Abstract: A processor implemented image processing method includes acquiring a facial image by performing a face detection on an image, performing a quality assessment on the facial image using a preset facial image regression model, and determining a quality level of the facial image based on the quality assessment.

Abstract: A processor implemented method of processing a facial expression image, the method includes acquiring an expression feature of each of at least two reference facial expression images; generating a new expression feature based on an interpolation value of the expression feature; and adjusting a target facial expression image based on the new expression feature and creating a new facial expression image.

Abstract: An image processing apparatus, includes an image classifier configured to determine whether an input image is a low-quality image or a high-quality image; and an image evaluator configured to determine a first predetermined number of clearest images from a plurality of low-quality images determined by the image classifier.

Abstract: Provided are a positioning method and apparatus. The positioning method includes acquiring a plurality of positioning results including positions of key points of a facial area included in an input image, respectively using a plurality of predetermined positioning models, evaluating the plurality of positioning results using an evaluation model of the positions of the key points, and updating at least one of the plurality of predetermined positioning models and the evaluation model based on a positioning result that is selected, based on a result of the evaluating, from among the plurality of positioning results.

Abstract: A method of detecting a target includes determining a quality type of a target image captured using a camera, determining a convolutional neural network of a quality type corresponding to the quality type of the target image in a database comprising convolutional neural networks, determining a detection value of the target image based on the convolutional neural network of the corresponding quality type, and determining whether a target in the target image is a true target based on the detection value of the target image.

Abstract: A method of detecting a target includes generating an image pyramid based on an image on which a detection is to be performed; classifying candidate areas in the image pyramid using a cascade neural network; and determining a target area corresponding to a target included in the image based on the plurality of candidate areas, wherein the cascade neural network includes a plurality of neural networks, and at least one neural network among the neural networks includes parallel sub-neural networks.

Abstract: An eye detection method and apparatus based on depth information. The eye detection method includes inputting an image to a trained deep neural network and acquiring eye position information included in the image based on an output of the deep neural network.

Abstract: A virtual world processing apparatus and method. Sensed information, which is information collected by a sensor is inputted. The sensed information is adapted, based on a sensor capability, which is information on capability of the sensor. Accordingly, interoperability between a real world and a virtual world or interoperability between virtual worlds may be achieved.

Abstract: A method to analyze a facial image includes: inputting a facial image to a residual network including residual blocks that are sequentially combined and arranged in a direction from an input to an output; processing the facial image using the residual network; and acquiring an analysis map from an output of an N-th residual block among the residual blocks using a residual deconvolution network, wherein the residual network transfers the output of the N-th residual block to the residual deconvolution network, and N is a natural number that is less than a number of all of the residual blocks, and wherein the residual deconvolution network includes residual deconvolution blocks that are sequentially combined, and the residual deconvolution blocks correspond to respective residual blocks from a first residual block among the residual blocks to the N-th residual block.

Abstract: At least one example embodiment discloses a method of converting a vector corresponding to an input image. The method includes receiving first-dimensional vector data associated with an input image, the input image including an object and converting the received first-dimensional vector data to second-dimensional vector data based on a projection matrix with an associated rank. A first dimension of the first-dimensional vector data is higher than a second dimension of the second-dimensional vector data.

Abstract: A method to reduce a neural network includes: adding a reduced layer, which is reduced from a layer in the neural network, to the neural network; computing a layer loss and a result loss with respect to the reduced layer based on the layer and the reduced layer; and determining a parameter of the reduced layer based on the layer loss and the result loss.

Abstract: In an apparatus and method for processing a virtual world, haptic information regarding a virtual object in the virtual world, the haptic information corresponding to sensed information, is extracted and transmitted to a haptic feedback device. Accordingly, interaction between a real world and the virtual world is achieved. The processing speed of the haptic information with respect to the virtual object may be increased by varying data structures according to types of the virtual object.

Abstract: A lightened neural network method and apparatus. The neural network apparatus includes a processor configured to generate a neural network with a plurality of layers including plural nodes by applying lightened weighted connections between neighboring nodes in neighboring layers of the neural network to interpret input data applied to the neural network, wherein lightened weighted connections of at least one of the plurality of layers includes weighted connections that have values equal to zero for respective non-zero values whose absolute values are less than an absolute value of a non-zero value. The lightened weighted connections also include weighted connections that have values whose absolute values are no greater than an absolute value of another non-zero value, the lightened weighted connections being lightened weighted connections of trained final weighted connections of a trained neural network whose absolute maximum values are greater than the absolute value of the other non-zero value.

Abstract: A lightened neural network, method, and apparatus, and recognition method and apparatus implementing the same. A neural network includes a plurality of layers each comprising neurons and plural synapses connecting neurons included in neighboring layers. Synaptic weights with values greater than zero and less than a preset value of a variable a, which is greater than zero, may be at least partially set to zero. Synaptic weights with values greater than a preset value of a variable b, which is greater than zero, may be at least partially set to the preset value of the variable b.

Abstract: A multi-touch sensing apparatus using a rear view camera of an array type is provided. The multi-touch sensing apparatus may include a display panel to display an image, a sensing light source to emit light to sense a touch image which is generated by an object and displayed on a back side of the display panel, and a camera to divide and sense the touch image. The camera may be arranged in an edge of a lower side of the multi-touch sensing apparatus, or a mirror to reflect the touch image may be included in the multi-touch sensing apparatus.

Abstract: A user verification apparatus may perform user verification using multiple biometric verifiers. The user verification apparatus may set a termination stage of one or more biometric verifiers. Multiple biometric verifiers may be used to generate outputs, for which separate termination stages are set to establish a particular combination of set termination stages associated with the multiple biometric verifiers, and the user verification apparatus may fuse outputs of the biometric verifiers based on the particular combination of set termination stages. The user verification apparatus may verify a user based on a result of the fusing, and an unlocking command signal may be generated based on the verifying. The unlocking command signal may be generated to selectively grant access, to the verified user, to one or more elements of a device. The device may be a vehicle.

Abstract: A method for authenticating a user includes generating an image for authentication based on at least one authenticated image based on an input image, and performing authentication based on the generated image for authentication.

Abstract: A three-dimensional (3D) display device for displaying a 3D image using at least one of a gaze direction of a user and a gravity direction includes a gaze direction measuring unit to measure the gaze direction, a data obtaining unit to obtain 3D image data for the 3D image, a viewpoint information obtaining unit to obtain information relating to a viewpoint of the 3D image, a data transform unit to transform the 3D image data, based on the gaze direction and the information relating to the viewpoint of the 3D image, and a display unit to display the 3D image, based on the transformed 3D image data.

Abstract: An apparatus and method for analyzing body part association. The apparatus and method may recognize at least one body part from a user image extracted from an observed image, select at least one candidate body part based on association of the at least one body part, and output a user pose skeleton related to the user image based on the selected at least one candidate body part.

Abstract: A data transmission apparatus and method. Information exchange between virtual worlds is achieved by encoding information on a virtual world into metadata and transmitting the metadata to another virtual world. In particular, since the information on the virtual world is encoded into a binary format, high speed data transmission may be achieved.