marcobendinelli/plants-classification-with-neural-networks

This project uses Deep Learning to classify plant species from images, exploring various techniques, including custom CNNs, pre-trained models, and transfer learning

Neural Networks for Plant Species Classification 🍀

The project delves into the realm of deep learning to tackle the challenge of classifying plant species from images. By leveraging advanced Neural Networks, the most accurate models for this classification task are identified.

Plant images are categorized based on the species they belong to, and the objective is to predict the correct class label for a given image, essentially making it a classification problem.

Various techniques are explored, including:

• Custom Convolutional Neural Networks tailored for our specific task.
• Utilization of pre-trained models like VGG16.
• Transfer learning and fine-tuning techniques, to adapt pre-trained models to the plant species classification problem.

The full Report is available here

Confusion Matrix

Key Metrics:

• Accuracy: 89.72%
• Precision: 90.59%
• Recall: 87.35%
• F1-score: 88.42%

Our analysis reveals promising results, with high accuracy, precision, recall, and F1-score, demonstrating the effectiveness of our deep learning approach in classifying plant species accurately.