Blink Technologies, Inc.

Almog David

Gilad Drozdov

Tsahi Mizrahi

Oren Haimovitch-Yogev

Artyom Borzin

Andrey Zhitnikov

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

Methods, systems, and storage media for projecting a viewer-specific 3D object perspectives from a single 3D display are disclosed. Implementations may: acquire face and eye region image data of a plurality of viewers within a field of view of at least one camera associated with a 3D-enabled digital display; analyze the eye region image data to determine at least one 3D eye position, at least one eye state, at least one gaze angle, and at least one point-of-regard for a viewer relative to at least one camera associated with the 3D-enabled digital display; and calculate a plurality of processed image projections for display by the single 3D display. The digital-processing of input image projection enables a separate optical input to the user's eyes, and by the use of visual-acuity pre-processing of the image—via visual-field kernel, enables the treatment of eye abbreviations, including an Amblyopic-eye without the need for any additional eye-ware, or head-up-displays (HMD's).

System and method for the diagnosis and treatment of amblyopia using a 3D display

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 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

Kiryat Motzkin, Israel

Almog David