Detection of defects in wooden structures in the forestry industry has become a crucial area of research. Existing studies have focused on specific categories of wood defects, failing to provide a comprehensive classification for high-quality wood. Trained human operators currently perform a variety of wood quality in wood processing facilities. However, this human-dependent process leads to time and performance losses and inaccurate type. This study aims to address all these challenges in future intelligent production systems by targeting the detection of the fungus in oak wood, one of the wood defect classes. The algorithm created based on image processing utilizes median filtering, Canny edge detection, and masking technologies using the HSV color space. The algorithm then calculates the fungal area ratio to the wooden piece's surface area on the masked image to reach the final result. While existing studies in the literature are primarily based on deep learning methods, there has been limited focus on fungus detection. The novelty of this study, conducted on oak wood, lies in its use of a specific dataset, fungal detection, and image processing. An algorithm has been developed and presented in the literature that can be used in the software of future intelligent production systems in the forestry industry.