Flatfish lesion detection based on part segmentation approach and lesion image generation

Abstract

The flatfish is a major farmed species consumed globally in large quantities. However, due to the densely populated farming environment, flatfish are susceptible to lesions and diseases, making early lesion detection crucial. Traditionally, lesions were detected through visual inspection, but observing large numbers of fish is challenging. Automated approaches based on deep learning technologies have been widely used to address this problem, but accurate detection remains difficult due to the diversity of the fish and the lack of a fish lesion and disease dataset. This study augments fish lesion images using generative adversarial networks and image harmonization methods. Next, lesion detectors are trained separately for three body parts (head, fins, and body) to address individual lesions properly. Additionally, a flatfish lesion and disease image dataset, called FlatIMG, was created and verified using the proposed methods on the dataset. A flash salmon lesion dataset was also tested to validate the generalizability of the proposed methods. The results achieved 12% higher performance than the baseline framework. This study is the first attempt to create a high-quality flatfish lesion image dataset with detailed annotations and proposes an effective lesion detection framework. Automatic lesion and disease monitoring can be achieved in farming environments using the proposed methods and dataset.