Blink Technologies, Inc.

Tsahi Mizrahi

Gilad Drozdov

Oren Haimovitch-Yogev

Almog David

Artyom Borzin

Andrey Zhitnikov

Uri Wollner

Nadav Arbel

Soliman Nasser

A computer implemented method and system for fitting eyeglasses captures images of the consumer while naturally trying-on frames in the normal course of selecting new frames. The system and method capture natural images of frame placement and using gaze prediction and eye tracking techniques ascertain eye measurements for accurate placement of the prescription within new eyewear.

System and method for fitting eye wear

Unsupervised, deep learning of eye-landmarks in a user-specific eyes' image data by capturing an unlabeled image comprising an eye region of a user, using an initial geometrically regularized loss function, training a plurality of convolutional autoencoders on the unlabeled image comprising the eye region of the user to recover a plurality of user-specific eye landmarks, training a convolutional neural network for autoencoded landmarks-based recovery from the unlabeled image, and where the initial geometrically regularized loss function is represented by the formula L=λL+λL+λL+λLwhere Lis total AutoEncoder Loss, λLis λ-weighted reconstruction loss, λLis λ-weighted concentration loss, λLis λ-weighted separation loss, and λLis λ-weighted equivalence loss.

Geometrically constrained, unsupervised training of convolutional autoencoders for extraction of eye landmarks

The disclosure relates to systems, methods and programs for developing real-time user-specific eye model based on iris localization using solely pupil-ellipse analysis.

Pupil ellipse-based, real-time iris localization

The disclosure relates to systems, methods and programs for geometrically constrained, unsupervised training of convolutional autoencoders on unlabeled images for extracting eye landmarks. Disclosed systems for unsupervised deep learning of gaze estimation in eyes' image data are implementable in a computerized system. Disclosed methods include capturing an unlabeled image comprising the eye region of a user; and training a plurality of convolutional autoencoders on the unlabeled image comprising the eye region of a user using an initial geometrically regularized loss function to determine a plurality of eye landmarks.

Growing community of inventors

Yoqneam Ilit, Israel

Tsahi Mizrahi