Image-Based Classification of Freshwater Fish Species to Support Feed Recommendation Using Random Forest

Accurate identification of freshwater fish species plays a vital role in aquaculture, particularly in determining appropriate feed strategies to optimize fish growth. Visual similarities among species—such as color, shape, and surface texture—often hinder novice farmers from correctly recognizing fish types. This study proposes an image-based classification system using the Random Forest algorithm to identify six freshwater fish species: pomfret (bawal), gourami (gurame), catfish (lele), barb (melem), tilapia (nila), and Java barb (tawes) and provide automated feed recommendations. A total of 120 fish images were used as the dataset, collected from various sources, including online repositories and field documentation. Feature extraction was applied to capture color characteristics (HSV), texture patterns (GLCM), and morphological features (regionprops). The model was trained on 70% of the dataset and tested on the remaining 30%. Evaluation results show that the system achieved a classification accuracy of 83.33%, with a precision of 83.53%, recall of 83.33%, and an F1-score of 82.86%. Notably, catfish, barb, and tilapia classes achieved perfect classification, while pomfret and gourami showed room for improvement due to overlapping visual features. The findings indicate that the integration of Random Forest with multi-domain image features offers an effective, affordable, and practical solution to support the digital transformation of small and medium scale aquaculture systems through intelligent species recognition and feed guidance