The waste classification system is an important tool for managing and controlling the generation, handling, and disposal of waste materials. This system is designed to categorize waste based on its properties, potential risks, and environmental impacts. By accurately classifying waste, it becomes easier to identify the most appropriate treatment and disposal methods and minimize the negative impacts of waste on human health and the environment. The waste classification system using Convolutional Neural Networks (CNNs) is a computer vision-based approach that can automatically identify and sort waste materials into different categories, such as plastic, paper, glass, and metal. This paper proposes a system that uses a deep learning model trained on a large dataset of waste images to recognize and classify different types of waste with good accuracy. This system presents the waste classification system using CNN, which describes the design and implementation of the system, including the CNN architecture, training process, and testing results. The proposed system is built on Raspberry Pi. The camera is used to capture images of waste and make a record of three types of waste i.e. paper, plastic, and metal. Overall, the proposed system can provide an efficient and reliable solution to the waste management industry by reducing the time and cost of waste sorting and improving the accuracy and efficiency of the process.