Detection of Bovine Species on Image Using Machine Learning Classifiers

There are too many cattle in the world and breeds of cattle. For someone who is new to breeding, it may be difficult tell which species their are. In some cases, an experienced person not understand two that similar appearance. this study, aim classify with image processing methods mobile applications written Flutter TensorFlow Lite. classifying breeds, The VGG-16 algorithm was used for feature extraction. XGBoost Random Forest algorithms were classification combined versions compared. addition, SMOTE augmentation prevent imbalance dataset, performance results Images different from farms obtained dataset prepared, then trained models tested models. As a result tests, it’s best model VGG16+Random Forest+SMOTE+Augmentation 88.77% accuracy study. application, first detected pre-trained object detection model, breed on made model.