A Pre-Processing Method Based on Self-Scoring Restoration and Self-Calibration for Image in Pressure Flow Pipes

Abstract

The appearance of the inside of a running pressure flow pipe, when viewed through a photo-lens, is often blurred and deformed by the influence of fluid pressure, temperature and type. This study proposes an image pre-processing method based on self-scoring restoration and self-calibration to solve the problems and make it adaptable to the complicated environments inside the pipe. The method consists of two stages, in the first stage, a restoration method based on Wiener filter is used to work with the defined merit functions to deal with the degenerated images, in the second stage, two images taken from different depths inside the pipe are used to calculate the distortion parameters according to the matching points obtained from those two pictures. The experiment results show the proposed method performs well in clarity and contrast and removes the distortion effectively.