Project Description

This project, AI Image Colorization, focuses on using machine learning techniques to automatically colorize black-and-white images. Conducted over six months (August 2018 to January 2019), the project aimed to develop a model capable of predicting realistic colors for grayscale images. We followed a structured process, including data collection, neural network model creation, and multiple iterations to improve accuracy. A convolutional neural network (CNN) was employed to process image channels, and the project advanced to using UNET and GAN models for better results. This work was guided by Team Drishti, with future plans to enhance the model's capabilities using additional computing resources.