively comprising lenses having different focal distances and respectively configured to capture a plurality of images having different resolutions; a storage configured to store the plurality of images captured by the plurality of image capturers; an image processor configured to adjust properties of the plurality of images to correspond to each other; a controller configured to, in response to a magnification change command being input, control the image processor to synthesize the plurality of images of which the properties are adjusted and generate a synthesis image of a magnification changed according to the magnification change command; and a display configured to display the synthesis image.

Abstract: A method and apparatus for detecting an object is provided. The method includes recognizing a predetermined object from at least one of an image and a video and determining a position of the recognized object, displaying on the image or the video a location of a predetermined part of the recognized object, rearranging the displayed location of the predetermined part of the recognized object based on an input signal, and renewing the position of the recognized object based on a result of the rearranging of the displayed location of the predetermined part of the recognized object.