Classifying Biodegradable and Non-Biodegradable Waste using a Pretrained VGG16 Model

This research explores the development of an automated waste segregation system using the VGG16 model, aimed at accurately classifying waste into biodegradable and non-biodegradable categories. Leveraging transfer learning, the pre-trained VGG16 model was fine-tuned on a dataset of waste images, allowing it to effectively distinguish between different types of waste based on their visual features. The study involved a systematic approach to data collection, preprocessing, model training, and evaluation, ensuring robust performance. The results demonstrated a consistent improvement in both training and validation accuracy, with final accuracies exceeding 90%. Despite a brief challenge of overfitting observed during the mid-training phase, the model successfully overcame it, achieving high accuracy and low loss by the final epochs. This suggests that the VGG16-based system can reliably automate waste segregation, potentially enhancing efficiency and accuracy in waste management practices. The research highlights the model’s potential for practical application, contributing to more sustainable and effective waste management solutions.