Abstract
In this paper, a new method for the removal of Gaussian noise based on two types of prior information is described. The first type of prior information is internal, based on the similarities between the pixels in the noisy image, and the other is external, based on the index or pixel location in the image. The proposed method focuses on leveraging these two types of prior information to obtain tangible results. To this end, very similar patches are collected from the noisy image. This is done by sorting the image pixels in ascending order and then placing them in consecutive rows in a new two-dimensional image. Henceforth, a principal component analysis is applied on the patch matrix to help remove the small noisy components. Since the restored pixels are similar or close in values to those in the clean image, it is preferable to arrange them using indices similar to those of the clean pixels. Simulation experiments show that outstanding results are achieved, compared to other known methods, either in terms of image visual quality or peak signal to noise ratio. Specifically, once the proper indices are used, the proposed method achieves PSNR value better than the other well-known methods by >1.5 dB in all the simulation experiments.
Highlights
Images can acquire noise during image acquisition, transmission, or recording
Extensive simulation experiments are implemented on different images to illustrate that the proposed method delivers outstanding results, either in terms of visual image quality based on human perception or peak signal to noise ratio (PSNR)
It is clear that the versions using the indices of the original image in (b) and the indices of the restored version obtained from low-noise-corrupted image at σ = 5 in (c) and (d) deliver superior results that are better than BM3D and PGPCA, either in terms of PSNR or visual image quality
Summary
Images can acquire noise during image acquisition, transmission, or recording. Gaussian noise is considered one of the most prevalent types of noise that may degrade an image and exists both, in wired and wireless channels [1,2]. Other approaches use external images as prior information, such as EPLL [8], dictionary-based denoising methods [9] and others [10,11]. To better estimate the noisy patches, other approaches use a combination of internal and external prior information [12,13]. Two types of prior information are used; one is external, based on the indices of the training image, and the other is internal, based on the similarity between the pixels in the overlapped. Extensive simulation experiments are implemented on different images to illustrate that the proposed method delivers outstanding results, either in terms of visual image quality based on human perception or peak signal to noise ratio (PSNR).
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
