Please use this identifier to cite or link to this item: http://hdl.handle.net/10263/7164
Full metadata record
DC FieldValueLanguage
dc.contributor.authorChaurasia, Rishabh-
dc.date.accessioned2021-07-12T06:36:30Z-
dc.date.available2021-07-12T06:36:30Z-
dc.date.issued2020-09-
dc.identifier.citation22p.en_US
dc.identifier.urihttp://hdl.handle.net/10263/7164-
dc.descriptionDissertation under the supervision of Dr. Sarbani Palit, CVPR, Indian Statistical Institute, Kolkataen_US
dc.description.abstractImage restoration is the operation of taking a corrupt/noisy image and estimat- ing the clean, original image. There are various source of noise in image like fog, haze, glow, scattering of light, motion blur and camera mis-focus.Image restoration involve various methods to restore images to original form like im- age dehazing, image denoising, image super-resolution. Images acquired by a visual system are seriously degraded under hazy and foggy weather, which will a ect the detection, tracking, and recognition of targets. Thus, restoring the true scene from such a foggy image is of signi cance.But we focus on Nighttime scenes,which however commonly include visible lights sources with varying col- ors. 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 illus- trate you by CNN model used in various methods and in Image denoising by Auto-encoder .en_US
dc.language.isoenen_US
dc.publisherIndian Statistical Institute, Kolkataen_US
dc.relation.ispartofseriesDissertation;;2020-11-
dc.subjectAtmospheric scattering modelen_US
dc.subjectCNN modelen_US
dc.titleImage Restoration of Night Time Hazy Imagesen_US
dc.typeOtheren_US
Appears in Collections:Dissertations - M Tech (CS)

Files in This Item:
File Description SizeFormat 
Dissertation_Rishabh Chaurasia CS1822.pdf765.26 kBAdobe PDFView/Open


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