CNN Performance Improvement for Classifying Stunted Facial Images Using Early Stopping Approach

Stunting, a condition characterised by short stature, is a growth disorder caused by chronic malnutrition, which often begins in the womb. Children affected by stunting usually show different physical and cognitive characteristics compared to their peers. Research shows that these physical differenc...

Full description

Saved in:
Bibliographic Details
Main Authors: Yunidar Yunidar, Y Yusni, N Nasaruddin, Fitri Arnia
Format: Article
Language:English
Published: Ikatan Ahli Informatika Indonesia 2025-01-01
Series:Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi)
Subjects:
Online Access:https://jurnal.iaii.or.id/index.php/RESTI/article/view/6068
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850053049062522880
author Yunidar Yunidar
Y Yusni
N Nasaruddin
Fitri Arnia
author_facet Yunidar Yunidar
Y Yusni
N Nasaruddin
Fitri Arnia
author_sort Yunidar Yunidar
collection DOAJ
description Stunting, a condition characterised by short stature, is a growth disorder caused by chronic malnutrition, which often begins in the womb. Children affected by stunting usually show different physical and cognitive characteristics compared to their peers. Research shows that these physical differences can also be observed in facial features. Because faces provide important information and are commonly studied in digital image processing, in this study, we will compare the facial image classification performance of stunted children versus normal children using various Convolutional Neural Network (CNN) architectures. The evaluated architectures include MobileNetV2, InceptionV3, VGG19, ResNet18, EfficientNetB0, and AlexNet. To improve the learning process, augmentation techniques with Haar cascade and Gaussian filters were applied so that the data set increased from 1,000 to 6,000 images. After adding the dataset, training is carried out with an early stop approach to minimise overfitting. The main aim of this research is to identify the CNN model that is most effective in differentiating facial images of stunted children from normal children. The results show that the EfficientNetB0 architecture outperforms other models, achieving 100% accuracy. Early stopping has been shown to improve training efficiency and help prevent overfitting.
format Article
id doaj-art-eac81407dd9746b999169a0f633a6bdf
institution DOAJ
issn 2580-0760
language English
publishDate 2025-01-01
publisher Ikatan Ahli Informatika Indonesia
record_format Article
series Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi)
spelling doaj-art-eac81407dd9746b999169a0f633a6bdf2025-08-20T02:52:38ZengIkatan Ahli Informatika IndonesiaJurnal RESTI (Rekayasa Sistem dan Teknologi Informasi)2580-07602025-01-0191626810.29207/resti.v9i1.60686068CNN Performance Improvement for Classifying Stunted Facial Images Using Early Stopping ApproachYunidar Yunidar0Y Yusni1N Nasaruddin2Fitri Arnia3Universitas Syiah KualaUniversitas Syiah KualaUniversitas Syiah KualaUniversitas Syiah KualaStunting, a condition characterised by short stature, is a growth disorder caused by chronic malnutrition, which often begins in the womb. Children affected by stunting usually show different physical and cognitive characteristics compared to their peers. Research shows that these physical differences can also be observed in facial features. Because faces provide important information and are commonly studied in digital image processing, in this study, we will compare the facial image classification performance of stunted children versus normal children using various Convolutional Neural Network (CNN) architectures. The evaluated architectures include MobileNetV2, InceptionV3, VGG19, ResNet18, EfficientNetB0, and AlexNet. To improve the learning process, augmentation techniques with Haar cascade and Gaussian filters were applied so that the data set increased from 1,000 to 6,000 images. After adding the dataset, training is carried out with an early stop approach to minimise overfitting. The main aim of this research is to identify the CNN model that is most effective in differentiating facial images of stunted children from normal children. The results show that the EfficientNetB0 architecture outperforms other models, achieving 100% accuracy. Early stopping has been shown to improve training efficiency and help prevent overfitting.https://jurnal.iaii.or.id/index.php/RESTI/article/view/6068stuntingfacescnnstuntedhaar cascadeearly stopping
spellingShingle Yunidar Yunidar
Y Yusni
N Nasaruddin
Fitri Arnia
CNN Performance Improvement for Classifying Stunted Facial Images Using Early Stopping Approach
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi)
stunting
faces
cnn
stunted
haar cascade
early stopping
title CNN Performance Improvement for Classifying Stunted Facial Images Using Early Stopping Approach
title_full CNN Performance Improvement for Classifying Stunted Facial Images Using Early Stopping Approach
title_fullStr CNN Performance Improvement for Classifying Stunted Facial Images Using Early Stopping Approach
title_full_unstemmed CNN Performance Improvement for Classifying Stunted Facial Images Using Early Stopping Approach
title_short CNN Performance Improvement for Classifying Stunted Facial Images Using Early Stopping Approach
title_sort cnn performance improvement for classifying stunted facial images using early stopping approach
topic stunting
faces
cnn
stunted
haar cascade
early stopping
url https://jurnal.iaii.or.id/index.php/RESTI/article/view/6068
work_keys_str_mv AT yunidaryunidar cnnperformanceimprovementforclassifyingstuntedfacialimagesusingearlystoppingapproach
AT yyusni cnnperformanceimprovementforclassifyingstuntedfacialimagesusingearlystoppingapproach
AT nnasaruddin cnnperformanceimprovementforclassifyingstuntedfacialimagesusingearlystoppingapproach
AT fitriarnia cnnperformanceimprovementforclassifyingstuntedfacialimagesusingearlystoppingapproach