Plastic waste pollution poses a significant environmental threat, harming ecosystems and wildlife. While recycling offers a solution, sorting different types of waste remains a challenge. This work proposes a Deep Learning (DL) approach using computer vision to automate solid waste identification and classification within a multi-category recycling system, aiming to improve sorting efficiency and reduce the amount of plastic and other solid waste ending up in landfills. We present the development a Convolutional Neural Network (CNN) designed for accurate waste classification from image data, thereby enabling fully automated smart bin operation. We applied different optimization techniques on several CNN architectures, including transfer learning and data augmentation, to improve the classification accuracy and computational efficiency. Our experimental results demonstrate that the proposed model achieves high accuracy in classifying plastic waste but also metal, paper, cardboard and glass. This research demonstrates that Artificial Intelligence (AI) in the form of Deep Learning has the potential to significantly contribute to a more sustainable waste management system.