Contextual image caption creation using object positional embedding and generative models
PLOS One · 09.07.2026 · 21 (7) · e0353466
DOI: 10.1371/journal.pone.0353466 ↗Kurz gefasst
Fachartikel in der Zeitschrift PLOS One, online erschienen am 09.07.2026. Verfasst von Muhammad Danyal und 3 weiteren Autor:innen. Beteiligte Einrichtung: Institute of Computing, Kohat University of Science and Technology, Kohat, Pakistan. Hauptthemen laut MEDLINE: Image Processing, Computer-Assisted, Deep Learning. Die Arbeit nennt 44 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Automated image captioning remains a challenge, as it enables machines to generate context-aware textual descriptions of visual content. Traditional deep learning approaches often rely on lexical overlap and fail to capture semantic relationships among objects, leading to captions that lack contextual richness. This study proposes an encoder–decoder framework that integrates YOLOv5 with a generative transformer to generate descriptive image captions. The proposed model was evaluated against two baselines: CNN-LSTM (M1) and a BERT-based transformer model (M2). M1 achieves BLEU-1 (0.45) and ROUGE-L (0.42) but demonstrates limited semantic understanding with METEOR (0.18) and SPICE (0.07). M2 improves with higher METEOR (0.24) and CIDEr (0.62), although its BLEU scores remain low. The proposed model achieves the highest CIDEr (1.10) and SPICE (0.25), reflecting superior semantic understanding and better capture of object relationships. Despite a lower BLEU (0.40), it significantly outperforms traditional methods in caption quality. To further validate these results, we conducted an expert-based evaluation to assess semantic accuracy, visual grounding, and caption usefulness. The proposed model achieved 93% accuracy in expert evaluations across 500 images, indicating strong contextual alignment with human interpretation. Additionally, we employed exploratory data analysis to examine and visualize the text captions, aiming to gain a deeper understanding of the optimal caption.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Institute of Computing, Kohat University of Science and Technology, Kohat, Pakistan.
- Bristol Research and Innovation Laboratory (BRIL), Toshiba Europe Ltd., Bristol, England.
- School of Business, South East Technological University (SETU), Waterford, Ireland.
- Data Science Institute, University of Galway, Galway, Ireland.
ORCID-Profile: Muhammad Danyal, Abdul Shahid, Muhammad Yahya
Zitieren
APA
Danyal, M., Roman, M., Shahid, A., & Yahya, M. (2026). Contextual image caption creation using object positional embedding and generative models. PLOS One, 21(7), e0353466. https://doi.org/10.1371/journal.pone.0353466
Vancouver
Danyal M, Roman M, Shahid A, Yahya M. Contextual image caption creation using object positional embedding and generative models. PLOS One. 2026;21(7):e0353466. doi:10.1371/journal.pone.0353466
BibTeX
@article{Danyal2026,
author = {Danyal, Muhammad and Roman, Muhammad and Shahid, Abdul and Yahya, Muhammad},
title = {Contextual image caption creation using object positional embedding and generative models},
journal = {PLOS One},
year = {2026},
volume = {21},
number = {7},
pages = {e0353466},
doi = {10.1371/journal.pone.0353466}
}
EUVIMED