Image Restoration of Night Time Hazy Images.
Date of Submission
December 2020
Date of Award
Winter 12-12-2021
Institute Name (Publisher)
Indian Statistical Institute
Document Type
Master's Dissertation
Degree Name
Master of Technology
Subject Name
Computer Science
Department
Computer Vision and Pattern Recognition Unit (CVPR-Kolkata)
Supervisor
Palit, Sarbani (CVPR-Kolkata; ISI)
Abstract (Summary of the Work)
Image restoration is the operation of taking a corrupt/noisy image and estimating the clean, original image. There are various source of noise in image like fog, haze, glow, scattering of light, motion blur and camera misfocus. Image restoration involve various methods to restore images to original form like image dehazing, image denoising, image super-resolution. Images acquired by a visual system are seriously degraded under hazy and foggy weather, which will affect the detection, tracking, and recognition of targets. Thus, restoring the true scene from such a foggy image is of significance. But we focus on Nighttime scenes, which however commonly include visible lights sources with varying colors. These light sources also often introduce noticeable amounts of glow that is not present in daytime images. So in this work we illustrate you with night and day time image dehazing models and our approach of image denoising which also comes under image restoration. In night time image dehazing we illustrate you by CNN model used in various methods and in Image denoising by Auto-encoder.
Control Number
ISI-DISS-2020-11
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 International License.
DOI
http://dspace.isical.ac.in:8080/jspui/handle/10263/7164
Recommended Citation
Chaurasia, Rishabh, "Image Restoration of Night Time Hazy Images." (2021). Master’s Dissertations. 1.
https://digitalcommons.isical.ac.in/masters-dissertations/1
Comments
ProQuest Collection ID: http://gateway.proquest.com/openurl?url_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:dissertation&res_dat=xri:pqm&rft_dat=xri:pqdiss:28842683