GazeAppraise v. 0.1
- Sandia National Laboratories
GazeAppraise advances the state of the art of gaze pattern analysis using methods that simultaneously analyze spatial and temporal characteristics of gaze patterns. GazeAppraise enables novel research in visual perception and cognition; for example, using shape features as distinguishing elements to assess individual differences in visual search strategy. Given a set of point-to-point gaze sequences, hereafter referred to as scanpaths, the method constructs multiple descriptive features for each scanpath. Once the scanpath features have been calculated, they are used to form a multidimensional vector representing each scanpath and cluster analysis is performed on the set of vectors from all scanpaths. An additional benefit of this method is the identification of causal or correlated characteristics of the stimuli, subjects, and visual task through statistical analysis of descriptive metadata distributions within and across clusters.
- Short Name / Acronym:
- GazeAppraise; 005030WKSTN00
- Site Accession Number:
- SCR #2104
- Version:
- 00
- Programming Language(s):
- Medium: X; OS: Windows 7, RedHat Linux Enterprise
- Research Organization:
- Sandia National Lab. (SNL-NM), Albuquerque, NM (United States)
- Sponsoring Organization:
- USDOE
- DOE Contract Number:
- AC04-94AL85000
- OSTI ID:
- 1331978
- Country of Origin:
- United States
Similar Records
Analysis and categorization of eye tracking data describing scanpaths
Investigating the Link Between Radiologists Gaze, Diagnostic Decision, and Image Content