<![CDATA[Waste management has become one of the most pressing environmental challenges due to the increasing volume of waste and the limited public awareness of proper waste segregation. The inability to distinguish between organic and inorganic waste often reduces the effectiveness of recycling and sustainable waste management practices. This study aims to develop an automatic image classification system based on the Convolutional Neural Network (CNN) method to identify organic and inorganic waste from digital images. The dataset consists of 25,077 images collected from publicly available sources and self-collected data, which were divided into 90% training data and 10% testing data. Before model training, the images underwent preprocessing techniques, including resizing, normalization, and data augmentation, to improve model performance and generalization. The CNN model was developed using the TensorFlow framework and achieved a training accuracy of 93.08% at the ninth epoch. Furthermore, the trained model was integrated into a Flask-based web application, enabling users to upload waste images and instantly receive classification results. The findings demonstrate that the proposed CNN-based system effectively classifies organic and inorganic waste images and has the potential to support intelligent waste management systems by improving the efficiency and accuracy of waste sorting. This research also highlights the applicability of deep learning techniques in addressing environmental issues through automated image recognition technology.]]>
