An Attention-Enhanced Deep Learning Framework for Automated Quality Grading of Ribbed Smoked Rubber Sheets

D. P. Sumalatha; M. L. Smitha; U. J. Ujwal

doi:10.48084/etasr.16066

Authors

D. P. Sumalatha Department of Computer Science and Engineering, KVG College of Engineering, Sullia, Karnataka, India
M. L. Smitha Department of Computer Science and Engineering, KVG College of Engineering, Sullia, Karnataka, India
U. J. Ujwal Department of Computer Science and Engineering, KVG College of Engineering, Sullia, Karnataka, India

Volume: 16 | Issue: 2 | Pages: 32921-32927 | April 2026 | https://doi.org/10.48084/etasr.16066

Received: 6 November 2025 | Revised: 12 December 2025 | Accepted: 29 December 2025 | Online: 4 February 2026

Corresponding author: D. P. Sumalatha

Abstract

The grading of Ribbed Smoked Rubber Sheets (RSS) plays a critical role in ensuring consistency, quality, and market value within the natural rubber industry. Traditional manual inspection methods are subjective, time-consuming, and prone to human error. With the increasing demand for standardized systems, there is a need for automating the RSS grading process using vision-based techniques. This study proposes an Attention-Enhanced Deep Learning Framework (AEDL-RSS) that combines convolutional feature extraction with spatial and channel attention modules to enhance robustness against lighting, color variation, and surface defects. The model integrates an attention-augmented Convolutional Neural Network (CNN) backbone and a lightweight classifier for real-time deployment. The experimental results demonstrate that the proposed system outperforms the baseline VGG16 model, achieving a classification accuracy of 95% on the test set. The system provides a reliable, scalable, and objective alternative to manual inspection, offering potential for real-time industrial deployment and smart factory integration in the rubber processing sector.

Keywords:

attention mechanism, CBAM, CNN, deep learning, K-Fold cross-validation, rubber sheet grading

Downloads

Download data is not yet available.

References

N. Hütten, M. Alves Gomes, F. Hölken, K. Andricevic, R. Meyes, and T. Meisen, "Deep Learning for Automated Visual Inspection in Manufacturing and Maintenance: A Survey of Open-Access Papers," Applied System Innovation, vol. 7, no. 1, Jan. 2024, Art. no. 11. DOI: https://doi.org/10.3390/asi7010011

Z. Niu, G. Zhong, and H. Yu, "A Review on the Attention Mechanism of Deep Learning," Neurocomputing, vol. 452, pp. 48–62, Sep. 2021. DOI: https://doi.org/10.1016/j.neucom.2021.03.091

D. Soydaner, "Attention Mechanism in Neural Networks: Where It Comes and Where It Goes," 2022. DOI: https://doi.org/10.1007/s00521-022-07366-3

I. Fibriani, Sumardi, A. B. Satriya, and S. B. Utomo, "Colour Based Image Processing Method for Recognizing Ribbed Smoked Sheet Grade," IOP Conference Series: Materials Science and Engineering, vol. 185, Mar. 2017, Art. no. 01202. DOI: https://doi.org/10.1088/1757-899X/185/1/012025

R. F. Rahmat, A. F. Pulungan, S. Faza, and R. Budiarto, "Image Classification of Ribbed Smoked Sheet Using Learning Vector Quantization," Journal of Physics: Conference Series, vol. 801, Jan. 2017, Art. no. 012050. DOI: https://doi.org/10.1088/1742-6596/801/1/012050

Z. Arifin, E. Y. Madya Mukti, A. Jehan Tamamy, and M. Ary Heryanto, "Classification of RSS (Ribbed Smoke Sheet) Based on Presence or Absence of Fungus Using the NN (Neural Network) Perceptron Method," in 2020 International Seminar on Application for Technology of Information and Communication, Semarang, Indonesia, Sep. 2020, pp. 359–363. DOI: https://doi.org/10.1109/iSemantic50169.2020.9234277

C. Pornpanomchai and N. Chantharangsikul, "Ribbed Smoked Sheet Grading System (RSSGS)," in 2010 International Conference on Electronics and Information Engineering, Kyoto, Japan, Aug. 2010, pp. V1-128-V1-132. DOI: https://doi.org/10.1109/ICEIE.2010.5559907

B. Suksawat and P. Komkum, "Pineapple Quality Grading Using Image Processing and Fuzzy Logic Based on Thai Agriculture Standards," in 2015 International Conference on Control, Automation and Robotics, Singapore, May 2015, pp. 218–222. DOI: https://doi.org/10.1109/ICCAR.2015.7166035

H. S. Choi, J. B. Cho, S. G. Kim, and H. S. Choi, "A Real-Time Smart Fruit Quality Grading System Classifying by External Appearance and Internal Flavor Factors," in 2018 IEEE International Conference on Industrial Technology, Lyon, France, Feb. 2018, pp. 2081–2086. DOI: https://doi.org/10.1109/ICIT.2018.8352510

H. Wang, "Garbage Recognition and Classification System Based on Convolutional Neural Network VGG16," in 2020 3rd International Conference on Advanced Electronic Materials, Computers and Software Engineering, Shenzhen, China, Apr. 2020, pp. 252–255. DOI: https://doi.org/10.1109/AEMCSE50948.2020.00061

S. Choudhury and A. Agarwal, "Mango Disease Classification Using CNN," in International Conference on Emerging Techniques in Computational Intelligence, Hyderabad, India, pp. 1-6, Sep. 2023. DOI: https://doi.org/10.1109/ICIICS59993.2023.10421401

S. Woo, J. Park, J.-Y. Lee, and I. S. Kweon, "CBAM: Convolutional Block Attention Module," in Computer Vision – ECCV 2018, vol. 11211, V. Ferrari, M. Hebert, C. Sminchisescu, and Y. Weiss, Eds. Cham, Switzerland: Springer International Publishing, 2018, pp. 3–19. DOI: https://doi.org/10.1007/978-3-030-01234-2_1

R. Kohavi, "A Study of Cross-Validation and Bootstrap for Accuracy Estimation and Model Selection," in 14th International Joint Conference on Artificial Intelligence, Montréal, QC, Canada, Aug. 1995, pp. 1137–1143.

K. Simonyan and A. Zisserman, "Very Deep Convolutional Networks for Large-Scale Image Recognition." arXiv, 2014.