Method for inferring mental states from eye movements

• US 6,102,870 A
• Filed: 05/03/1999
• Issued: 08/15/2000
• Est. Priority Date: 10/16/1997
• Status: Expired

• Current Assignee: Board of Trustees of the Leland Stanford Junior University (Stanford University)
• Original Assignee: Board of Trustees of the Leland Stanford Junior University (Stanford University)
• Inventors: Edwards, Gregory T.
• Primary Examiner(s): MANUEL, GEORGE C
• Application Number:
  US09/304,542
• Time in Patent Office: 470 Days
• Field of Search: 600/544, 600/545, 600/558, 128/925, 128/898, 340/575, 434/258, 434/259
• US Class Current: 600/558
• CPC Class Codes: A61B 3/113 for determining or recording eye movement
• CPC Class Codes: A61B 5/16 Devices for psychotechnics using teaching or educational appliances G09B1/00 - G09B7/00; Testing reaction times ; Devices for evaluating the psychological state
• CPC Class Codes: A61B 5/163 by tracking eye movement, gaze, or pupil change

Abstract

A computer-implemented method infers mental states of a person from eye movements of the person. The method includes identifying elementary features of eye tracker data, such as fixations and saccades, and recognizing from the elementary features a plurality of eye-movement patterns. Each eye-movement pattern is recognized by comparing the elementary features with a predetermined eye-movement pattern template. A given eye-movement pattern is recognized if the elementary features satisfy a set of criteria associated with the template for that eye-movement pattern. The method further includes the step of recognizing from the eye-movement patterns a plurality of eye-behavior patterns corresponding to the mental states of the person. Because high level mental states of the user are determined in real time, the method provides the basis for reliably determining when a user intends to select a target.

Claims

1. A computer implemented method for inferring mental states of a person from eye movements of the person in real time, the method comprising:

a) identifying a plurality of elementary features of eye tracker data for the person;

b) computing from the elementary features a plurality of eye movement patterns, wherein each pattern satisfies a set of predetermined eye movement pattern template criteria, wherein computing eye movement patterns is performed without requiring any a priori knowledge of contents of the person'"'"'s visual field; and

c) computing from the eye movement patterns a plurality of eye-behavior patterns corresponding to mental states of the person.

2. The method of claim 1 further comprising classifying the elementary features according to associated eye-behavior patterns.

3. The method of claim 2 wherein computing the eye movement patterns comprises computing a significant fixation when a current fixation duration is longer than a significant threshold for a current eye-behavior, where the threshold is calculated from recent fixation duration times classified by the current eye-behavior.

4. The method of claim 1 further comprising computing high level features from the elementary features.

5. The method of claim 1 wherein the plurality of eye behavior patterns comprises at least three eye behavior patterns.

6. The method of claim 5 wherein the eye behavior patterns comprise a pattern selected from the group consisting of reading patterns, spacing out patterns, and searching patterns.

7. The method of claim 1 wherein computing eye movement patterns is performed without requiring knowledge of specific types of objects being displayed in the person'"'"'s visual field.

8. The method of claim 1 being documented in a machine-readable code and being stored on a computer storage device.

9. A computer implemented method for inferring mental states of a person from eye movements of the person in real time, the method comprising:

a) identifying a plurality of elementary features of eye tracker data for the person;

b) computing from the elementary features a plurality of eye movement patterns, wherein each pattern comprises a temporally ordered sequence of fixations and saccades satisfying a set of predetermined eye movement pattern template criteria; and

c) computing from the eye movement patterns a plurality of eye-behavior patterns corresponding to mental states of the person.

10. The method of claim 9 further comprising classifying the elementary features according to associated eye-behavior patterns.

11. The method of claim 10 wherein computing the eye movement patterns comprises computing a significant fixation when a current fixation duration is longer than a significant fixation threshold for a current eye-behavior, where the threshold is calculated from recent fixation duration times classified by the current eye-behavior.

12. The method of claim 9 further comprising computing high level features from the elementary features.

13. The method of claim 9 wherein the plurality of eye behavior patterns comprises at least three eye behavior patterns.

14. The method of claim 13 wherein the eye behavior patterns comprise a pattern selected from the group consisting of reading patterns, spacing out patterns, and searching patterns.

15. The method of claim 9 wherein computing the eye behavior patterns comprises identifying a sequence of short saccades to the right.

16. The method of claim 9 being documented in a machine-readable code and being stored on a computer storage device.

17. A computer implemented method for inferring from eye movements of a person that the person is reading, the method comprising:

a) identifying elementary features of eye tracker data for the person;

b) computing from the elementary features a hierarchy of patterns on various interpretive levels, wherein computed patterns on higher levels are derived from computed patterns on lower levels, wherein highest level computed patterns comprise a reading pattern corresponding to a reading state of the person.

18. The method of claim 17 wherein computing patterns on various interpretive levels comprises identifying a sequence of short saccades to the right.

19. The method of claim 17 wherein computing patterns on various interpretive levels comprises identifying a plurality of sequences of short saccades to the right, wherein the plurality of sequences are approximately vertically aligned with each other.

20. The method of claim 17 wherein computing patterns on various interpretive levels and computing highest level patterns is accomplished without requiring any a priori knowledge of the person'"'"'s visual field.

21. The method of claim 17 being documented in a machine-readable code and being stored on a computer storage device.