DIGITAL IMAGE QUALITY OPTIMIZATION USING DEEP NEURAL NETWORK
Abstract
Abstract: One of the main challenges in digital image processing is limited resolution, which makes it difficult to preserve visual details when images are enlarged. Conventional methods such as Bilinear Interpolation are commonly used for image upscaling; however, these approaches often produce blurred images, lose fine textures, and fail to reconstruct complex visual structures. This study aims to enhance digital image resolution by employing a deep learni based approach using a Low-Light Convolutional Neural Network (LLCNN) built upon a Deep Neural Network (DNN) architecture. The dataset used in this study is the DIV2K dataset, which consists of 1,000 high-resolution images. These images were downsampled using scaling factors of ×2, ×3, and ×4 to generate paired Low Resolution–High Resolution (LR–HR) data for training and evaluation. The proposed LLCNN is designed to extract important features such as edges, textures, and local patterns through multiple convolutional layers, followed by non-linear mapping to reconstruct high-resolution images more accurately. Quantitative performance evaluation was conducted using the Peak Signal-to-Noise Ratio (PSNR) and the Structural Similarity Index (SSIM). Model performance was evaluated quantitatively using the Peak Signal-to-Noise Ratio (PSNR) metric. Experimental results showed that the proposed method improved image quality compared to the bilinear method. These results indicate that the deep learning based approach effectively improves image sharpness and structural fidelity, thereby demonstrating its potential for digital image resolution enhancement.
Keywords: deep neural network; image resolution; low-light convolutional neural network; machine learning
Abstrak: Permasalahan utama dalam pengolahan citra digital adalah keterbatasan resolusi yang menyebabkan detail visual sulit dipertahankan ketika citra diperbesar. Metode konvensional seperti Bilinear Interpolation masih banyak digunakan, namun sering menghasilkan citra buram, kehilangan tekstur halus, serta tidak mampu merekonstruksi struktur visual yang kompleks. Penelitian ini bertujuan untuk meningkatkan kualitas resolusi citra digital dengan memanfaatkan pendekatan deep learning berbasis Low-Light Convolutional Neural Network (LLCNN) yang dibangun di atas arsitektur Deep Neural Network (DNN). Data yang digunakan dalam penelitian ini berasal dari dataset DIV2K, yang terdiri dari 1000 citra beresolusi tinggi. Citra tersebut diturunkan menjadi resolusi rendah menggunakan faktor downsampling ×2, ×3, dan ×4 untuk membentuk pasangan data Low Resolution–High Resolution (LR–HR) sebagai data pelatihan dan pengujian. LLCNN dirancang untuk mengekstraksi fitur-fitur penting seperti tepi, tekstur, dan pola lokal melalui beberapa lapisan konvolusi, kemudian melakukan pemetaan non-linear guna merekonstruksi citra resolusi tinggi secara lebih presisi. Evaluasi performa model dilakukan secara kuantitatif menggunakan metrik Peak Signal-to-Noise Ratio (PSNR). Hasil eksperimen menunjukkan bahwa metode yang diusulkan mampu meningkatkan kualitas citra dibandingkan metode bilinear. Hasil ini membuktikan bahwa pendekatan berbasis deep learning efektif dalam meningkatkan ketajaman dan kesesuaian struktur citra digital.
Kata kunci: deep neural network; low-light convolutional neural network; machine learning; resolusi citra
References
B. R. Ermawan and N. Cahyono, “Optimasi Metode Klasifikasi Menggunakan Fasttext Dan Grid Search Pada Analisis Sentimen Ulasan Aplikasi Seabank,” JIKO (Jurnal Inform. dan Komputer), vol. 9, no. 1, p. 226, 2025, doi: 10.26798/jiko.v9i1.1523.
S. Sulistyowati and A. Mandasari, “Peningkatan Resolusi Citra Digital Menggunakan Deep Neural Network,” 2024, [Online]. Available: http://repository.iti.ac.id/jspui/handle/123456789/2056
T. Jaiswal and S. Dash, “Deep learning in medical image analysis,” Min. Biomed. Text, Images Vis. Featur. Inf. Retr., pp. 287–295, 2024, doi: 10.1016/B978-0-443-15452-2.00014-5.
A. A. Chamid, R. Nindyasari, and M. I. Ghozali, “Comparative Analysis of Machine Learning Algorithms for,” vol. 5, no. 158, pp. 185–194, 2026.
W. Widowati and R. Kusumaningrum, “Text Data Labeling Process for Semi-Supervised Learning,” vol. 030011, 2024.
A. A. Chamid, “Graph-Based Semi-Supervised Deep Learning for Indonesian Aspect-Based Sentiment Analysis,” 2023.
A. N. Komariyah, B. Rohmatulloh, Y. Hendrawan, S. M. Sutan, D. F. Al Riza, and M. B. Hermanto, “Klasifikasi Kualitas Teh Hitam Menggunakan Metode Convolutional Neural Network (CNN) Berbasis Citra Digital,” J. Ilm. Rekayasa Pertan. dan Biosist., vol. 11, no. 2, pp. 221–231, 2023, doi: 10.29303/jrpb.v11i2.542.
