Method and system for correlating an image capturing device to a human user for analysis of cognitive performance
Inventors
BOTT, Nick • LANGE, Alexander R. • COSGRIFF, Rob • HSIAO, Roger • DOLIN, Brad
Assignees
Interested in licensing this patent?
MTEC can help explore whether this patent might be available for licensing for your application.
Publication Number
US-10517520-B2
Publication Date
2019-12-31
Expiration Date
Abstract
A method capturing eye movement data for detection of cognitive anomalies, includes a computer application displaying a frame on a display, capturing and displaying a video image of a user's face and eyes, while the user aligns the face to the frame, capturing and processing the face image to initiate an image eye movement capture process, outputting an indication on a display and moving the indication spatially to one of a plurality of images, capturing a video of each user eye, to track the position of the indication of the display, the image of each eye comprising a sclera portion, an iris portion, and a pupil portion, parsing the video to determine a reference images corresponding to eye positions, capturing the user's eyes while the user views familiar and novel images, and correlating the images of the user's eyes to the familiar or novel images using the reference images.
Core Innovation
The invention provides a web-based image capturing device and processor-controlled application for eye tracking to detect cognitive anomalies. An application outputs an image of a frame on a display device to a user and initiates a camera to capture video image of a head of the user positioned by viewing the display. The video of the head is displayed within a vicinity of the frame being displayed, and the user positions the head within the frame to align the head and capture an image of the head.
The processor processes captured information regarding the image of the head to initiate an image capturing process of eye movement. The system outputs an indication on the display, moves the indication spatially to one of a plurality of images, and captures a video of each eye while the head is maintained at an approximately stationary spatial position relative to the camera. Each eye image comprises a sclera portion, an iris portion, and a pupil portion.
The captured eye video is parsed to determine a first reference image corresponding to a first eye position for a first spatial position and a second reference image corresponding to a second eye position for a second spatial position. The system correlates each of the other plurality of images to either the first reference image or the second reference image. The disclosed approach supports producing a cognitive performance score by correlating eye movement data with known reference images associated with familiar and novel stimuli.
The disclosed system supports calibration or analysis being performed locally on a user computing device or remotely on a server device. It includes using parsed reference images for different eye positions and correlating subsequent eye images to known reference images, with a web-based interface enabling convenient remote administration. The document further describes generating a gaze model using principal component analysis and eigenvectors and using preference for novel over familiar images for scoring.
Claims Coverage
One independent claim is provided. It contains multiple inventive elements spanning user alignment to a displayed frame, capture of eye video with sclera/iris/pupil portions, spatial indication tracking, parsing to generate reference images per eye position, and correlating captured eye images to those reference images to detect cognitive anomalies.
Displaying a frame and capturing head video for user alignment
initiating an application, under control of a processor, to output an image of a frame on a display device to a user; initiating a camera to capture a video image of a head of a user, the head being positioned by the user viewing the display device; displaying the video of the head within a vicinity of the frame, positioning the head within the frame, and capturing an image of the head
Spatial indication and eye video capture with stationary head
outputting an indication on a display after initiation of the image capturing process; moving the indication spatially to one of a plurality of images being displayed; capturing a video of each eye while the head is maintained at an approximately stationary spatial position relative to the camera, each eye image comprising a sclera portion, an iris portion, and a pupil portion
Parsing video into reference images by eye position and correlating images
parsing the video to determine a first reference image corresponding to a first eye position for a first spatial position for the indication and a second reference image corresponding to a second eye position for a second spatial position of the indication; correlating each of the other plurality of images to either the first reference image or the second reference image
The independent claim centers on aligning a user's head to a displayed frame, capturing video of both eyes with sclera/iris/pupil portions while an on-screen indication moves, parsing the video to create reference images for different eye positions, and correlating subsequent eye images to the reference images to detect cognitive anomalies.
Stated Advantages
Convenient remote administration is described.
Documented Applications
Web-based eye-tracking for cognitive assessment to detect cognitive anomalies and support cognitive performance scoring based on correlation to reference images.
Remote administration using local user computing device processing or remote server device processing is described.
Interested in licensing this patent?