Image restoration evaluation method using spatial and frequency filters

Abstract

When processing and transmitting information in the form of images, the problem of reducing their distortion due to various noises is important. Noise reduces the quality of the image and thus the perception of the information contained in it. Because of these problems, the ability to evaluate the information that can be obtained as a result of analysis using both visual and computer methods is impaired. The process of reducing noise in images is handled by an area of image processing called restoration. Despite the intersection of this area with image enhancement, it should be noted that the latter is a largely subjective procedure, while the restoration process is largely objective in nature. During restoration, an attempt is made to reconstruct or reproduce the distorted image, using a priori information about the phenomenon that caused its deterioration. Restoration methods are based on the modeling of distortion processes and the use of reverse procedures to restore the original image. In this paper, a new method for evaluating the restoration of distorted images, implemented with the help of spatial and frequency filters, is proposed. It consists in converting distorted images before filtering into gray scale and obtaining their histograms. The obtained histogram is extrapolated by a Gaussian curve and the value of the root mean square deviation is determined. A similar procedure is carried out for the restored image. The analysis was performed in the Python programming language using the Pillow and OpenCV image libraries. . The restoration evaluation parameter R is proposed, which is the ratio of the difference between the root mean square deviations of the distorted and restored images to the root mean square deviation of the distorted image. The R parameter was estimated for the geometric mean filter, the midpoint filter, and the Wiener filter and was found to be equal to 0.2; 0.3 and 0.43, respectively, which correlates with visual observations.