Colorizing Images using CNN in Machine Learning


Authors : Siddhartha Kaushik; Ujjwal Jagtiani; Vinamra Kumar Jain; Suresh kumar; Javed Miya

Volume/Issue : Volume 6 - 2021, Issue 7 - July

Google Scholar : http://bitly.ws/9nMw

Scribd : https://bit.ly/3y6vtFz

Our research paper proposes a model of fully automatic Convolutional Neural Network for converting greyscale image to colored image. The issue is under constrained, because of which earlier methodologies have either resulted in unsaturated color production or relied on considerable user involvement. Our deep neural network introduces a fusion layer that allows us to effectively merge low-level information extracted from multiple small image patches with overall features extracted from the entire image. The makes a direct use the greyscale image (L channel) and predicts A and B channels for LAB color space. The predicted values of AB channel are concatenated with the input L channel and then it is converted to RGB color space for visualization. Additionally, our model can take and process images of any resolution, this makes our model different from other approaches based on CNN. We compare our approach against the state of the art [Z Cheng’s Model] and validate the results with a user study, where we demonstrate considerable improvements.

Keywords : Colorization, Convolutional Neural Network, Machine Learning

CALL FOR PAPERS


Paper Submission Last Date
30 - November - 2021

Paper Review Notification
In 1-2 Days

Paper Publishing
In 2-3 Days

Never miss an update from Papermashup

Get notified about the latest tutorials and downloads.

Subscribe by Email

Get alerts directly into your inbox after each post and stay updated.
Subscribe
OR

Subscribe by RSS

Add our RSS to your feedreader to get regular updates from us.
Subscribe