Detection of whether a video is a fake video derived from an original video and altered is undertaken using both image analysis and frequency domain analysis of one or more frames of the video. The analysis may be implemented using neural networks.

Photochromic formulations including a core material and a photochromic layer overlying the core material and forming a particle are provided. The photochromic layer may include a plurality of photochromic materials, including a first photo-responsive pigment characterized by reversible diffuse reflectance at a first central wavelength from 490 nm to 520 nm in response to irradiation by photons of a first characteristic wavelength, a second photo-responsive pigment characterized by reversible diffuse reflectance at a second central wavelength from 570 nm to 590 nm in response to irradiation by photons of a second characteristic wavelength, and a third photo-responsive pigment characterized by reversible diffuse reflectance at a third central wavelength from 450 nm to 495 nm and a fourth central wavelength from 625 nm to 740 nm in response to irradiation by photons of a third characteristic wavelength. The first, second, and third characteristic wavelengths may be different.

A facial recognition method using online sparse learning includes initializing target position and scale, extracting positive and negative samples, and extracting high-dimensional Haar-like features. A sparse coding function can be used to determine sparse Haar-like features and form a sparse feature matrix, and the sparse feature matrix in turn is used to classify targets.

An image processing method and apparatus, a computer device, and a computer-readable storage medium. The image processing method includes: displaying a first application page, the first application page including an original role object and a face fusion control; acquiring a user face image of a target user in a case that the face fusion control is triggered; and displaying a target role object on a second application page, the target role object being obtained by fusing the user face image and the original role object, a display angle of the target role object matching posture information of the target user, and the posture information of the target user being determined according to the user face image.

Techniques are described for passive three-dimensional (3D) object authentication based on image sizing, such as for biometric facial recognition. For example, during a registration routine, an imaging system captures images of a registering user's face at multiple distances. The images can be processed to extract registration dimensions, including individual deterministic structural dimensions, dimensional relationships that are static over changes in imaging distance, and dimensional relationships that changes predictably over changes in imaging distance. During an authentication routine, the imaging system again captures authentication images of an authenticating user's face (purportedly the previously registered user) at some authentication imaging distance and processes the images to extract authentication dimensions. Expected and actual dimensional quantities are computed from the authentication and registration dimensions and are compared to determine whether the authenticating user's face appears to be authorized as previously registered and/or is a spoof.

A method of adaptively updating an enrollment database is disclosed. The method may include extracting a first feature vector from an input image, the input image including a face of a user, determining whether to enroll the input image in the enrollment database based on the first feature vector, second feature vectors of enrollment images and a representative vector, the second feature vectors of the enrollment images being enrolled in the enrollment database, and the representative vector representing the second feature vectors, and enrolling the input image in the enrollment database based on a result of the determining.

A system and method of landmark detection using deep neural network with multi-frequency self-attention is provided. The system includes an encoder network that receives an image of an object of interest as an input and generates multi-frequency feature maps as output. The system further includes an attention layer that receives the generated multi-frequency feature maps and refines the generated multi-frequency feature maps based on correlations or associations between the received multi-frequency feature maps. The system further includes a decoder network that receives the refined multi-frequency feature maps as a second input from the attention layer and generates a landmark detection result based on the second input. The landmark detection result includes a heatmap image of the object of interest and the heatmap image indicates locations of landmark points on the object of interest in the image.

A computer-implemented method for correcting data to match user identity may include (i) receiving user input specifying an aspect of physical presentation of the user that does not match an authentic identity of the user, where the authentic identity of the user includes a realistic version of the user that reflects an internal self-image of the user, (ii) capturing, via a sensor, data of the user that includes the aspect of the physical presentation of the user, (iii) correcting the captured data of the user to portray a corrected version of the aspect that matches the authentic identity of the user, and (iv) storing the corrected data of the user that matches the authentic identity of the user instead of uncorrected data of the user that includes the aspect that does not match the authentic identity of the user. Various other methods, systems, and computer-readable media are also disclosed.

A label assigning device of an embodiment includes one or more hardware processors configured to function as a label candidate generation unit, a feature amount pair detection unit, and a label assigning unit. The label candidate generation unit generates a label candidate from association data associated with a content. The feature amount pair detection unit detects a feature amount pair that is a combination of feature amounts having a highest similarity among combinations of a feature amount extracted from a first content and a feature amount extracted from a second content. The label assigning unit assigns, as a label, a common label candidate generated from both first association data associated with the first content and second association data associated with the second content to each feature amount constituting the feature amount pair.

A training method for an image fusion processing model is provided. The method includes: obtaining an image set, and compressing the image set, updating a parameter of an encoder of a single image processing model and a parameter of a decoder of the single image processing model according to a single to-be-replaced face in the original image set, and updating parameters of an encoder and a decoder that are of the image fusion processing model according to different to-be-replaced faces and different target faces that are in the original image set while the parameters of the encoder and the decoder that are of the single image processing model remain unchanged. An image processing method and apparatus for an image fusion processing model, an electronic device, and a storage medium are further provided.