Method for correction of the eyes image using machine learning and method for machine learning

A computing device, comprising:

• a logic machine;
• and
• a storage machine holding instructions executable by the logic machine to:
• receive a digital input image depicting a human eye;
• generate a gaze-adjusted image from the digital input image by changing an apparent gaze direction of the human eye via a gaze adjustment machine learning model, wherein the gaze adjustment machine learning model comprises a predictor is obtained by:
• obtaining a plurality of learning pairs of images containing in each pair of images views of a same person, the learning pairs of images differing by a gaze direction, and wherein, for the learning pairs of images, the difference in gaze direction in each image in the learning pair is equal;
• determining positions of eyes in each of the learning pair of images;
• and
• determining the predictor for producing adjusting displacement vector fields for each learning pair of images by replacing color components of each pixel of the first image from the pair, with color components of another pixel of the first image of the pair according to a prediction of the predictor, resulting in an image similar to the second image of the pair;
• and output the gaze-adjusted image.