147905-Thumbnail Image.png
Description

This paper is centered on the use of generative adversarial networks (GANs) to convert or generate RGB images from grayscale ones. The primary goal is to create sensible and colorful versions of a set of grayscale images by training a

This paper is centered on the use of generative adversarial networks (GANs) to convert or generate RGB images from grayscale ones. The primary goal is to create sensible and colorful versions of a set of grayscale images by training a discriminator to recognize failed or generated images and training a generator to attempt to satisfy the discriminator. The network design is described in further detail below; however there are several potential issues that arise including the averaging of a color for certain images such that small details in an image are not assigned unique colors leading to a neutral blend. We attempt to mitigate this issue as much as possible.

303.45 KB application/pdf

Download restricted. Please sign in.
Restrictions Statement

Barrett Honors College theses and creative projects are restricted to ASU community members.

Details

Title
  • Using Neural Networks to Perform Colorwork on Images
Contributors
Date Created
2021-05
Resource Type
  • Text
  • Machine-readable links