Research on Improved Image Segmentation Algorithm Based on GrabCut
Electronics · 16.10.2024 · 13 (20) · 4068
DOI: 10.3390/electronics13204068 ↗Kurz gefasst
Fachartikel in der Zeitschrift Electronics, online erschienen am 16.10.2024. Verfasst von Shangzhen Pang und 4 weiteren Autor:innen. Die Arbeit wurde bisher 17-mal zitiert (Crossref) und nennt 20 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Opening Project of Sichuan Province University Key Laboratory of Bridge Non-destruction Detecting and Engineering Computing.
Abstract (Originalsprache)
The classic interactive image segmentation algorithm GrabCut achieves segmentation through iterative optimization. However, GrabCut requires multiple iterations, resulting in slower performance. Moreover, relying solely on a rectangular bounding box can sometimes lead to inaccuracies, especially when dealing with complex shapes or intricate object boundaries. To address these issues in GrabCut, an improvement is introduced by incorporating appearance overlap terms to optimize segmentation energy function, thereby achieving optimal segmentation results in a single iteration. This enhancement significantly reduces computational costs while improving the overall segmentation speed without compromising accuracy. Additionally, users can directly provide seed points on the image to more accurately indicate foreground and background regions, rather than relying solely on a bounding box. This interactive approach not only enhances the algorithm’s ability to accurately segment complex objects but also simplifies the user experience. We evaluate the experimental results through qualitative and quantitative analysis. In qualitative analysis, improvements in segmentation accuracy are visibly demonstrated through segmented images and residual segmentation results. In quantitative analysis, the improved algorithm outperforms GrabCut and min_cut algorithms in processing speed. When dealing with scenes where complex objects or foreground objects are very similar to the background, the improved algorithm will display more stable segmentation results.
Förderung
- Opening Project of Sichuan Province University Key Laboratory of Bridge Non-destruction Detecting and Engineering Computing
Zitieren
APA
Pang, S., Thio, T. H. G., Siaw, F. L., Chen, M., & Xia, Y. (2024). Research on Improved Image Segmentation Algorithm Based on GrabCut. Electronics, 13(20), 4068. https://doi.org/10.3390/electronics13204068
Vancouver
Pang S, Thio THG, Siaw FL, Chen M, Xia Y. Research on Improved Image Segmentation Algorithm Based on GrabCut. Electronics. 2024;13(20):4068. doi:10.3390/electronics13204068
BibTeX
@article{Pang2024,
author = {Pang, Shangzhen and Thio, Tzer Hwai Gilbert and Siaw, Fei Lu and Chen, Mingju and Xia, Yule},
title = {Research on Improved Image Segmentation Algorithm Based on GrabCut},
journal = {Electronics},
year = {2024},
volume = {13},
number = {20},
pages = {4068},
doi = {10.3390/electronics13204068}
}
EUVIMED