Chakrit Watcharopas
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Chakrit Watcharopas has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
- Pakaket Wattuya
Department of Computer Science, Faculty of Science, Kasetsart University, Bangkok, Thailand
2 shared publications - Akarapon Lertwiputh
Department of Computer Science, Faculty of Science, Kasetsart University, Bangkok, Thailand
1 shared publication Panthira Jansakra
Department of Forest Products, Kasetsart University, Bangkok, Thailand
1 shared publicationPhichit Somboon
Department of Forest Products, Kasetsart University, Bangkok, Thailand
1 shared publication- Tanachot Chirakitsakul
Department of Computer Science, Kasetsart University, Bangkok, Thailand
1 shared publication
Latest Publications
- Open Access
- 21 April 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 74634-74646
Integration of Convolutional Neural Network and Image Processing for Pulp Fibril Detection and Measurement
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.
- 21 April 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 74634-74646
Open AccessIntegration of Convolutional Neural Network and Image Processing for Pulp Fibril Detection and Measurement
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.
- Open Access
- 26 July 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-6
Forecasting of photovoltaic power using deep learning
- 26 July 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-6
Open AccessForecasting of photovoltaic power using deep learning