Garuda - Garba Rujukan Digital

Iris Identification Using Resnet Iris Feature Extraction Architecture For Better Biometric Security Hendi Sama; Tukino Tukino; Mangapul Siahaan; Erica Titoni
Journal of Applied Data Sciences Vol 7, No 2: May 2026
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v7i2.1166

Iris recognition is widely acknowledged as one of the most reliable biometric modalities due to its high uniqueness, rich textural patterns, and long-term stability. Unlike other biometric traits, iris characteristics resist forgery, aging effects, and environmental variations, making it suitable for high-security applications. Recently, convolutional neural networks (CNNs) have been extensively applied in iris recognition to improve feature representation and classification accuracy. However, many CNN-based approaches still depend on conventional segmentation and handcrafted features, which reduce robustness under noisy data, illumination variations, occlusions, or unconstrained environments. To address these limitations, this study proposes an enhanced iris identification framework combining a modified T-Net for precise segmentation with deep residual feature extraction for improved discrimination. Unlike conventional systems focus mainly on classification, the proposed approach emphasizes segmentation-driven feature consistency, ensuring extracted features originate from accurately localized iris regions. This design enhances stability and reliability, particularly under challenging imaging conditions. The framework leverages transfer learning and efficient representation learning strategies, enabling high accuracy even with a limited labelled data. Evaluations on three benchmark datasets CASIA-IrisV4, IITD Iris Database, and UBIRIS.v2 covering both controlled and less-constrained acquisition scenarios. Results show that it achieves classification accuracy of up to 98.35%, while maintaining computational efficiency suitable for deployment. The proposed architecture offers a robust, data-efficient, and scalable solution for secure biometric authentication, with strong potential for real-world applications such as access control, identity verification, and high-security authentication systems.

Image-Based Detection of Reduced Security Features in Indonesian Banknotes Using U-Net Architecture Silfia Andini; Tukino Tukino
Journal of Applied Data Sciences Vol 7, No 1: January 2026
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v7i1.1087

The circulation of fake currency banknotes in Indonesia continues to rise alongside rapid technological advancements, while conventional verification systems remain limited and often ineffective in detecting subtle authenticity cues. The main objective of this study is to develop an image-based fake currency detection system using the U-Net deep learning architecture and its modified version, T-Net, to enhance feature extraction and classification accuracy. The key contribution of this research lies in combining convolutional architectures with a practical, web-based interface that enables real-time image analysis, thus bridging the gap between model performance and user accessibility. A quantitative experimental method was employed, involving model development in Python using TensorFlow and Keras, and implementation of a Flask-based web application for real-time classification. The research utilized a dataset of 2,141 Indonesian rupiah banknote images, consisting of 1,015 genuine and 1,126 fake currency samples synthetically generated through digital modification of security features such as watermarks and color-shifting ink. Image preprocessing included resizing, normalization, and augmentation techniques such as random flipping and brightness adjustment to enhance data quality. Three convolutional architectures U-Net, ResNet-50, and the modified T-Net were trained and compared using identical hyperparameters. The T-Net model achieved the best performance, with 97.8% training accuracy, 82.6% validation accuracy, precision of 0.83, recall of 0.80, and an F1-score of 0.81. Despite the performance gap indicating overfitting, the model effectively distinguishes genuine from fake currency notes. The Flask-based interface allows users to upload images and receive classification results from all three models within 0.3–1.8 seconds per image. The findings demonstrate the feasibility and efficiency of U-Net based architectures for image-driven fake currency detection and provide a foundation for developing advanced, reliable, and real-time financial authentication systems that can strengthen digital security infrastructures in future applications.

Application of Convolutional Neural Networks for Automated Iris Edge Detection in Sleepiness Monitoring during Blended Learning Tukino Tukino; Yuhandri Yuhandri; Sumijan Sumijan
Journal of Applied Data Sciences Vol 6, No 4: December 2025
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v6i4.882

