HPCGen: Hierarchical K-Means Clustering and Level Based Principal Components for Scan Path Genaration

TL;DR

This paper introduces HPCGen, a hierarchical clustering and principal component approach for generating realistic scan paths that mimic human gaze behavior, useful for data augmentation and analysis.

Contribution

The paper proposes a novel hierarchical K-Means clustering combined with level-based principal components for scan path generation, enhancing realism and utility.

Findings

Generated scan paths closely resemble human gaze patterns

The method improves scan path classification accuracy

It can produce realistic fake scan paths for testing

Abstract

In this paper, we present a new approach for decomposing scan paths and its utility for generating new scan paths. For this purpose, we use the K-Means clustering procedure to the raw gaze data and subsequently iteratively to find more clusters in the found clusters. The found clusters are grouped for each level in the hierarchy, and the most important principal components are computed from the data contained in them. Using this tree hierarchy and the principal components, new scan paths can be generated that match the human behavior of the original data. We show that this generated data is very useful for generating new data for scan path classification but can also be used to generate fake scan paths.