A Comparative Study of Prediction Models for Tomato Plant Stages Dataset

Tomato cultivation is of significant agricultural importance worldwide. Monitoring the growth stages of tomato plants is crucial for optimizing cultivation practices and ensuring a healthy yield. In this study, we propose a novel Tomato Plant Stages Detection System utilizing deep learning algorithms, including Custom CNN, ResNet50, VGG16, InceptionV3, EfficientNetB0, and MobileNetV2,YOLOV3. We collected a specialized dataset comprising images of tomato plants at two distinct growth stages from the fields of the Tamil Nadu Agricultural University (TNAU),Coimbatore. The dataset encompasses various environmental conditions and growth variations typical of field settings. Our proposed system aims to automate the identification of tomato plant stages, enabling farmers to make informed decisions regarding crop management.