Page 131 - 2024-Vol20-Issue2

Received: 16 June 2023 | Revised: 14 October 2023 | Accepted: 2 November 2023

DOI: 10.37917/ijeee.20.2.11 Vol. 20 | Issue 2 | December 2024

Open Access

Iraqi Journal for Electrical and Electronic Engineering

Original Article

A Dataset for Kinship Estimation from Image of Hand

Using Machine Learning

Sarah Ibrahim Fathi*, Mazin H. Aziz
Computer Engineering Department, University of Mosul, Mosul, Iraq

Correspondance
*Sarah Ibrahim Fathi
Computer Engineering Department,
University of Mosul, Mosul,Iraq.
Email: saraibraheem.new@gmail.com

Abstract
Kinship (Familial relationships) detection is crucial in many fields and has applications in biometric security, adoption,
forensic investigations, and more. It is also essential during wars and natural disasters like earthquakes since it may
aid in reunion, missing person searches, establishing emergency contacts, and providing psychological support. The
most common method of determining kinship is DNA analysis which is highly accurate. Another approach, which is
noninvasive, uses facial photos with computer vision and machine learning algorithms for kinship estimation. Each part
of the Human -body has its own embedded information that can be extracted and adopted for identification, verification,
or classification of that person. Kinship recognition is based on finding traits that are shared by every family. We
investigate the use of hand geometry for kinship detection, which is a new approach. Because of the available hand
image Datasets do not contain kinship ground truth; therefore, we created our own dataset. This paper describes the
tools, methodology, and details of the collected MKH, which stands for the Mosul Kinship Hand, images dataset. The
images of MKH dataset were collected using a mobile phone camera with a suitable setup and consisted of 648 images for
81 individuals from 14 families (8 hand situations per person). This paper also presents the use of this dataset in kinship
prediction using machine learning. Google MdiaPipe was used for hand detection, segmentation, and geometrical
key points finding. Handcraft feature extraction was used to extract 43 distinctive geometrical features from each
image. A neural network classifier was designed and trained to predict kinship, yielding about 93% prediction accuracy.
The results of this novel approach demonstrated that the hand possesses biometric characteristics that may be used to
establish kinship, and that the suggested method is a promising way as a kinship indicator.

Keywords
Hand geometrical features, Hand image dataset, Kinship prediction, MediaPipe, Neural Network.

I. INTRODUCTION acterized as mean of verification, recognition, and their utilize
in various spheres of life. Behavioral and Physiological are
Kinship Verification is the process of achieving whether two two divisions of biometric characteristics, as presented in Fig.
people are related by blood. Because of its usefulness, it is 1 [2]. The choice of biometric trait in biometric system design
a new and difficult subject that is receiving more and more is a critical issue. In theory, any behavioral, anatomical, or
attention [1]. Familial relationship prediction based on image physiological characteristic of an individual can be used as
processing and machine learning (ML) techniques is limited a biometric feature . In the literature, geometric hand fea-
to facial images only. The hand images contain several bio- tures make up the bulk of the hand features approved in most
metric traits that were used to classify persons based on gen- biometric systems [3]. Typical traits include finger length,
der, age, or group affiliation. It can also be used for person finger breadth, palm width, and finger aspect ratio [4], finger
identification and verification. A biometric technology is char-

This is an open-access article under the terms of the Creative Commons Attribution License,
which permits use, distribution, and reproduction in any medium, provided the original work is properly cited.
©2024 The Authors.
Published by Iraqi Journal for Electrical and Electronic Engineering | College of Engineering, University of Basrah.

https://doi.org/10.37917/ijeee.20.2.11 |https://www.ijeee.edu.iq 127