UGC Approved Journal no 63975(19)

ISSN: 2349-5162 | ESTD Year : 2014
Call for Paper
Volume 11 | Issue 3 | March 2024

JETIREXPLORE- Search Thousands of research papers



WhatsApp Contact
Click Here

Published in:

Volume 9 Issue 5
May-2022
eISSN: 2349-5162

UGC and ISSN approved 7.95 impact factor UGC Approved Journal no 63975

7.95 impact factor calculated by Google scholar

Unique Identifier

Published Paper ID:
JETIR2205719


Registration ID:
402740

Page Number

g173-g179

Share This Article


Jetir RMS

Title

Effective Approaches for Auto-Colorization of Grayscale Images Using No GANs

Abstract

In centuries the images or pictures was drawn by manual process with human intervention. However, the technology evolved and photography was first invented and images were captured by low end resolution cameras which were black and white images. However, enhancing the black and white images into color images was an extension research in the field of computer vision and machine learning techniques. Auto-Colorization of a grayscale image has been an imminent topic in the image processing and also an interesting area to explore over the recent years with the importance given to achieve the artifact-free quality. It is being used to improve the visual appealing of images like the grayscale photos, historic illusions, degraded images or videos. In this article, we aim to perform auto-colorization by taking a grayscale image as an input and generate a realistic colorized output image using convolutional neural network (CNN) and generative adversarial network (GAN). Both these proposed models tries to map grayscale image with their respective RGB colour format. The proposed models are trained on the standard dataset Flickr by ourselves with 30k images having 200X200 resolutions. The obtained result is compared using the adam optimizer and root means squared error and is clearly stated that the performance of auto-colorization of the generative adversarial network is better when compared with convolutional neural network model.

Key Words

Auto-colorization, Generative adversarial network, generator, discriminator, Root mean squared error, Convolutional neural network

Cite This Article

"Effective Approaches for Auto-Colorization of Grayscale Images Using No GANs", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.9, Issue 5, page no.g173-g179, May-2022, Available :http://www.jetir.org/papers/JETIR2205719.pdf

ISSN


2349-5162 | Impact Factor 7.95 Calculate by Google Scholar

An International Scholarly Open Access Journal, Peer-Reviewed, Refereed Journal Impact Factor 7.95 Calculate by Google Scholar and Semantic Scholar | AI-Powered Research Tool, Multidisciplinary, Monthly, Multilanguage Journal Indexing in All Major Database & Metadata, Citation Generator

Cite This Article

"Effective Approaches for Auto-Colorization of Grayscale Images Using No GANs", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.9, Issue 5, page no. ppg173-g179, May-2022, Available at : http://www.jetir.org/papers/JETIR2205719.pdf

Publication Details

Published Paper ID: JETIR2205719
Registration ID: 402740
Published In: Volume 9 | Issue 5 | Year May-2022
DOI (Digital Object Identifier):
Page No: g173-g179
Country: VIZIANAGARAM, ANDHRA PRADESH, India .
Area: Engineering
ISSN Number: 2349-5162
Publisher: IJ Publication


Preview This Article


Downlaod

Click here for Article Preview

Download PDF

Downloads

000314

Print This Page

Current Call For Paper

Jetir RMS