Emotional State Prediction From Online Handwriting and Signature Biometrics

Yasemin Bay Ayzeren,Meryem Erbilek,Erbug Celebi

doi:10.1109/access.2019.2952313

Yasemin Bay Ayzeren, Meryem Erbilek + Show 1 more

Open Access

https://doi.org/10.1109/access.2019.2952313

Copy DOI

Abstract

Handwriting and signature biometrics have a long history in the literature, especially in terms of identity recognition and/or verification; nevertheless, it reveals more information therefore provides more opportunities for personal characteristics estimation, particularly, emotional state. However, almost all publicly or commercially available databases do not include contributors' demographic labels or emotional status in addition to their identification labels, leading these available databases to be only useful for verification and identification based research studies. For this reason, this paper proposes both offline and online handwriting and signature biometric database with a wide range of ground truths (emotional status labels - happy, sad and stress) in addition to the identity labels and tries to predict ones' emotional state, namely happy, sad and stress, from their online biometric handwriting and signatures. The proposed database comprised total of 134 participants with 804 handwriting and 8040 signature biometric samples. The database presented also includes individuals' demographic information such as age, gender, handedness, education level and nationality. Subsequently, there are several experiments have been conducted, with different thresholds, which present the usability of the proposed database and preliminary results of emotional state prediction from both signature and handwriting biometrics. The experiments achieved remarkable success especially on stress prediction for handwriting. On the other hand, considering the results from signature biometrics, it is observed that happy and then sad and finally stress class forms the most part of the prediction accuracy.

Highlights

Biometrics is a generic term to reliably identify and/or verify an individual by recognizing the unique physiological and/or behavioral traits that cannot be lost, forgotten, or used by others, as it is often the case with traditional ID (Identity) and password authentication systems [1]
FEATURE EXTRACTION Unlike offline signature and handwriting biometrics that focus on the shape and structural characteristics of an image, this study focuses on the online features collecting path and time dependent features, since due to gathering input data
The review and discussion presented in itself is a very valuable study since it clearly identifies the strengths and weaknesses of the currently available biometric databases, and illustrates the characteristics likely to be needed for the future research in the biometrics and softbiometrics fields

Summary

Introduction

Biometrics is a generic term to reliably identify and/or verify an individual by recognizing the unique physiological (such as face, iris, fingerprint, ear and so on) and/or behavioral (such as handwriting, signature, gait, voice, keystroke and so on) traits that cannot be lost, forgotten, or used by others, as it is often the case with traditional ID (Identity) and password authentication systems [1]. Biometrics is helping reshape industries by relieving businesses’ concerns about the security and privacy of their confidential information This field is gaining stable growth of attention from researchers bringing new features into the identification and authentication processes. We acquired data from participants in both dynamic and static representations

Objectives

Results

Conclusion