Research Article Open Access

Systematic Evaluation of Image-Based NPR Applied to Video

Alberto F.F. de Barros1, Jose E.R. de Queiroz1 and Herman M. Gomes1
  • 1 Federal University of Campina Grande, Brazil
Journal of Computer Science
Volume 16 No. 4, 2020, 508-517

DOI: https://doi.org/10.3844/jcssp.2020.508.517

Submitted On: 16 December 2019 Published On: 29 April 2020

How to Cite: de Barros, A. F., de Queiroz, J. E. & Gomes, H. M. (2020). Systematic Evaluation of Image-Based NPR Applied to Video. Journal of Computer Science, 16(4), 508-517. https://doi.org/10.3844/jcssp.2020.508.517

Abstract

In this article, it was studied the effect of state-of-the-art approaches for Non-Photorealistic Rendering (NPR), originally developed for static images, when applied to videos. Six criteria were objectively evaluated (using a 5-point Likert scales): Simplicity, content preservation, resemblance to the original content, sharpness, temporal coherence and subjective satisfaction. Sixty participants and a dataset of 30 videos of different genres were used in the experiments. Each participant voted 15 pairwise video comparisons. Three approaches were considered: Anisotropic Kuwahara, Coherent Enhancement and Extended Difference of Gaussians (XDoG). The results of the study, under 99% statistical confidence, indicated that the Anisotropic Kuwahara approach achieved the best results for most of the criteria. Coherent Enhancement and XDoG approaches came next. These results indicate that the selected approaches were considered satisfactory, when applied to video, for most considered criteria.

  • 379 Views
  • 128 Downloads
  • 0 Citations

Download

Keywords

  • Non-Photorealistic Rendering
  • Video Abstraction
  • Image Filtering
  • Comparative Evaluation