A Robust Approach for Image Segmentation using U-Net Model
International Journal of Engineering & Extended Technologies Research · 28.03.2026 · 08 (02)
DOI: 10.15662/ijeetr.2026.0802177 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Engineering & Extended Technologies Research, online erschienen am 28.03.2026. Verfasst von M.Sweetline Sonia und 2 weiteren Autor:innen.
Abstract (Originalsprache)
Image segmentation is a fundamental task in computer vision that involves partitioning an image into meaningful regions for analysis. This paper presents a deep learning-based approach for image segmentation using the U-Net architecture. The model employs an encoder-decoder structure with skip connections to effectively capture both spatial and contextual information. The input images are preprocessed and fed into the network, which learns to generate accurate segmentation masks. Experimental results demonstrate that the proposed U-Net model achieves improved segmentation performance with higher accuracy and reduced loss. The predicted outputs closely match the ground truth masks, indicating the effectiveness of the model in identifying object boundaries. The proposed approach can be applied to various applications such as medical imaging, object detection, and scene understanding.
Zitieren
APA
Sonia, M., Vijayalakshmi, A., & Indhumathi, N. (2026). A Robust Approach for Image Segmentation using U-Net Model. International Journal of Engineering & Extended Technologies Research, 08(02). https://doi.org/10.15662/ijeetr.2026.0802177
Vancouver
Sonia M, Vijayalakshmi A, Indhumathi N. A Robust Approach for Image Segmentation using U-Net Model. International Journal of Engineering & Extended Technologies Research. 2026;08(02). doi:10.15662/ijeetr.2026.0802177
BibTeX
@article{Sonia2026,
author = {Sonia, M.Sweetline and Vijayalakshmi, A. and Indhumathi, N.},
title = {A Robust Approach for Image Segmentation using U-Net Model},
journal = {International Journal of Engineering & Extended Technologies Research},
year = {2026},
volume = {08},
number = {02},
doi = {10.15662/ijeetr.2026.0802177}
}
EUVIMED