Feature extraction of static foam images based on U-Net and Hough transform
PLOS One · 11.11.2026 · 21 (11) · e0362662
DOI: 10.1371/journal.pone.0362662 ↗Kurz gefasst
Fachartikel in der Zeitschrift PLOS One, online erschienen am 11.11.2026. Verfasst von Deqiang Peng und 4 weiteren Autor:innen. Beteiligte Einrichtung: College of Energy and Mining, Heilongjiang University of Science and Technology, Harbin, China. Hauptthemen laut MEDLINE: Image Processing, Computer-Assisted, Minerals. Die Arbeit nennt 32 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: the Heilongjiang Provincial Natural Science Foundation Project, the Heilongjiang Province’s “Challenge and Response” Science and Technology Research Projects.
Abstract (Originalsprache)
In flotation-based mineral processing, froth images contain important visual information that reflects the operating condition of the process and provides a basis for process monitoring and control. However, conventional machine-vision methods still encounter difficulties in extracting static froth features under conditions of bubble adhesion, overlap, weak boundaries, and uneven illumination. To address these problems, a flotation froth image analysis framework is proposed by combining a boundary-aware U-Net segmentation model with a segmentation-guided adaptive Hough transform. In the first stage, the U-Net architecture is enhanced with explicit boundary-oriented supervision to improve the separation of adherent and overlapping bubbles. In the second stage, the geometric priors derived from the segmentation results are used to constrain the Hough-based detection process, thereby improving the reliability of bubble counting and geometric feature extraction. Experimental results show that the proposed method achieves a Dice similarity coefficient of 96.39% and an intersection over union of 93.04%, while maintaining favorable inference efficiency. Compared with representative segmentation models, the proposed framework provides a better balance between accuracy and speed. The study demonstrates that the integration of deep boundary-aware segmentation and adaptive geometric detection is effective for static feature extraction of flotation froth images and has potential for intelligent monitoring of flotation processes.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Substanzen
Autor:innen und Institutionen
- College of Energy and Mining, Heilongjiang University of Science and Technology, Harbin, China.
- Department of Mineral Processing Engineering, Taiyuan University of Technology, Taiyuan, China.
ORCID-Profile: Daoguang Li, Chenyi Wang
Förderung
- the Heilongjiang Provincial Natural Science Foundation Project
- the Heilongjiang Province’s “Challenge and Response” Science and Technology Research Projects
Zitieren
APA
Peng, D., Li, D., Li, Q., Wang, C., & Ma, X. (2026). Feature extraction of static foam images based on U-Net and Hough transform. PLOS One, 21(11), e0362662. https://doi.org/10.1371/journal.pone.0362662
Vancouver
Peng D, Li D, Li Q, Wang C, Ma X. Feature extraction of static foam images based on U-Net and Hough transform. PLOS One. 2026;21(11):e0362662. doi:10.1371/journal.pone.0362662
BibTeX
@article{Peng2026,
author = {Peng, Deqiang and Li, Daoguang and Li, Qingxia and Wang, Chenyi and Ma, Xiaomin},
title = {Feature extraction of static foam images based on U-Net and Hough transform},
journal = {PLOS One},
year = {2026},
volume = {21},
number = {11},
pages = {e0362662},
doi = {10.1371/journal.pone.0362662}
}
EUVIMED