No Detail Found!

An efficient convolutional neural network based image colorization technique

Author(s)
Muhammad Wasim UIT University, Karachi, Pakistan
Lubaid Ahmed UIT University, Karachi, Pakistan
Muhammad Saad Najib UIT University, Karachi, Pakistan
Muhammad Talha Khalil UIT University, Karachi, Pakistan
Mohammad Waiz Ali UIT University, Karachi, Pakistan
Ali Ahmed Khan UIT University, Karachi, Pakistan
Abstract
Color in any image plays a vital role in better understanding and real image visualization. In the past when there was no concept of colored images, each black-and-white image need to highlight its own merits to explain an image in a better way. But when the concept of colored images started things changed. The color image is used to describe and highlight key features and attributes of an image in a better and more effective manner. The key issue is that the old images and videos are colored and in some cases, it needs to be colorized. There are several applications, which use to color a gray-scale image. The paper presented an efficient deep learning-based image colorization technique. The proposed system maps all the gray contrast pixels of the image into their corresponding colored pixels to produce a colored image using the Convolutional Neural Network technique. The proposed system is automated and avoids any manual work or user hand-define rules. The system tested around 100 images and found an accuracy of about 95%.
Publication Details
Page(s) 82-92
DOI 10.51153/kjcis.v6i1.159
Published Journal: KIET Journal of Computing & Information Sciences, Volume: 6, Issue: 1, Year: 2023

Request the full text from PASTIC

Keywords
Convolutional Neural Network, Image, features, gray-scale, colorization
More from KIET Journal of Computing & Information Sciences
0

Citations

0

Downloads

76

Views

Copyright ©  PASTIC National Center, Islamabad www.pastic.gov.pk