Abstract- Image colorization is an emerging topic and a fascinating area of research in recent years. In this paper, we implemented deep learning algorithms to colorize black and white images. Convolutional autoencoder neural network and generative adversarial network (GAN) have been implemented on black and white images. The networks aim to convert the black and white images to their respective color format. The color format used for the implementation of the networks is RGB color space. The performance of the autoencoder model is evaluated using root means squared error, means squared error, means absolute error and colorization accuracy. The data used for the implementation of the networks consists of 7000 images in the RGB color space. The performance of the implemented autoencoder models and generative adversarial network is measured using mean absolute error. The colorization performance of the generative adversarial network is better that that of the autoencoder models.

Keywords: Autoencoders, Colorization, Generative adversarial Network, Generator, Discriminator, Mean squared error

| DOI: 10.17148/IARJSET.2022.9115