Waste and Natural Image Classification Using Transfer Learning

Computer Engineering

Natural disasters can have a profound and wide-ranging influence on humans, affecting individuals, communities, and societies in numerous ways, encompassing physical, mental, economic, and social aspects. Classifying images of natural disasters using machine learning algorithms can offer significant assistance to humans in various ways by providing valuable insights and support in disaster management and response efforts. Annually, the Earth produces 2.01 billion metric tons of municipal solid waste, and at the very least, a very conservative estimate suggests that approximately 33 percent of this waste is not handled in an environmentally sound manner. Looking ahead to the future, it is anticipated that global waste production will reach 3.40 billion metric tons by 2050, which is more than double the rate of population growth during the same period. Waste image classification has the potential to enhance waste management practices, increase recycling rates, reduce environmental pollution, and support sustainable development. A Convolutional Neural Network is a type of machine learning algorithm, more precisely, a type of artificial neural network specifically designed for tasks involving images and visual data. CNNs have revolutionized computer vision and image processing applications due to their ability to automatically learn and extract meaningful features from images. This compilation of contemporary research encompasses academic papers and articles addressing the diverse algorithms employed in the classification of images related to both natural disasters and waste. This literature review also includes papers discussing algorithms used in image classification and covers papers on convolution neural network.

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.