Perkembangan Metode Image Quality Assessment Berbasis Deep Learning: A Systematic Literature Review terhadap Tren dan Evaluasi Performa
DOI:
https://doi.org/10.51903/pixel.v19i1.3780Keywords:
Convolutional Neural Network, Deep Learning, Image Quality Assessment, No-Reference Image Quality Assessment, Systematic Literature ReviewAbstract
Image Quality Assessment has become an important research area in computer vision due to the increasing use of digital imaging in medical, industrial, and remote sensing applications. This study conducted a Systematic Literature Review (SLR) using articles retrieved exclusively from the Scopus database. A total of fifteen Scopus-indexed articles were selected through the PRISMA process consisting of identification, screening, eligibility, and inclusion stages. The findings indicated that convolutional neural networks, transformer architectures, and no-reference approaches dominated recent studies because of their ability to capture complex visual features and improve evaluation accuracy. The application domain strongly influenced method selection, particularly in medical imaging, industrial quality control, and remote sensing. Deep learning methods achieved high performance but required large datasets and high computational resources. Overall, recent research trends shifted from traditional image enhancement toward artificial intelligence-based quality evaluation.
References
[1] Herath HMSS, Herath HMKKMB, Madusanka N, et al. A Systematic Review of Medical Image Quality Assessment. J Imaging. 2025;11(4):1–32.
[2] Chen Z, Du J, Li J, et al. MDFN: Enhancing Power Grid Image Quality Assessment via Multi-Dimension Distortion Feature. Sensors. 2025;25(11):18.
[3] Zhang J, Zhao Z, Tian X. ISAR Image Quality Assessment Based on Visual Attention Model. Appl Sci. 2025;15(4).
[4] Vulpoi RA, Ciobanu A, Drug VL, et al. Deep Learning-Based Semantic Segmentation for Objective Colonoscopy Quality Assessment. J Imaging. 2025;11(3):1–20.
[5] Yanai A, Horie A, Sakurai A, et al. Innovative AI models for clinical decision-making : predicting blastocyst formation and quality from time-lapse embryo images up to embryonic. Comput Biol Med [Internet]. 2025;195(February):110637.
[6] Arct B, Świderski B, Różańska MA, et al. Comparative Evaluation of CNN and Transformer Architectures for Flowering Phase Classification of Tilia cordata Mill. with Automated Image Quality Filtering. Sensors. 2025;25(17):1–37.
[7] Rotter P, Knapik D, Klemiato M, et al. Compensation of Speckle Noise in 2D Images from Triangulation Laser Profile Sensors Using Local Column Median Vectors with an Application in a Quality Control System. Sensors. 2025;25(11):1–20.
[8] Rottmayer N, Redenbach C. A Novel Distance-Based Metric for Quality Assessment in Image Segmentation. IET Image Process. 2026;20(1):1–9.
[9] Xie Y, Zhao Y, Xia T, et al. No-Reference Plane Image Quality Assessment Based on Differential Feature Fusion. 7th Int. Conf. Video, Signal Image Process. (VSIP 2025), Novemb. 1416, 2025, Kunming, China. Association for Computing Machinery; 2025.
[10] Telesco LG, Nejamkin D, Mata E, et al. Semi-supervised multi-task learning for interpretable quality assessment of fundus images. Biomed Signal Process Control [Internet]. 2026;113:43.
[11] Ozer C, Guler A, Turkvatan Cansever A, et al. Consistent explainable image quality assessment for medical imaging. Heal Inf Sci Syst. 2026;14(1).
[12] Lin S, Chiu H. From Quality Grading to Defect Recognition: A Dual-Pipeline Deep Learning Approach for Automated Mango Assessment. Electron. 2026;15(3).
[13] Lech P. Multi-Criteria Visual Quality Control Algorithm for Selected Technological Processes Designed for Budget IIoT Edge Devices. Electron. 2025;14(16):20.
[14] Zachar P, Wilk Ł, Pilarska-mazurek M, et al. Assessment of UAV image quality in terms of optical resolution. Int Arch Photogramm Remote Sens Spat Inf Sci Vol XLVIII-1/W4-2025 EuroCOW 2025 – Eur Work Calibration Orientat Remote Sensing, 16–18 June 2025, Warsaw, Pol Assess. 2025;XLVIII(June):16–18.
[15] Yang Y, Idris NB, Wahab AWA, et al. An image quality assessment algorithm based on ‘global + local’ feature fusion. PeerJ Comput Sci. 2025;11:1–25.
[16] Varga D. Comparative Evaluation of Multimodal Large Language Models for No-Reference Image Quality Assessment with Authentic Distortions: A Study of OpenAI and Claude.AI Models. Big Data Cogn Comput. 2025;9(5).
[17] Gao M, Song C, Zhang Q, et al. Research Progress on Color Image Quality Assessment. J Imaging. 2025;11(9):1–41.
[18] Yang Y, Liu C, Wu H, et al. A quality assessment algorithm for no-reference images based on transfer learning. PeerJ Comput Sci. 2025;11(2024).
[19] Ishchenko R, Solopov M, Popandopulo A, et al. Evaluation of Transfer Learning Efficacy for Surgical Suture Quality Classification on Limited Datasets. J Imaging. 2025;11(8):1–14.
[20] Isaac A, Barrera P, Rodríguez LM, et al. Tabular Data-to-Image Methods for Improved Indoor Air Quality Analysis and Risk Detection. 8th Int. Conf. Syst. Eng. - Cybersecurity & AI Build. a Reliab. Digit. Futur. (CIIS 2025), Oct. 0103, 2025, Lima, Peru. Association for Computing Machinery; 2025.
[21] Li L xin, Chen C zi, Zhao N xuan. Blind image quality assessment based on transformer. Sci Rep. 2022;44.
[22] Mohammadi S, Jenadeleh M, Sneyers J, et al. Evaluation of Objective Image Quality Metrics for High-Fidelity Image Compression. IEEE Access [Internet]. 2025;1–19.
[23] Wang H, Li L, Wang W, et al. Development and validation of a deep learning image quality feedback system for infant fundus photography. Sci Rep. 2025;15(1):1–12.
[24] Felicetti F, Lamonaca F, Carnì DL, et al. Image Quality Standardization in Radiomics: A Systematic Review of Artifacts, Variability, and Feature Stability. Sensors. 2026;26(3):1–22.
[25] Haddaway NR, Page MJ, Pritchard CC, et al. PRISMA2020: An R package and Shiny app for producing PRISMA 2020-compliant flow diagrams, with interactivity for optimised digital transparency and Open Synthesis. Campbell Syst Rev. 2022;18(2):1–12.
[26] Dobre-Baron R, Savu-Jivanov A, Ancuți C. Evaluating Image Quality Metrics as Loss Functions for Image Dehazing †. Sensors. 2025;25(15):1–14.
2.png)
