Please use this identifier to cite or link to this item: http://hdl.handle.net/2080/4033
Title: Image Defogging based on combined Sparse Gradient Minimization and CNN Architecture
Authors: Jana, Anisha
Sahoo, Upendra Kumar
Keywords: Defogging
image enhancement
convolution neural network (CNN)
sparse gradient minimization (SGM)
atmospheric scattering model (ASM)
Issue Date: May-2023
Citation: International Conference on Microwave, Optical and Communication Engineering, 26-28 May 2023, IIT, Bhubaneswar, India
Abstract: Some environmental factors like haze or fog de-grades the quality of the image. These factors affect some real time processes such as object detection and recognition, automated vehicles and remote sensing which needs clear visible images for making critical decisions. Therefore, restoring the true image from the foggy image becomes significant. Now with the advancement in image processing, many image defogging and dehazing algorithms has been developed to improve the quality of the image. Many standard filtering techniques such as high boost filter, homomorphic filter can be used for image defogging but it fails to restore the foggy images completely so some advanced techniques like dark channel prior, decomposition techniques, convolution network-based algorithms are used. Image quality assessment (IQA) is done to measure the quality of the defogged image. These performance metrics mainly includes mean squared error (MSE), structural similarity index metric (SSIM),peak signal to noise ratio (PSNR).
Description: Copyright belongs to proceedings publisher
URI: http://hdl.handle.net/2080/4033
Appears in Collections:Conference Papers

Files in This Item:
File Description SizeFormat 
2023_AJana_ICMOCE_Image.pdf449.19 kBAdobe PDFView/Open


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.