Abstract: A face verification method and apparatus is disclosed. The face verification method includes selecting a current verification mode, from among plural verification modes, to be implemented for the verifying of the face, determining one or more recognizers, from among plural recognizers, based on the selected current verification mode, extracting feature information from information of the face using at least one of the determined one or more recognizers, and indicating whether a verification is successful based on the extracted feature information.

Abstract: Disclosed is a convolutional neural network (CNN) processing apparatus and method, the apparatus configured to determine a loading space unit for at least one loading space in an input based on a height or a width for an input feature map of the input and an extent of a dimension of a kernel feature map, load target input elements corresponding to a target loading space, among the at least one loading space, from a memory and store the target input elements in an allocated input buffer having a size corresponding to the loading space unit, and perform a convolution operation between the target input elements stored in the input buffer and at least one kernel element of a kernel.

Abstract: A gaze estimation method includes receiving, by a processor, input data including a current image and a previous image each including a face of a user, determining, by the processor, a gaze mode indicating a relative movement between the user and a camera that captured the current image and the previous image based on the input data, and estimating, by the processor, a gaze of the user based on the determined gaze mode, wherein the determined gaze mode is one of a plurality of gaze modes comprising a stationary mode and a motion mode.

Abstract: A convolutional neural network (CNN) processing method and apparatus. The apparatus may select, based on at least one of a characteristic of at least one kernel of a convolution layer or a characteristic of an input of the convolution layer, one operation mode from a first operation mode reusing a kernel, of the at least one kernel, and a second operation mode reusing the input, and perform a convolution operation based on the selected operation mode.

Abstract: A method and apparatus with an adaptively updated enrollment database (DB) are provided. A method with an adaptively updated enrollment database (DB) includes extracting an input feature vector from an input image, determining whether the input feature vector is included in a changeable enrollment range, with the changeable enrollment range being determined based on a threshold distance from each of plural enrolled feature vectors in the enrollment DB, and with the enrolled feature vectors corresponding to enrolled images, determining whether to enroll the input feature vector in the enrollment DB in response to the input feature vector being determined as being included in the changeable enrollment range, and in response to a result of the determining of whether to enroll the input feature vector being to enroll the input feature vector, selectively enrolling the input feature vector in the enrollment DB.

Abstract: Disclosed is an image fusion method and apparatus. The fusion method includes detecting first feature points of an object in a first image frame from the first image frame; transforming the first image frame based on the detected first feature points and predefined reference points to generate a transformed first image frame; detecting second feature points of the object in a second image frame from the second image frame; transforming the second image frame based on the detected second feature points and the predefined reference points to generate a transformed second image frame; and generating a combined image by combining the transformed first image frame and the transformed second image frame.

Abstract: An object recognition apparatus and method are provided. The apparatus includes a processor configured to verify a target image using an object model and based on reference intermediate data extracted by a partial layer of the object model as used in an object recognition of an input image, in response to a failure of a verification of the input image after a success of the object recognition of the input image, and perform an additional verification of the target image in response to the target image being verified in the verifying of the target image.

Abstract: A processor-implemented verification method includes: detecting a characteristic of an input image; acquiring input feature transformation data and enrolled feature transformation data by respectively transforming input feature data and enrolled feature data based on the detected characteristic, wherein the input feature data is extracted from the input image using a feature extraction model; and verifying a user corresponding to the input image based on a result of comparison between the input feature transformation data and the enrolled feature transformation data.

Abstract: A data recognition method includes: extracting a feature map from input data based on a feature extraction layer of a data recognition model; pooling component vectors from the feature map based on a pooling layer of the data recognition model; and generating an embedding vector by recombining the component vectors based on a combination layer of the data recognition model.

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: An apparatus for training an image generative model and an image generating apparatus are provided. The apparatus generates output images from a plurality of input images based on the generative model, extracts depth features from the respective output images based on a depth classification model, calculates a depth loss from the extracted depth features, and trains the generative model based on an overall loss that includes the calculated depth loss.

Abstract: A gaze tracking method and apparatus, and a gaze tracking neural network training method and apparatus are provided. The gaze tracking apparatus includes one or more processors and a memory, and the one or more processors obtain output position information from an input face image of a user using a neural network model, determines a position adjustment parameter for the user, and predicts gaze position information of the user by adjusting the output position information based on the position adjustment parameter.

Abstract: A device and substrate are disclosed. An illustrative device includes a substrate having a first surface and an opposing second surface, a solder material receiving curved surface exposed at the second surface of the substrate, a solder resist material that at least partially covers the solder material receiving curved surface such that a middle portion of the solder receiving curved surface is exposed and such that an edge portion of the solder material receiving curved surface is covered by the solder resist material and forms an undercut, and a solder material disposed within the solder material receiving curved surface and within the undercut.

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: An apparatus and method for detecting a fake fingerprint is disclosed. The apparatus may divide an input fingerprint image into blocks, determine an image quality assessment (IQA) value associated with each block, determine a confidence value based on the IQA values using a confidence determination model, and determine whether an input fingerprint in the input fingerprint image is a fake fingerprint based on the determined confidence value.

Abstract: A three-dimensional (3D) image-based facial verification method and apparatus is provided. The facial verification method may include capturing a facial image of a 3D face of a user, determining an occluded region in the captured facial image by comparing the captured facial image and an average facial image, generating a synthetic image by synthesizing the captured facial image and the average facial image based on the occluded region, and verifying the user based on the synthetic image.

Abstract: A device and substrate are disclosed. An illustrative device includes a substrate having a first surface and an opposing second surface, a solder material receiving curved surface exposed at the second surface of the substrate, a solder resist material that at least partially covers the solder material receiving curved surface such that a middle portion of the solder receiving curved surface is exposed and such that an edge portion of the solder material receiving curved surface is covered by the solder resist material and forms an undercut, and a solder material disposed within the solder material receiving curved surface and within the undercut.

Abstract: A buffer circuit configured to receive first and second input signals through first and second input transistors coupled to a first power voltage node, output a first output signal through a first output node and a second output signal through a second output node based on the first and second input signals. A load circuit is coupled among the first output node, the second output node, and a second power voltage node and a resistance value is adjusted based on at least one of the first and second output signals.

Abstract: A buffer circuit configured to receive first and second input signals through first and second input transistors coupled to a first power voltage node, output a first output signal through a first output node and a second output signal through a second output node based on the first and second input signals. A load circuit is coupled among the first output node, the second output node, and a second power voltage node and a resistance value is adjusted based on at least one of the first and second output signals.

Abstract: A method and apparatus for processing an image based on partial images. The method includes extracting a feature of a current partial processing region of an input image frame by inputting pixel data of the current partial processing region into a convolutional neural network (CNN), updating a hidden state of a recurrent neural network (RNN) for a context between the current partial processing region and at least one previous partial processing region by inputting the extracted feature into the RNN, and generating an image processing result for the input image frame based on the updated hidden state.