PAPER making! FROM THE PUBLISHERS OF PAPER TECHNOLOGY INTERNATIONAL ® FROM THE PUBLISHERS OF PAPER TEC Volume 11, Number 2, 2025
Integration of Convolutional Neural Network and Image Processing for Pulp Fibril Detection and Measurement TANACHOT CHIRAKITSAKUL 1,2 , PAKAKET WATTUYA 1,2 , PHICHIT SOMBOON 3 , PANTHIRA JANSAKRA 3 & CHAKRIT WATCHAROPAS 1,2 The fibrillation index is a critical metric in paper manufacturing, quantifying the degree of fibrillation achieved during the pulp refining process. Optimizing this metric enhances both paper quality and production efficiency. However, traditional measurement methods—such as manual visual examination of pulp samples under microscopy—are slow, error-prone, and labor-intensive, limiting their scalability in industrial applications. This study proposes a novel method that integrates deep learning with image processing techniques to automate fibril detection and fibrillation index computation. The proposed method leverages the discriminative capabilities of convolutional neural networks (CNNs) with adaptive image processing techniques to overcome key challenges such as low contrast, image noise, and variability in fibril morphology. The patch-based classification approach effectively filters out irrelevant objects, especially those whose features visually resemble fibrils, thus improving fibril segmentation accuracy. The method was comprehensively validated against expert-labeled ground truth images and achieved a promising average error rate of 0.4494 ± 0.4187. Experimental results also demonstrate the strong robustness of the proposed method, with consistent performance across diverse refining conditions and image qualities, making it suitable for real-world application in the pulp and paper industry. Furthermore, this study paves the way for broader applications in materials science and biomedical imaging, where precise feature detection in microscopic images is essential. Contact information: 1 Department of Computer Science, Kasetsart University, Bangkok 10900, Thailand. 2 Artificial Intelligence Technology and Innovation Center for Health, Faculty of Science, Kasetsart University, Bangkok 10900, Thailand. 3 Department of Forest Products, Kasetsart University, Bangkok 10900, Thailand.
IEEE Access, Vol.13, 74634-74646. DOI: 10.1109/ACCESS.2025.3562873 Creative Commons Attribution 4.0 International License
The Paper Industry Technical Association (PITA) is an independent organisation which operates for the general benefit of its members – both individual and corporate – dedicated to promoting and improving the technical and scientific knowledge of those working in the UK pulp and paper industry. Formed in 1960, it serves the Industry, both manufacturers and suppliers, by providing a forum for members to meet and network; it organises visits, conferences and training seminars that cover all aspects of papermaking science. It also publishes the prestigious journal Paper Technology International ® and the PITA Annual Review , both sent free to members, and a range of other technical publications which include conference proceedings and the acclaimed Essential Guide to Aqueous Coating .
Article 3 – Pulp Fibril Detection
Page 1 of 14
Made with FlippingBook. PDF to flipbook with ease