Shrimp Body Weight Estimation in Aquaculture Ponds Using Morphometric Features Based on Underwater Image Analysis and Machine Learning Approach

Shrimp is a marine culture found globally due to the ability of its yields boost country's economy. It imperative monitor size determine condition shrimp underwater with complex noise using non-invasive method. Therefore, this study aims develop new method for measuring body weight morphometric features based on image analysis and machine learning approach. The used consists several steps, data collection an camera, grayscale, binary, edge detection, region interest extraction, camera calibration Triangle Similarity (TS), Correction Factor (CF), calculation value, create model, training data, testing estimation weight. After get best accuracy value RMSE = 0.05, MAE 0.04, R2 0.96 from MLR In conclusion, results showed that hybrid TS-CF-MLR lowest error rate highest coefficient determination.