Chellapilla V. K. N. S. N. Moorthy
Vasavi College of Engineering

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

SEM and TEM images’ dehazing using multiscale progressive feature fusion techniques Chellapilla V. K. N. S. N. Moorthy; Mukesh Kumar Tripathi; Suvarna Joshi; Ashwini Shinde; Tejaswini Kishor Zope; Vaibhavi Umesh Avachat
Indonesian Journal of Electrical Engineering and Computer Science Vol 33, No 3: March 2024
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v33.i3.pp2007-2014

Abstract

We present a highly effective algorithm for image dehazing that leverages the valuable information within the hazy image to guide the haze removal process. Our proposed algorithm begins by employing a neural network that has been trained to establish a mapping between hazy images and their corresponding clear versions. This network learns to identify the shared structural elements and patterns between hazy and clear images through the training process. To enhance the utilization of guidance information from the generated reference image, we introduce a progressive feature fusion module that combines the features extracted from the hazy image and the reference image. Our proposed algorithm is an effective solution for image dehazing, as it capitalizes on the guidance information in the hazy appearance. By combining the strengths of deep learning, progressive feature fusion, and end-to-end training, we achieve impressive results in restoring clear images from hazy counterparts. The practical applicability of our algorithm is further validated by its success on benchmark data sets and real-world SEM and TEM images.