This study proposes an improved deep convolutional neural network (DCNN) for organic and recyclable waste classification to enhance the efficiency and accuracy of waste segregation. The dataset consists of 25,077 images divided into 70% training and 30% testing. The model uses LeakyReLU as the activation function and dropout for regularization. Experimental results show that the proposed model achieves an accuracy of 93.28%, outperforming other models like VGG16, VGG19, MobileNetV2, DenseNet121, and EfficientNetB0. The model's performance is evaluated using accuracy, missed detection rate (MDR), and false detection rate (FDR). The study highlights the importance of hyper-parameter tuning and the effectiveness of the proposed DCNN in reducing MDR and FDR. The results demonstrate that the improved DCNN provides a more accurate and efficient solution for waste classification, contributing to better recycling processes and environmental protection. The study also discusses the challenges in waste classification, including data imbalance and the need for robust models that can handle varying conditions. The proposed method offers a promising approach for automated waste segregation, improving resource efficiency and reducing environmental impact.This study proposes an improved deep convolutional neural network (DCNN) for organic and recyclable waste classification to enhance the efficiency and accuracy of waste segregation. The dataset consists of 25,077 images divided into 70% training and 30% testing. The model uses LeakyReLU as the activation function and dropout for regularization. Experimental results show that the proposed model achieves an accuracy of 93.28%, outperforming other models like VGG16, VGG19, MobileNetV2, DenseNet121, and EfficientNetB0. The model's performance is evaluated using accuracy, missed detection rate (MDR), and false detection rate (FDR). The study highlights the importance of hyper-parameter tuning and the effectiveness of the proposed DCNN in reducing MDR and FDR. The results demonstrate that the improved DCNN provides a more accurate and efficient solution for waste classification, contributing to better recycling processes and environmental protection. The study also discusses the challenges in waste classification, including data imbalance and the need for robust models that can handle varying conditions. The proposed method offers a promising approach for automated waste segregation, improving resource efficiency and reducing environmental impact.