Image Deblurring using Wiener Filtering and Siamese Neural Network

Abstract

Blurred images are difficult to avoid in situations when minor Atmospheric turbulence or camera movement results in low-quality images. We propose a system that takes a blurred image as input and produces a deblurred image by utilizing various filtering techniques. Additionally, we utilize the Siamese Network to match local image segments. A Siamese Neural Network model is used that is trained to account for image matching in the spatial domain. The best-matched image returned by the model is then further used for Signal-to-Noise ratio and Point Spread Function estimation. The Wiener filter is then used to deblur the image. Finally, the results of the deblurring techniques with existing algorithms are compared and it is shown that the error in deblurring an image using the techniques presented in this paper is considerably lesser than other techniques.

Enhanced Mask R-CNN blur instance segmentation based on generated adversarial network

“…To test the effectiveness of enhancing the Mask R-CNN deblurring convolution block, this paper adopts the traditional fuzzing algorithm of the Wiener filter [12] and the generative adversarial network deblurring convolution block, Lucy-Richardson algorithm and super-resolution reconstruction algorithm [13] conduct simulation experiments on blur datasets. The effect of the deblurring experiment is shown below, and the image quality evaluation results are shown in Table 3.…”