According to the World Bank report, waste is one of the problems that the world is facing. Image classification is one of the fields of machine learning that is capable of classifying waste based on its type. One of the most widely popular used classifications is the CNN algorithm which is a deep learning algorithm. In this study, we will perform a comparative analysis of the performance of the CNN algorithm with the MLP algorithm in terms of classifying waste types. From the research we did, CNN got a better performance where the results of precision, recall, f1-score, and accuracy were 0.98 and the CNN model was more effective in classifying waste based on its class.