Method and system for correlating an image capturing device to a human user for analyzing gaze information associated with cognitive performance

A method for identifying a feature of an eye of a human user, the method comprising:

• initiating an image capturing device under control of a processing device, the image capturing device comprising a plurality of sensors arranged in an array;
• capturing video information from a facial region of the human user using the image capturing device, the video information being a stream of video comprising a plurality of frames;
• processing the video information using an image processing device, to parse the video information into the plurality of images, each of the plurality of images having a time stamp from a first time stamp, a second time stamp, to an Nth time stamp, where N is greater than 10;
• processing each of images using the image processing device to identify a location of the facial region;
• processing each of the images with the location of the facial region to identify a plurality of landmarks associated with the facial region;
• processing each of the images with the location of the facial regions and the plurality of landmarks to isolation a region including each of the eyes;
• processing each of the regions, frame by frame, using the image processing device, to identify a pupil region for each of the eyes, the processing comprising at least:
• processing the region using a grayscale conversion to output a grayscale image;
• processing the grayscale image using an equalization process to output an equalized image;
• processing the equalized image using a thresholding process to output a thresholded image;
• processing the thresholded image using a dilation and erosion process to output a dilated and eroded image;
• and processing the dilated and eroded image using a contour and moment process to output a finalized processed image;
• processing the finalized processed image to identify a spatial location of each pupil in the region, each pupil being identified by a two-dimensional spatial coordinate;
• processing information associated with each pupil identified by the two d-dimensional spatial coordinate to output a plurality of two-dimensional spatial coordinates, each of which is in reference to a time, in a two-dimensional space;
• and
• outputting a gaze information about the human user.