Return to search

Image Restoration in Consideration of Poisson Noise

It¡¦s not easy to keep photographs clean in every day. A photograph is liable to be polluted by accumulating defects such as dusts, which can degrade the imaging quality. In the thesis, a method of image restoration is proposed for image polluted by multiplicative transmittance noise. The method is based on estimating the approximate autocorrelation function of the unpolluted image. This autocorrelation function is obtained by analyzing the relationship among the autocorrelation function for polluted image, unpolluted image and noise. Further more, the noisy image is restored by the property of the autocorrelation function.
A polluted photograph in imaging system is modeled by a thin random screen against the original image. In this model, defects are Poisson-distribution and may be overlapped. Since transmittance effect of each defect is multiplicative, the transmittance of random screen is computed as a product of Poisson-distribution-centered random function. Then, the statistical autocorrelation function of random screen is accordingly computed. More specifically, we should rearrange image data as periodic signal to avoid insufficient data in computing the process autocorrelation function.
The simulated polluted image is restored by the amplitude information from the estimated autocorrelation function of the original image. Simulating results is demonstrated that the RMS of the restored image computed with the polluted image is improved.

Identiferoai:union.ndltd.org:NSYSU/oai:NSYSU:etd-0728100-231749
Date28 July 2000
CreatorsChang, Yuan-Ming
ContributorsBen-Shung Chow, S.C.Tai, Chin-Hsing Chen, Inn-Chyn Her
PublisherNSYSU
Source SetsNSYSU Electronic Thesis and Dissertation Archive
LanguageCholon
Detected LanguageEnglish
Typetext
Formatapplication/pdf
Sourcehttp://etd.lib.nsysu.edu.tw/ETD-db/ETD-search/view_etd?URN=etd-0728100-231749
Rightsnot_available, Copyright information available at source archive

Page generated in 0.0021 seconds