Digital Image Processing

Open Access Open Access  Restricted Access Subscription Access
Open Access Open Access Open Access  Restricted Access Restricted Access Subscription Access

Performance Analysis and Automatic Selection of Restoration Techniques for Diversified Field Images


Affiliations
1 G. H. Raisoni College of Engineering and Management, Wagholi, Pune, India
2 Dr. D. Y. Patil School of Engineering, University of Pune, India
3 G. H. Raisoni College of Engineering and Management, Wagholi, Pune, India
4 ITM College of Engineering, Nagpur, India
     

   Subscribe/Renew Journal


In this Paper, a new formulation based on Least Square Regression (LSR) is discussed for image alignment. Contrary to the conventional approach, LSR technique takes an advantage in image restoration. Based on this formulation, three methods Wiener filter, Regularized filter and Blind Deconvolution are proposed and Peak Signal to Noise Ratio (PSNR) is discussed. Analysis is carried out by comparing the combination of single type of image and noise dealing PSNR for each image. We proposed automatic parameter estimation and selection of restoration methods for diversified field images.

Keywords

Blind Deconvolution, Least Square Regression, Regularized Filter, Wiener Filter.
User
Subscription Login to verify subscription
Notifications
Font Size

Abstract Views: 243

PDF Views: 1




  • Performance Analysis and Automatic Selection of Restoration Techniques for Diversified Field Images

Abstract Views: 243  |  PDF Views: 1

Authors

Shraddha K. Hatwar
G. H. Raisoni College of Engineering and Management, Wagholi, Pune, India
A. L. Wanare
Dr. D. Y. Patil School of Engineering, University of Pune, India
Dilip D. Shah
G. H. Raisoni College of Engineering and Management, Wagholi, Pune, India
J. B. Helonde
ITM College of Engineering, Nagpur, India

Abstract


In this Paper, a new formulation based on Least Square Regression (LSR) is discussed for image alignment. Contrary to the conventional approach, LSR technique takes an advantage in image restoration. Based on this formulation, three methods Wiener filter, Regularized filter and Blind Deconvolution are proposed and Peak Signal to Noise Ratio (PSNR) is discussed. Analysis is carried out by comparing the combination of single type of image and noise dealing PSNR for each image. We proposed automatic parameter estimation and selection of restoration methods for diversified field images.

Keywords


Blind Deconvolution, Least Square Regression, Regularized Filter, Wiener Filter.