A Sustainable Approach to Waste Segregation – ResNet vs. MobileNet

It is uncertain how much waste is produced in the neighborhood or city, and the overflow or spill of trash from the bins contaminates the land. The precise type of waste that needs to be identified is difficult to determine. The current method takes longer to identify the specific waste and predictive image classification is trailing. To address this issue, image classification is performed using a ResNet model and MobileNet. Garbage pictures are used to train and test the entire architecture. The convolution neural network is linked to a model, which has been trained on images of metal, trash, plastic, paper, cardboard, and glass.