A method of training and using a machine learning model that controls for consideration of undesired factors which might otherwise be considered by the trained model during its subsequent analyses of new data. For example, the model may be a neural network trained on a set of training images to evaluate an insurance applicant based upon an image or audio data of the insurance applicant as part of an underwriting process to determine an appropriate life or health insurance premium. The model is trained to probabilistically correlate an aspect of the applicant's appearance with a personal and/or health-related characteristic. Any undesired factors, such as age, sex, ethnicity, and/or race, are identified for exclusion. The trained model receives the image (e.g., a “selfie”) of the insurance applicant, analyzes the image without considering the identified undesired factors, and suggests the appropriate insurance premium based only on the remaining desired factors.

Methods, systems, and computer program products are described for obtaining, from a first tracking system, an initial three-dimensional (3D) position of an electronic device in relation to image features captured by a camera of the electronic device and obtaining, from a second tracking system, an orientation associated with the electronic device. Responsive to detecting a movement of the electronic device, obtaining, from the second tracking system, an updated orientation associated with the detected movement of the electronic device, generating and providing a query to the first tracking system, the query corresponding to at least a portion of the image features and including the updated orientation and the initial 3D position of the electronic device, generating, for a sampled number of received position changes, an updated 3D position for the electronic device and generating a 6-DoF pose using the updated 3D positions and the updated orientation for the electronic device.

An electronic device and a controlling method thereof are provided. A controlling method of an electronic device according to the disclosure includes: performing first learning for a neural network model for acquiring a video sequence including a talking head of a random user based on a plurality of learning video sequences including talking heads of a plurality of users, performing second learning for fine-tuning the neural network model based on at least one image including a talking head of a first user different from the plurality of users and first landmark information included in the at least one image, and acquiring a first video sequence including the talking head of the first user based on the at least one image and pre-stored second landmark information using the neural network model for which the first learning and the second learning were performed.

Systems and methods for generating a face model for a user of a head-mounted device are disclosed. The head-mounted device can include one or more eye cameras configured to image the face of the user while the user is putting the device on or taking the device off. The images obtained by the eye cameras may be analyzed using a stereoscopic vision technique, a monocular vision technique, or a combination, to generate a face model for the user.

Systems and methods for creating fully custom products from scratch without exclusive use of off-the-shelf or pre-specified components. A system for creating custom products includes an image capture device for capturing image data and/or measurement data of a user. A computer is communicatively coupled with the image capture device and configured to construct an anatomic model of the user based on the captured image data and/or measurement data. The computer provides a configurable product model and enables preview and automatic or user-guided customization of the product model. A display is communicatively coupled with the computer and displays the custom product model superimposed on the anatomic model or image data of the user. The computer is further configured to provide the customized product model to a manufacturer for manufacturing eyewear for the user in accordance with the customized product model. The manufacturing system is configured to interpret the product model and prepare instructions and control equipment for the manufacturing of the customized product.

A system, a method, and a program that easily verify that a certificate with a photograph belongs to a user. The system that verifies that a certificate 1 with a photograph belongs to a user acquires a first image containing the certificate with the photograph of a user, judges the validity of the first image, acquires a second image containing the user and the certificate with a photograph that corresponds to the first image that has validity, judges if the user's face and the photograph of the certificate in the second image match, and certifies that the certificate with a photograph belongs to the user if the face and the photograph of the certificate match.

According to one embodiment, a person authentication method includes obtaining, from a medium carried by a person who passes through a first position, first information indicating the gender and the age of the person; performing a first authentication operation with respect to a person whose face image is included in a first image obtained by capturing a person passing through the first position; and setting, as the first authentication operation, an authentication operation to be performed using the face image of a person having the gender and the age specified in the first information.

A method and system for matching an unknown facial image of an individual with an image of a celebrity using facial recognition techniques and human perception is disclosed herein. The invention provides a internet hosted system to find, compare, contrast and identify similar characteristics among two or more individuals using a digital camera, cellular telephone camera, wireless device for the purpose of returning information regarding similar faces to the user The system features classification of unknown facial images from a variety of internet accessible sources, including mobile phones, wireless camera-enabled devices, images obtained from digital cameras or scanners that are uploaded from PCs, third-party applications and databases. Once classified, the matching person's name, image and associated meta-data is sent back to the user. The method and system uses human perception techniques to weight the feature vectors.

A secure 5-D user identification system using 3-D facial recognition plus micro-expression recognition and head gait analysis, and method for a body-worn sensor to increase security for users and thereby decrease security circumvention for illegitimate reproduction purposes.

Provided are an image candidate determination apparatus that assists which image is to be selected in order to uniformize the number of images including each person in an image to be made public as much as possible, a method thereof, a program thereof, and a recording medium storing the program. In a case where a plurality of images are input, images in which the same person is included are grouped. In a case where there are images of which the number is equal to or larger than a maximum number of images to be made public for the same person (YES in step 61), a total image evaluation value is calculated for the images in which the same person is included (step 62). An image with a small total image evaluation value is determined as a private image candidate so that the number thereof is smaller than the maximum number (step 63).