L. Alzubaidi et al., Review of deep learning: concepts, CNN architectures, challenges, applications, future directions, vol. 8, no. 1. Springer International Publishing, 2021. doi: 10.1186/s40537-021-00444-8.
B. Wang et al., “Low-light-level image super-resolution reconstruction based on a multi-scale features extraction network,” Photonics, vol. 8, no. 8, 2021, doi: 10.3390/photonics8080321.
J. Kim, J. K. Lee, and K. M. Lee, “Accurate image super-resolution using very deep convolutional networks,” Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit., vol. 2016-Decem, pp. 1646–1654, 2016, doi: 10.1109/CVPR.2016.182.
R. Images, L. Hu, M. Qin, F. Zhang, Z. Du, and R. Liu, “RSCNN : A CNN-Based Method to Enhance Low-Light,” Remote Sensing, MDPI 2020, pp. 1–13, 2020.
A. A. Chamid and R. Kusumaningrum, “Ingénierie des Systèmes d ’ Information Labeling Consistency Test of Multi-Label Data for Aspect and Sentiment Classification Using the Cohen Kappa Method,” vol. 29, no. 1, pp. 161–167, 2024.
A. A. Chamid and R. Kusumaningrum, “Multi-Label Text Classification On Indonesian User,” vol. 17, no. 10, pp. 1075–1084, 2023, doi: 10.24507/icicel.17.10.1075.
M. Thoriq, “Peramalan Jumlah Permintaan Produksi Menggunakan Jaringan Saraf Tiruan Algoritma Backpropagation,” J. Inf. dan Teknol., vol. 1, no. 2, pp. 27–32, 2022, doi: 10.37034/jidt.v4i1.178.
C. Hudaya, A. Gunawan, B. W. Tri, and P. A. Darat, “Penerapan Arsitektur Jst Dalam Deep Learning,” pp. 203–210.
M. Rizky and Y. Sugiarti, “Pengunaan Metode Scrum Dalam Pengembangan Perangkat Lunak: Literature Review,” J. Comput. Sci. Eng., vol. 3, no. 1, pp. 41–48, 2022, doi: 10.36596/jcse.v3i1.353.
H. R. Suharno, N. Gunantara, and M. Sudarma, “Analisis Penerapan Metode Scrum Pada Sistem Informasi Manajemen Proyek Dalam Industri & Organisasi Digital,” Maj. Ilm. Teknol. Elektro, vol. 19, no. 2, p. 203, 2020, doi: 10.24843/mite.2020.v19i02.p12.
W. Warkim, M. H. Muslim, F. Harvianto, and S. Utama, “Penerapan Metode SCRUM dalam Pengembangan Sistem Informasi Layanan Kawasan,” J. Tek. Inform. dan Sist. Inf., vol. 6, no. 2, pp. 365–378, 2020, doi: 10.28932/jutisi.v6i2.2711.
A. K. Nugroho, I. Permadi, and M. Faturrahim, “Improvement of Image Quality Using Convolutional Neural Networks Method,” Scientific Journal of Informatics, vol. 9, no. 1, pp. 95–103, May 2022, doi: 10.15294/sji.v9i1.30892.
B. Nugroho and E. Y. Puspaningrum, “Kinerja metode CNN untuk klasifikasi pneumonia dengan variasi ukuran citra input,” Jurnal Teknologi Informasi dan Ilmu Komputer, vol. 8, no. 3, pp. xxx–xxx, 2021, doi: 10.25126/jtiik.202184515.
S. Ayas and M. Ekinci, “Single image super resolution using dictionary learning and sparse coding with multi-scale and multi-directional Gabor feature representation,” Inf. Sci. (Ny)., vol. 512, pp. 1264–1278, 2020.
C. K. and Z. D. O. Keleş, M. A. Yιlmaz, A. M. Tekalp, “On the Computation of PSNR for a Set of Images or Video,” 2021.
P. Mane, Vanita & Jadhav, Suchit & Lal, “Image Super-Resolution for MRI Images using 3D Faster Super-Resolution Convolutional Neural Network architecture,” ITM Web Conf., vol. 32, p. 03044, 2020.
P. Simon and V. Uma, “Deep learning based feature extraction for texture classification,” Procedia Computer Science, vol. 171, pp. 1680–1687, 2020, doi: 10.1016/j.procs.2020.04.180.
K. Wiguna and D. Mahdiana, “Analysis of Information Systems Development Methods: A Literature Review,” Jurnal Inovtek Polbeng – Seri Informatika, vol. 8, no. 2, pp. 472–481, 2023, ISSN: 2527-9866.
