PUBLIC MARKS from decembre with tags logiciel & face

Avec leur technologie vidéo, des chercheurs peuvent recréer n'importe quelle expression, à la perfection. (CCM) — En avant-première de la conférence SIGGRAPH (lien en anglais), des chercheurs ont publié un extrait vidéo bluffant. Il montre à quel point les fausses vidéos peuvent être confondues avec les vraies. En transformant les expressions et mouvements du visage d'une personnalité, un deepfake devient indétectable ou presque. En principe, ces fausses vidéos utilisent les expressions d'un acteur anonyme, et les greffent sur le visage d'une personnalité. Autre option : placer un visage modifié sur un autre corps et dans une autre situation qu'à l'origine. Avec leur technologie Deep Video Portraits, les chercheurs ont utilisé un système complexe de superposition des expressions. Ils y ont ajouté un ré-encodage et de l'apprentissage machine. Le résultat est spectaculaire.

Overview: The following overview shows the workflow for a single input image of Sylvestor Stallone from the publicly available LFW dataset. Detect faces with a pre-trained models from dlib or OpenCV. Transform the face for the neural network. This repository uses dlib's real-time pose estimation with OpenCV's affine transformation to try to make the eyes and bottom lip appear in the same location on each image. Use a deep neural network to represent (or embed) the face on a 128-dimensional unit hypersphere. The embedding is a generic representation for anybody's face. Unlike other face representations, this embedding has the nice property that a larger distance between two face embeddings means that the faces are likely not of the same person. This property makes clustering, similarity detection, and classification tasks easier than other face recognition techniques where the Euclidean distance between features is not meaningful. Apply your favorite clustering or classification techniques to the features to complete your recognition task. See below for our examples for classification and similarity detection, including an online web demo.

A Dataset With Over 100,000 Face Images of 530 People. Large face datasets are important for advancing face recognition research, but they are tedious to build, because a lot of work has to go into cleaning the huge amount of raw data. To facilitate this task, we developed an approach to building face datasets that detects faces in images returned from searches for public figures on the Internet, followed by automatically discarding those not belonging to each queried person. The FaceScrub dataset was created using this approach, followed by manually checking and cleaning the results. It comprises a total of 106,863 face images* of male and female 530 celebrities, with about 200 images per person. As such, it is one of the largest public face databases. The images were retrieved from the Internet and are taken under real-world situations (uncontrolled conditions). Name and gender annotations of the faces are included.

Ils ont mis au point un logiciel détectant la présence de visages dans une image au format numérique. Applications possibles dans les domaines de la biométrie, de la vidéo-conférence ou des systèmes de surveillance.Pas affilé à Google