Fish and Fish Part Detection

This dataset is an enhancement version of the dataset used in [1], containing 600 images with 4486 annotations. The annotations for objects detected are fish heads, 1602 fishtails, and 1004 intact fish. It is used for object detection experiments using the YOLO model. Furthermore, it can be used for other models by first converting annotations to the required format.

[1] Prasetyo, E., Suciati, N., Fatichah, C., 2021. Yolov4-tiny and Spatial Pyramid Pooling for Detecting Head and Tail of Fish, in: International Conference on Artificial Intelligence and Computer Science Technology (ICAICST). pp. 157–161, doi: 10.1109/ICAICST53116.2021.9497822.

For use this dataset, please cite the following related articles:

Prasetyo, E., Suciati, N., Fatichah, C., 2022. Yolov4-tiny with Wing Convolution Layer for Detecting Fish Body Part. Computers and Electronics in Agriculture.