A survey on various image deblurring methods
Image blur is one of the main types of degradation that reduces image quality. Image deblurring is an attempt to invert blurring process by using mathematical model to get best estimation of latent (sharp) image. Blurring can be modeled mathematically as a convolution process between two functions w...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Published: |
Medwell Journals
2016
|
| Subjects: | |
| Online Access: | http://eprints.utm.my/id/eprint/71227/ https://www.scopus.com/inward/record.uri?eid=2-s2.0-85013643470&partnerID=40&md5=480414dc459ab7d98e0bfe6bf3a9a880 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Image blur is one of the main types of degradation that reduces image quality. Image deblurring is an attempt to invert blurring process by using mathematical model to get best estimation of latent (sharp) image. Blurring can be modeled mathematically as a convolution process between two functions which are image and Point Spread Function (PSF). PSF can be classified into more than one type depending on the reason for blurring. Gaussian is the type of PSF this study will focus on, and an implementation of such PSF to compare different deblurring methods. Based on the availability of prior knowledge about the degradation kernel (PSF), the deblurring methods can be divided into two major categories which are non-blind deconvolution and blind-deconvolution. Peak Signal to Noise Ratio (PSNR) and Structural Similarity (SSIM) are the tools used to estimate the performance of these methods. |
|---|