Claim Missing Document
Check
Articles

Found 3 Documents
Search

Adaptive deep learning based on FaceNet convolutional neural network for facial expression recognition Al-Ghiffary, Maulana Malik Ibrahim; Cahyo, Nur Ryan Dwi; Rachmawanto, Eko Hari; Irawan, Candra; Hendriyanto, Novi
Journal of Soft Computing Exploration Vol. 5 No. 3 (2024): September 2024
Publisher : SHM Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52465/joscex.v5i3.450

Abstract

Facial recognition technology has become increasingly crucial in various applications, from personal identification, security, and human-care. Facial recognition has numerous practical applications, ranging from assessing mental health and well-being through facial expressions to evaluating customer satisfaction in service quality ratings. This study aims to develop a facial recognition model using a Convolutional Neural Network (CNN) with FaceNet architecture. The proposed method utilizes an advanced deep learning approach to generate high-quality facial embeddings, enhancing the model's ability to accurately identify and verify individuals. Our methodology includes training the CNN with FaceNet architecture, achieving an impressive average accuracy of 99.93%, with precision, recall, and F1-score all reaching 100%. The model demonstrated both high accuracy and efficiency, with an average training time of 13 minutes and 51 seconds. Future research should explore incorporating data augmentation, K-fold cross-validation, and additional transfer learning techniques to further enhance model performance and generalization. These advancements could lead to more resilient and flexible facial recognition systems capable of functioning effectively in diverse and challenging real-world conditions.
High-Quality Evaluation for Invisible Watermarking Based on Discrete Cosine Transform (DCT) and Singular Value Decomposition (SVD) Sofyan, Ega Adiasa; Sari, Christy Atika; Rachmawanto, Eko Hari; Cahyo, Nur Ryan Dwi
Advance Sustainable Science, Engineering and Technology Vol 6, No 1 (2024): November-January
Publisher : Universitas PGRI Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26877/asset.v6i1.17186

Abstract

In this research, we propose an innovative approach that integrates Discrete Cosine Transform (DCT) and Singular Value Decomposition (SVD) to enhance the quality and security of digital images. The purpose of this technique is to embed imperceptible watermarks into images, preserving their integrity and authenticity. The integration of DCT allows for an efficient transformation of image data into frequency components, forming the basis for embedding watermarks that are nearly invisible to the human eye. In this context, SVD offers an advantage by separating singular values and corresponding vectors, facilitating a more sophisticated watermarking process. The quality evaluation using metrics such as MSE, PSNR, UQI, and MSSIM demonstrates the effectiveness of this approach. Low average MSE values, ranging from 0.0058 to 0.0064, indicate minimal distortion in the watermarked images. Additionally, high PSNR values, ranging from 67.20 dB to 67.22 dB, affirm the high image quality achieved after watermarking. These results validate that the integration of DCT and SVD provides a high level of security while maintaining optimal visual quality in digital images. This approach is highly relevant and effective in addressing the challenges of image protection in this digital era.
A Good Evaluation Based on Confusion Matrix for Lung Diseases Classification using Convolutional Neural Networks Kamila, Izza Putri; Sari, Christy Atika; Rachmawanto, Eko Hari; Cahyo, Nur Ryan Dwi
Advance Sustainable Science, Engineering and Technology Vol 6, No 1 (2024): November-January
Publisher : Universitas PGRI Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26877/asset.v6i1.17330

Abstract

CNN has been widely used to detect a pattern with image classification. This study used CNN to perform a classification analysis of lung abnormality detection on chest X-ray images. The dataset consists of 5,732 2D images with dimensions of 200 x 200 x 1 divided into training data (85%) and testing data (15%). The preprocessing process includes image resizing, enhancement to increase contrast and reduce image complexity, and filtering to improve visibility and reduce noise. CNN is used to classify imagery into three categories, Normal (no abnormalities), Pneumonia, and Tuberculosis. The results showed a good level of accuracy, with an average accuracy of 97.24% in 3 trainings, and a 100% success rate in 6 classification experiments. This research provides insights into the detection of lung disorders and encourages further exploration in medical diagnosis.