Eagal Vision: Identification of Ice-Ice Disease in Agal-Agal (Kappaphycus Alvarezii) using YOLOv5

Seaweed farming is a vital industry in coastal communities, significantly contributing to local economies and global production. Ice-Ice Disease in Agal-Agal poses a major challenge, leading to decreased seaweed quality and reduced market value. Many seaweed farmers lack the necessary tools and procedures to assess seaweed quality effectively, resulting in lower-value yields and economic losses. This paper presents a study identifying Ice-Ice Disease in Agal-Agal using YOLOv5. It introduces a system that analyzes seaweed images to identify healthy and diseased ones, helping farmers quickly spot and remove affected seaweed to improve their harvest. In this study, an image dataset of healthy and Ice-Ice Disease affected seaweeds was collected from a seaweed farm using a camera positioned at a constant height. These images were then used to train a YOLOv5-based detection model integrated with a Raspberry Pi 5 microcontroller. The model accurately and efficiently assesses seaweed quality, enabling farmers to identify and select high-quality seaweed, resulting in improved market value and profitability. Experimental results indicate that the system performs well in distinguishing high-quality seaweed from diseased ones, achieving an accuracy of 96.65%. This result demonstrates the effectiveness of the system as a practical and scalable solution for improving seaweed farming standards and increasing profitability.