Blind deconvolution of Gaussian blurred images containing additive white Gaussian noise
- Authors: Robinson, Philip E. , Roodt, Yuko
- Date: 2013
- Subjects: Gaussian blur , Gaussian noise , Bind deconvolution
- Language: English
- Type: Conference proceedings
- Identifier: http://hdl.handle.net/10210/16753 , uj:15807 , Robinson, P.E. & Roodt, Y. Blind deconvolution of Gaussian blurred images containing additive white Gaussian noise. IEEE International Conference on Industrial Technology (ICIT 2013), 2013, pp. 1092-1097.
- Description: Abstract: Image restoration algorithms are used to reconstruct the information that is suppressed when an observed image is subjected to blurring. These algorithms generally assume that knowledge of the nature of the distortion and noise contained in an observed image is available. When this information is not available and has to be directly estimated from the image being processed the problem becomes one of blind deconvolution. This paper makes use of a novel blur identification technique and a noise identification technique to perform blind deconvolution on single images that have been degraded by a Gaussian blur and contain additive white Gaussian noise.
- Full Text:
Gaussian blur identification using scale-space theory
- Authors: Robinson, Philip , Roodt, Yuko , Nel, Andre
- Date: 2012
- Subjects: Blur identification , Blur estimation , Gaussian blur , Image deblurring algorithms , Scale-space theory
- Type: Article
- Identifier: http://ujcontent.uj.ac.za8080/10210/366248 , uj:6060 , ISBN 978-0-620-54601-0 , http://hdl.handle.net/10210/10475
- Description: Image deblurring algorithms generally assume that the nature of the blurring function that degraded an image is known before an image can be deblurred. In the case of most naturally captured images the strength of the blur present in the image is not known. This paper proposes a method to identify the standard deviation of a Gaussian blur that has been applied to a single image with no a priori information about the conditions under which the image was captured. This simple method makes use of a property of the Gaussian function and the Gaussian scale space representation of an image to identify the amount of blur. This is in contrast to the majority of statistical techniques that require extensive training or complex statistical models of the blur for identification.
- Full Text: