Endoscopic image restoration using truncated constrained least squares filter in frequency-domain and SURE-LET filter

Abstract

T-CLS (Truncated Constrained Least Squares) filter is designed with Maxwell-Boltzmann distribution kernel in a frequency domain and hybridized with an SURE-LET algorithm for an effective restoration of degraded Endoscopic image. T-CLS filter successfully reduces degradation and the SURE-LET algorithm reduces Random noise in Endoscopic image. The proposed method provides advantages of reduction in Gradient reversal artifacts and Halos effect to a great extent in Endoscopic image. Experimental results show that the proposed method improves image quality parameters like PSNR (Peak Signal to Noise Ratio), MSE (Mean Square Error) and SSIM (Structure Similarity Index Measurement) as compared to conventional methods.