This study introduces a novel lightweight Convolutional Neural Network (CNN) model, T-Net, designed for real-time drowsiness detection based on eye closure patterns. The model was developed to address the prevalent issue of student fatigue in resource-constrained environments, such as during prolonged online learning or blended learning sessions. Unlike traditional deep learning models, T-Net prioritizes efficiency while maintaining high accuracy, making it suitable for deployment on devices with limited computational resources. The model uses a 68-point facial landmark detection technique to extract the eye region and accurately classify eyelid states (open or closed). Evaluated on two benchmark datasets, Dataset-1 (342 eye images) and Dataset-2 (1,510 eye images), T-Net demonstrated superior performance, achieving classification accuracies of 99.33% and 99.27%, respectively, outperforming other pre-trained models such as VGG19, ResNet50, and MobileNetV2. Usability testing revealed a high acceptance rate, with a System Usability Scale (SUS) score of 84.5, indicating the system’s practicality for real-world use. Additionally, statistical analysis showed a significant correlation (r = 0.67, p 0.01) between prolonged screen time and the emergence of visual fatigue symptoms. This study highlights the effectiveness of a lightweight CNN approach for real-time fatigue monitoring, offering a balance between performance and computational efficiency. The results suggest that T-Net can be effectively integrated into student monitoring systems to ensure alertness during learning sessions. Future research will focus on expanding the dataset, integrating infrared imaging for low-light environments, and incorporating additional fatigue indicators such as yawning and head pose.

Image-Based Detection of Reduced Security Features in Indonesian Banknotes Using U-Net Architecture Silfia Andini; Tukino Tukino
Journal of Applied Data Sciences Vol 7, No 1: January 2026
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v7i1.1087

The circulation of fake currency banknotes in Indonesia continues to rise alongside rapid technological advancements, while conventional verification systems remain limited and often ineffective in detecting subtle authenticity cues. The main objective of this study is to develop an image-based fake currency detection system using the U-Net deep learning architecture and its modified version, T-Net, to enhance feature extraction and classification accuracy. The key contribution of this research lies in combining convolutional architectures with a practical, web-based interface that enables real-time image analysis, thus bridging the gap between model performance and user accessibility. A quantitative experimental method was employed, involving model development in Python using TensorFlow and Keras, and implementation of a Flask-based web application for real-time classification. The research utilized a dataset of 2,141 Indonesian rupiah banknote images, consisting of 1,015 genuine and 1,126 fake currency samples synthetically generated through digital modification of security features such as watermarks and color-shifting ink. Image preprocessing included resizing, normalization, and augmentation techniques such as random flipping and brightness adjustment to enhance data quality. Three convolutional architectures U-Net, ResNet-50, and the modified T-Net were trained and compared using identical hyperparameters. The T-Net model achieved the best performance, with 97.8% training accuracy, 82.6% validation accuracy, precision of 0.83, recall of 0.80, and an F1-score of 0.81. Despite the performance gap indicating overfitting, the model effectively distinguishes genuine from fake currency notes. The Flask-based interface allows users to upload images and receive classification results from all three models within 0.3–1.8 seconds per image. The findings demonstrate the feasibility and efficiency of U-Net based architectures for image-driven fake currency detection and provide a foundation for developing advanced, reliable, and real-time financial authentication systems that can strengthen digital security infrastructures in future applications.

Iris Identification Using Resnet Iris Feature Extraction Architecture For Better Biometric Security Hendi Sama; Tukino Tukino; Mangapul Siahaan; Erica Titoni
Journal of Applied Data Sciences Vol 7, No 2: May 2026
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v7i2.1166

Iris recognition is widely acknowledged as one of the most reliable biometric modalities due to its high uniqueness, rich textural patterns, and long-term stability. Unlike other biometric traits, iris characteristics resist forgery, aging effects, and environmental variations, making it suitable for high-security applications. Recently, convolutional neural networks (CNNs) have been extensively applied in iris recognition to improve feature representation and classification accuracy. However, many CNN-based approaches still depend on conventional segmentation and handcrafted features, which reduce robustness under noisy data, illumination variations, occlusions, or unconstrained environments. To address these limitations, this study proposes an enhanced iris identification framework combining a modified T-Net for precise segmentation with deep residual feature extraction for improved discrimination. Unlike conventional systems focus mainly on classification, the proposed approach emphasizes segmentation-driven feature consistency, ensuring extracted features originate from accurately localized iris regions. This design enhances stability and reliability, particularly under challenging imaging conditions. The framework leverages transfer learning and efficient representation learning strategies, enabling high accuracy even with a limited labelled data. Evaluations on three benchmark datasets CASIA-IrisV4, IITD Iris Database, and UBIRIS.v2 covering both controlled and less-constrained acquisition scenarios. Results show that it achieves classification accuracy of up to 98.35%, while maintaining computational efficiency suitable for deployment. The proposed architecture offers a robust, data-efficient, and scalable solution for secure biometric authentication, with strong potential for real-world applications such as access control, identity verification, and high-security authentication systems.

Title

Found 5 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 5 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 5 Documents
Search