GANT: Gaze analysis technique for human identification

Cantoni, Virginio; Galdi, Chiara; Nappi, Michele; Porta, Marco; Riccio, Daniel

doi:10.1016/j.patcog.2014.02.017

Cited by 91 publications

(56 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…More recently research has been done on the use of eye movement dynamics for biometric authentication [5,19,25,26]. Eye movement dynamics are similar to mouse dynamics except they track eye movement on a screen rather than the mouse.…”

Section: Eye Trackingmentioning

confidence: 99%

Biometric Authentication Using Mouseand Eye Movement Data

Rose

Liu

Awad

2017

JCSM

View full text Add to dashboard Cite

Previous biometric systems have attempted to identify users solely by eye or mouse data. In this paper, we seek to find out if combining both kinds of data produces better results. In our system, mouse movement and eye movement data are gathered from each user simultaneously, a set of salient features are proposed, and a Neural Network classifier is trained on this data to uniquely identify users. After going through this process and investigating several Neural Network based classification models we conclude that combining the modalities results in a more accurate authentication decision and will become practical once the hardware is more widespread.

show abstract

Section: Eye Trackingmentioning

confidence: 99%

Biometric Authentication Using Mouseand Eye Movement Data

Rose

Liu

Awad

2017

JCSM

View full text Add to dashboard Cite

show abstract

“…In [7] and [16] is analyzed the gaze activity during the observation of face images. The studies are based on ad-hoc gaze tracking hardware such as Tobii 1750 remote eye tracker that integrates in a 17" LCD monitor the camera and infrared lighting to scan the eye movements or Dual Purkinje CRS Eye Tracker (Cambridge Research System).…”

Section: Related Workmentioning

confidence: 99%

“…In [16] the gaze movements is processed through the search of a Minimum Spanning Tree and discrimination through the Wald-Wofowitz random tests. In [7] a graph for each user is built considering the fixation point trajectories and the distance, among the relative adjacency matrices, are evaluated through the Frobenious norm.…”

Section: Related Workmentioning

confidence: 99%

“…The Intra-Cluster Entropy is defined as: (7) where N C is the number of clusters, N L is the number of labels, u ij is the number of times the i-th label is present in the j -th cluster and T j is the number of samples in the j -th cluster. This index gives a measure of the entropy inside the clusters.…”

Section: Entropy Based Clustering Measurementioning

confidence: 99%

“…The hypothesis is that these values are discriminative enough to identify who is in front of the computer screen and it is possible to classificate the gaze fixation sequences. Other authors (such as [7,9,16,18,20]) adopt the same hypothesis and their contribution are analyzed in the Section 2. The detected values are represented as a vector of values corresponding to a moving window that updates the values with the most recent observation discarding the oldest one.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Person identification through entropy oriented mean shift clustering of human gaze patterns

Vella

Infantino

Scardino

2016

Multimed Tools Appl

View full text Add to dashboard Cite

The paper describes a system aimed at improving the human machine interaction that is able to identify users according how she looks at the monitor. The proposed system does not need invasive measurements that could limit the naturalness of her actions. The approach, here described, detects the gaze movements on the monitor and clusters the sequences of user gaze fixation points on the screen characterizing the user according the particular patterns her gaze follows. The recognition of the user is performed through a clustering process employing the Mean-Shift algorithm and it can open new perspective in human-machine interaction. In particular, the parameters of the clustering process are tuned optimizing an entropy oriented cost function that allows an automatic selection of the best parameters setting.

show abstract