2021
DOI: 10.3389/frobt.2021.685966
|View full text |Cite
|
Sign up to set email alerts
|

Behavioral Biometric Data Analysis for Gender Classification Using Feature Fusion and Machine Learning

Abstract: Biometric security applications have been employed for providing a higher security in several access control systems during the past few years. The handwritten signature is the most widely accepted behavioral biometric trait for authenticating the documents like letters, contracts, wills, MOU’s, etc. for validation in day to day life. In this paper, a novel algorithm to detect gender of individuals based on the image of their handwritten signatures is proposed. The proposed work is based on the fusion of textu… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

0
6
0

Year Published

2022
2022
2024
2024

Publication Types

Select...
6
3

Relationship

1
8

Authors

Journals

citations
Cited by 14 publications
(6 citation statements)
references
References 21 publications
(17 reference statements)
0
6
0
Order By: Relevance
“…This CNN-SVM model combines the best features which were extracted by the CVM classifiers and the SVM classifiers for the identification of gender. In [3], the authors used the behavioural biometric of the person in order to classify the gender of the person. They have considered the behavioural biometrics like the handwritten signatures for the gender classification.…”
Section: Literature Surveymentioning
confidence: 99%
“…This CNN-SVM model combines the best features which were extracted by the CVM classifiers and the SVM classifiers for the identification of gender. In [3], the authors used the behavioural biometric of the person in order to classify the gender of the person. They have considered the behavioural biometrics like the handwritten signatures for the gender classification.…”
Section: Literature Surveymentioning
confidence: 99%
“…We also observed that attention had been paid lately to ensemble approaches [20], where several different classifiers are combined to create a master model. The majority of the aforementioned models were applied upon textural [9,[11][12][13][15][16][17][18]25] and a combination of textural and shape features [14,22,23,[27][28][29][30][31]. The best accuracy rates-between 77% and 82%-were achieved by the SVM classifiers with textural features [12,16,17,27].…”
Section: Gender Classificationmentioning
confidence: 99%
“…Gender is one of the physical or social information of a person being male or female, which is used in many applications like forensic science, medical, video surveillance, etc. As a result, handwritten signatures are used to identify a person's various characteristics, such as gender [4], personality analysis [5], emotional state, neurological diseases, age, and also nationality. Handwritten Signatures made on document signifies approval, acceptance, and knowledge of an individual.…”
Section: Introductionmentioning
confidence: 99%
“…In Sect. 4 Experimental results are analyzed. Finally, the Comparative study, and the conclusion are presented in Sect.…”
Section: Introductionmentioning
confidence: 99%