Gradient-Kalman Filtering (GKF) based endoscopic image restoration

Abstract

Gradient Kalman Filter (GKF) is designed for an effective restoration of Endoscopic frames. The combine advantages of Kalman filter and Gradient distribution restore highly degraded Endoscopic frame with Random noise and blur simultaneously. Kalman filter shows the advantage of the effective restoration of `high-frequency' region and Gradient filter shows the advantage of the effective restoration of `low-frequency' region without altering `high-frequency' region. Experimental results show that the proposed method improves frame quality in terms of parameters like PSNR (Peak Signal to Noise Ratio), MSE (Mean Square Error) and SSIM (Structure Similarity Index Measurement) as compared to conventional methods.