Bimodal Feature Enhancement‐Driven Deep Learning Model for Ceramic Surface Roughness Prediction
Journal of the American Ceramic Society · 2026-03 · 109 (3)
DOI: 10.1111/jace.70558 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of the American Ceramic Society, online erschienen am 27.02.2026. Verfasst von Xuwei Du und 9 weiteren Autor:innen. Die Arbeit nennt 31 Literaturangaben. Gefördert von: National Key Research and Development Program of China.
Abstract (Originalsprache)
Real‐time and efficient surface roughness detection is crucial in modern manufacturing. Noncontact measurement based on machine vision has attracted considerable attention owing to its high efficiency and strong adaptability. However, the reflection characteristics of the same surface vary under different light sources. To address this issue, a roughness dataset is constructed using zirconia, alumina, and ZTA materials, which is imaged under various light sources (white, red, green, and blue). We propose a novel bimodal feature fusion method based on the YOLOv8 network, termed DAM‐YOLO. Specifically, we construct a bimodal feature fusion module (DAM) that integrates the channel attention mechanism (CAM) and the spatial attention mechanism (SAM). Leveraging bimodal image inputs, DAM enhances the feature maps of single modalities by exploiting the intermodal dependency relationships, thereby strengthening the mixed spatial‐channel weights of cross‐modal fusion outputs. By fusing cross‐modal complementary features to refine the original unimodal features, DAM enables the formation of more discriminative features, ultimately generating highly representative bimodal feature maps. Furthermore, we integrate the online convolutional re‐parameterization (OREPA) and generalized efficient layer aggregation network (GELAN) modules into the detection network. This integration ensures that the model's feature extraction capability is significantly enhanced under the condition of low parameter complexity. Extensive experiments validate that the proposed DAM‐YOLO method achieves a mean average precision (mAP) of 0.993, which fully demonstrates the accuracy and effectiveness of our approach.
Förderung
- National Key Research and Development Program of China
Zitieren
APA
Du, X., Yao, P., Wang, Q., Qu, S., Zhou, P., Liu, X., Wang, T., Sun, Y., Chu, D., & Huang, C. (2026). Bimodal Feature Enhancement‐Driven Deep Learning Model for Ceramic Surface Roughness Prediction. Journal of the American Ceramic Society, 109(3). https://doi.org/10.1111/jace.70558
Vancouver
Du X, Yao P, Wang Q, Qu S, Zhou P, Liu X, et al. Bimodal Feature Enhancement‐Driven Deep Learning Model for Ceramic Surface Roughness Prediction. Journal of the American Ceramic Society. 2026;109(3). doi:10.1111/jace.70558
BibTeX
@article{Du2026,
author = {Du, Xuwei and Yao, Peng and Wang, Qilin and Qu, Shuoshuo and Zhou, Peifa and Liu, Xiang and Wang, Tingting and Sun, Yang and Chu, Dongkai and Huang, Chuanzhen},
title = {Bimodal Feature Enhancement‐Driven Deep Learning Model for Ceramic Surface Roughness Prediction},
journal = {Journal of the American Ceramic Society},
year = {2026},
volume = {109},
number = {3},
doi = {10.1111/jace.70558}
}
EUVIMED