Abstract: Face recognition of a face, to determine whether the face correlates with an enrolled face, may include generating a personalized three-dimensional (3D) face model based on a two-dimensional (2D) input image of the face, acquiring 3D shape information and a normalized 2D input image of the face based on the personalized 3D face model, generating feature information based on the 3D shape information and pixel color values of the normalized 2D input image, and comparing the feature information with feature information associated with the enrolled face. The feature information may include first and second feature information generated based on applying first and second deep neural network models to the pixel color values of the normalized 2D input image and the 3D shape information, respectively. The personalized 3D face model may be generated based on transforming a generic 3D face model based on landmarks detected in the 2D input image.

Abstract: Disclosed is a liveness test method and apparatus. A liveness test apparatus determines a pre-liveness score based on a plurality of sub-images acquired from an input image, determines a post-liveness score based on a recognition model for recognizing an object included in the input image, and determines a liveness of the object based on any one or any combination of the pre-liveness score and the post-liveness score.

Abstract: Disclosed is a face verification method and apparatus. The method including analyzing a current frame of a verification image, determining a current frame state score of the verification image indicating whether the current frame is in a state predetermined as being appropriate for verification, determining whether the current frame state score satisfies a predetermined validity condition, and selectively, based on a result of the determining of whether the current frame state score satisfies the predetermined validity condition, extracting a feature from the current frame and performing verification by comparing a determined similarity between the extracted feature and a registered feature to a set verification threshold.

Abstract: Face recognition of a face, to determine whether the face correlates with an enrolled face, may include generating a personalized three-dimensional (3D) face model based on a two-dimensional (2D) input image of the face, acquiring 3D shape information and a normalized 2D input image of the face based on the personalized 3D face model, generating feature information based on the 3D shape information and pixel color values of the normalized 2D input image, and comparing the feature information with feature information associated with the enrolled face. The feature information may include first and second feature information generated based on applying first and second deep neural network models to the pixel color values of the normalized 2D input image and the 3D shape information, respectively. The personalized 3D face model may be generated based on transforming a generic 3D face model based on landmarks detected in the 2D input image.

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: Disclosed is a liveness test method and apparatus. A liveness test apparatus determines a pre-liveness score based on a plurality of sub-images acquired from an input image, determines a post-liveness score based on a recognition model for recognizing an object included in the input image, and determines a liveness of the object based on any one or any combination of the pre-liveness score and the post-liveness score.

Abstract: A method and apparatus for generating a facial expression may receive an input image, and generate facial expression images that change from the input image based on an index indicating a facial expression intensity of the input image, the index being obtained from the input image.

Abstract: Disclosed is a facial verification apparatus and method. The facial verification apparatus is configured to detect a face area of a user from an obtained input image, generate a plurality of image patches, differently including respective portions of the detected face area, based on a consideration of an image patch set determination criterion with respect to the detected face area, extract a feature value corresponding to a face of the user based on an image patch set including the generated plurality of image patches, determine whether a facial verification is successful based on the extracted feature value, and indicate a result of the determination of whether the facial verification is successful.

Abstract: Provided is a method and apparatus to recognizing an object based on an attribute of the object and training that may calculate object age information from input data using an attribute layer trained with respect to an attribute of an object and a classification layer trained with respect to a classification of the object. The method to recognize the object includes extracting feature data from input data including an object using an object model, determining attribute classification information related to the input data from the feature data using a classification layer, determining attribute age information related to an attribute from the feature data using an attribute layer, and estimating object age information based on the attribute classification information and the attribute age information.

Abstract: A user authentication method includes receiving a first input image including information on a first modality; receiving a second input image including information on a second modality; determining at least one first score by processing the first input image based on at least one first classifier, the at least one first classifier being based on the first modality; determining at least one second score by processing the second input image based on at least one second classifier, the at least one second classifier being based on the second modality; and authenticating a user based on the at least one first score, the at least one second score, a first fusion parameter of the at least one first classifier, and a second fusion parameter of the at least one second classifier.

Abstract: A neural network recognition method includes obtaining a first neural network that includes layers and a second neural network that includes a layer connected to the first neural network, actuating a processor to compute a first feature map from input data based on a layer of the first neural network, compute a second feature map from the input data based on the layer connected to the first neural network in the second neural network, and generate a recognition result based on the first neural network from an intermediate feature map computed by applying an element-wise operation to the first feature map and the second feature map.

Abstract: A method of segmenting an object from an image includes receiving an input image including an object; generating an output image corresponding to the object from the input image using an image model; and extracting an object image from the output image.

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: 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 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 neural network recognition method includes obtaining a first neural network that includes layers and a second neural network that includes a layer connected to the first neural network, actuating a processor to compute a first feature map from input data based on a layer of the first neural network, compute a second feature map from the input data based on the layer connected to the first neural network in the second neural network, and generate a recognition result based on the first neural network from an intermediate feature map computed by applying an element-wise operation to the first feature map and the second feature map.

Abstract: At least some example embodiments disclose a device and a method for generating a synthetic image and a different-angled image and eliminating noise. The method may include receiving input images, extracting feature values corresponding to the input images using an image learning model, the image learning model permitting an input and an output to be identical and generating a synthetic image based on the feature values corresponding to the input images using the image learning model.

Abstract: Face recognition of a face, to determine whether the face correlates with an enrolled face, may include generating a personalized three-dimensional (3D) face model based on a two-dimensional (2D) input image of the face, acquiring 3D shape information and a normalized 2D input image of the face based on the personalized 3D face model, generating feature information based on the 3D shape information and pixel color values of the normalized 2D input image, and comparing the feature information with feature information associated with the enrolled face. The feature information may include first and second feature information generated based on applying first and second deep neural network models to the pixel color values of the normalized 2D input image and the 3D shape information, respectively. The personalized 3D face model may be generated based on transforming a generic 3D face model based on landmarks detected in the 2D input image.

Abstract: A complex authentication method includes identifying a user based on at least one image of a face image and a fingerprint image; identifying a first pattern associated with at least one of a feature point extracted from the face image and a first input to a display of an electronic device; and performing an operation assigned to the identified user and the identified first pattern.

Abstract: A method and apparatus for recognizing a facial expression is provided. The method of recognizing the facial expression includes extracting a feature from an input image, extracting a feature from a reference image, and recognizing a user facial expression based on a difference between the feature of the input image and the feature of the reference image.