Image Colorization using Convolutional Neural Network

Abstract

With its advent and extension in many areas, technology has become crucially integrated with human lifestyle and activities. Various branches of technology have found ways to progress and they serve imperatively in various fields of development, entertainment and utility. Artificial Intelligence and domains within it encompass a huge portion of technological applications, and deep learning being a subset of AI can be used for many such implementations. Image colourisation is one such domain which can utilize the deep learning capabilities of a machine to effectively produce results. Colorization of gray-scale images is generally carried out using photo editing software and is a tedious and expensive job.With the collaboration of different pre-trained models in a baseline CNN model,, we analyzed the one with the highest accuracy and the least loss,comparing it to the others.Based on evaluation metrics such as root mean square error, loss, and accuracy, we determined that the best model is the one incorporating EFFicientB0. Hence, our project makes this process automated and accurate utilizing the convolutional neural architecture combined with EfficientNetB0. In this project, we have realized and implemented several compositions of the baseline CNN model with pre-trained models to deduce the best version.