EUVIMEDEUVIMED entdecken
Crossref

A Siamese Neural Network-Based Perceptual Quality Metric for Image and Video Assessment

Amine Gonca Toprak, Öykü Berfin Mercan, Mehmet Özdem

Sivas Cumhuriyet Üniversitesi Bilim ve Teknoloji Dergisi · 29.06.2026 · 5 (1) · 40-52

DOI: 10.69560/cujast.1843247 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sivas Cumhuriyet Üniversitesi Bilim ve Teknoloji Dergisi, online erschienen am 29.06.2026. Verfasst von Amine Gonca Toprak und 2 weiteren Autor:innen. Die Arbeit nennt 46 Literaturangaben. Gefördert von: The Scientific and Technological Research Council of Türkiye.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurately assessing the perceptual similarity of visual data is a critical requirement in many multimedia applications, including video coding, streaming, and image restoration. Traditional pixel-based metrics such as Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index (SSIM), however, are limited in their ability to capture high-level semantic and contextual distortions perceived by humans, as they primarily focus on low-level structural differences. This limitation often results in inaccurate quality estimates, particularly when evaluating subtle texture losses or compression-induced visual artifacts. To address these challenges, this study introduces a new, fully neural, training-free evaluation metric, Neural Siamese Perceptual Quality (NSPQ). NSPQ measures perceptual similarity by comparing the feature embeddings of reference and distorted images using a pre-trained AlexNet-based Siamese Neural Network and translating the distance between embeddings into a perceptual similarity score. This approach shifts the focus of visual quality assessment from pixel-level differences to high-level feature representations, thereby providing estimates that better align with human visual perception. The proposed method was extensively evaluated on compressed natural video sequences obtained from the Xiph.org dataset as well as on a variety of distortions in the BAPPS dataset. Experimental results demonstrate that NSPQ achieves higher perceptual accuracy than traditional metrics. In the Xiph.org scenario, NSPQ reached an average performance of 99%, substantially surpassing SSIM (96%), normalized PSNR (39%), and VMAF (56%). In the BAPPS dataset, NSPQ obtained an average score of 85% in the p0 scenario, outperforming SSIM (65%). In the p1 scenario, NSPQ more accurately reflected distortion severity with an average score of 38%, remaining below the constant SSIM value of 65%. Overall, the findings indicate that NSPQ can serve not only as a complementary quality measure but also as a primary evaluation metric in applications such as video encoding, image restoration, and quality control.

Förderung

  • The Scientific and Technological Research Council of Türkiye

Zitieren

APA

Toprak, A. G., Mercan, Ö. B., & Özdem, M. (2026). A Siamese Neural Network-Based Perceptual Quality Metric for Image and Video Assessment. Sivas Cumhuriyet Üniversitesi Bilim ve Teknoloji Dergisi, 5(1), 40-52. https://doi.org/10.69560/cujast.1843247

Vancouver

Toprak AG, Mercan ÖB, Özdem M. A Siamese Neural Network-Based Perceptual Quality Metric for Image and Video Assessment. Sivas Cumhuriyet Üniversitesi Bilim ve Teknoloji Dergisi. 2026;5(1):40-52. doi:10.69560/cujast.1843247

BibTeX
@article{Toprak2026,
  author = {Toprak, Amine Gonca and Mercan, Öykü Berfin and Özdem, Mehmet},
  title = {A Siamese Neural Network-Based Perceptual Quality Metric for Image and Video Assessment},
  journal = {Sivas Cumhuriyet Üniversitesi Bilim ve Teknoloji Dergisi},
  year = {2026},
  volume = {5},
  number = {1},
  pages = {40--52},
  doi = {10.69560/cujast.1843247}
}
Kostenlos starten →