Weed-Detection-Model-Using-Deep-Learning.

Dataset: V2 Plant Seedlings Dataset (https://www.kaggle.com/vbookshelf/v2-plant-seedlings-dataset).

Overview:

1. Developed a deep learning model utilizing Convolutional Neural Network (CNN) layers, achieving a training accuracy of 98.02% over 8 epochs.
2. Preprocessed and standardized a dataset comprising 5,539 images of crop and weed seedlings, grouped into 12 classes representing common plant species in Danish agriculture.
3. Evaluated model performance using precision, recall, and F1-score metrics, achieving an average precision of 81% across classes.
4. Contributed to agricultural practices by providing an effective tool for weed detection, potentially aiding in maximizing crop yield and reducing yield losses due to weed interference.