Detection and identification of Red Snapper (Lutjanus gibbus and Lutjanus malabaricus) and grouper (Plectropomus leopardus and Plectropomus maculatus) with deep learning

Abstract

The Indonesian fishing industry is a major global contributor, particularly in the production and export of snapper and grouper fish. These two groups of fish are known for their high diversity, but distinguishing between the different species can be challenging due to their morphological similarities. In order to overcome this challenge, this paper proposes the application of deep learning methods to identify the two major species of snapper and grouper accurately. The deep learning framework utilized in this study is Detectron2, a state-of-the-art object detection and segmentation model. The datasets used in the study consist of 500 images each for the snapper species Lutjanus gibbus and Lutjanus malabaricus, and the grouper species Plectropomus leopardus and Plectropomus maculatus, totaling 2000 images. The datasets were labeled using Coco Annotator software with a focus on species segmentation. The labeled datasets were then trained using Google Collaboratory, resulting in an accuracy value of 89.51%, a precision of 87.69%, a recall of 99.85%, and an F1-score of 93.38%. These results demonstrate that, even with a relatively limited number of datasets, it is possible to accurately identify the Red Snapper Lutjanus gibbus and Lutjanus malabaricus, as well as the grouper species Plectropomus leopardus and Plectropomus maculatus using deep learning methods. In conclusion, this paper demonstrates the potential of deep learning methods, specifically Detectron2, in accurately identifying snapper and grouper species. The results of this study suggest that this technology can be used to improve the accuracy and efficiency of fish species identification, which could have significant implications for the fishing industry and marine conservation efforts.