Abstract: This application provides a face living body detection method performed by a computing device, the method including: obtaining a first face image of a target detection object in a first illumination condition and a second face image of the target detection object in a second illumination condition, determining a difference image according to the two images, decoupling an object reflectivity and an object normal vector corresponding to the target detection object from a feature map extracted from the difference image, and determining whether the target detection object is a living body according to the object reflectivity and the object normal vector. This method decouples texture information and depth information of a face, and performs living body detection by using decoupled information, which increases the defense capability against 3D attacks, thereby effectively defending against planar attacks and 3D attacks.

Abstract: A face liveness detection method is performed by an electronic device. The method includes: obtaining an initial face image of an object and a face image set of the object captured at N different illumination directions; obtaining N difference images according to the initial face image and the N face images in the face image set; generating a normal map and an albedo map according to the N difference images and the N illumination directions; and determining a face liveness detection result according to the N difference images, the normal map, and the albedo map, the face liveness detection result indicating whether the object has a live face or not. In this application, three-dimensional (3D) geometric information and surface material information of a face image are considered, thereby recognizing the authenticity of the face image, and effectively resisting different face liveness attack manners.

Abstract: An image authenticity detection method includes: obtaining a target image; inputting the target image into a generator of a generative adversarial network, and outputting an artifact image corresponding to the target image through the generator, where the artifact image is used for representing a difference between the target image and a real image; the generator is configured to output a prediction artifact image corresponding to a sample image and generate a fitting image based on the prediction artifact image; and the generative adversarial network further comprises a discriminator in a training stage, and the discriminator is configured to discriminate the authenticity of the fitting image, to assist the generator to learn a difference feature between a false image and a real image; and determining an authenticity detection result of the target image based on the artifact image.

Abstract: A method and apparatus for extracting biological features, a device, a medium, and a program product, relating to the field of image processing. The method includes generating an image sequence according to a biological feature image, the image sequence including the biological feature image and n local image blocks, the local image blocks being obtained by segmenting the biological feature image, n being a positive integer, generating a feature vector group based on the image sequence, feature vectors in the feature vector group being generated based on a feature information interaction result between the biological feature image and the local image blocks and a feature information interaction result between the local image blocks, and taking a feature vector corresponding to the biological feature image in the feature vector group as biological feature information of the biological feature image.

Abstract: An image processing method, including: obtaining an original image, the original image including biological features of a to-be-detected object, fusing a global frequency domain map corresponding to the original image with the original image to obtain a global fusion image, performing living body detection on the global fusion image to obtain a first detection result, determining that the original image does not pass the living body detection when the first detection result indicates that the original image belongs to a screen reproduced image, obtaining, when the original image does not belong to the screen reproduced image, a biological feature image based on the biological features, fusing a local frequency domain map with the biological feature image to obtain a local fusion image, performing living body detection on the local fusion image to obtain a second detection result, and determining a living body detection result corresponding to the original image.

Abstract: A liveness detection method is provided. In the method, image features are extracted from an image of a user. Convolution processing is performed on the image features through an estimation network to obtain a predicted mean value and a predicted variance of the image features. Standardization processing is performed on the image features based on the predicted mean value, the predicted variance, and predetermined network parameters of the standardization processing to obtain standardized features. Whether the image of the user includes a living body image is determined according to a liveness classification probability of a classification performed on the image of the user based on the standardized features. Apparatus and non-transitory computer-readable storage medium counterpart embodiments are also contemplated.

Abstract: An image detection method includes obtaining a facial image, and obtaining a frequency-domain image of the facial image and a spatial-domain feature of the facial image, the frequency-domain image being obtained by performing frequency-domain transformation on the facial image. The spatial-domain feature is obtained by performing feature extraction on the facial image. The method further includes performing feature extraction based on the frequency-domain image, to obtain a frequency-domain feature of the facial image, and fusing the spatial-domain feature and the frequency-domain feature by using an attention fusion network of a facial image detection model, to obtain a fused feature of the facial image. The method further includes obtaining a detection result of the facial image based on the fused feature, the detection result indicating whether the facial image is a forged facial image.

Abstract: A face liveness detection method is performed by an electronic device. The method includes: obtaining an initial face image of an object and a face image set of the object captured at N different illumination directions; obtaining N difference images according to the initial face image and the N face images in the face image set; generating a normal map and an albedo map according to the N difference images and the N illumination directions; and determining a face liveness detection result according to the N difference images, the normal map, and the albedo map, the face liveness detection result indicating whether the object has a live face or not. In this application, three-dimensional (3D) geometric information and surface material information of a face image are considered, thereby recognizing the authenticity of the face image, and effectively resisting different face liveness attack manners.

Abstract: This application provides a face living body detection method performed by a computing device, the method including: obtaining a first face image of a target detection object in a first illumination condition and a second face image of the target detection object in a second illumination condition, determining a difference image according to the two images, decoupling an object reflectivity and an object normal vector corresponding to the target detection object from a feature map extracted from the difference image, and determining whether the target detection object is a living body according to the object reflectivity and the object normal vector. This method decouples texture information and depth information of a face, and performs living body detection by using decoupled information, which increases the defense capability against 3D attacks, thereby effectively defending against planar attacks and 3D attacks.