Image Denoising Algorithm Combined with SGK Dictionary Learning and Principal Component Analysis Noise Estimation

SGK (sequential generalization of K-means) dictionary learning denoising algorithm has the characteristics of fast denoising speed and excellent denoising performance. However, the noise standard deviation must be known in advance when using SGK algorithm to process the image. This paper presents a denoising algorithm combined with SGK dictionary learning and the principal component analysis (PCA) noise estimation. At first, the noise standard deviation of the image is estimated by using the PCA noise estimation algorithm. And then it is used for SGK dictionary learning algorithm. Experimental results show the following: (1) The SGK algorithm has the best denoising performance compared with the other three dictionary learning algorithms. (2) The SGK algorithm combined with PCA is superior to the SGK algorithm combined with other noise estimation algorithms. (3) Compared with the original SGK algorithm, the proposed algorithm has higher PSNR and better denoising performance.

Design of Virtual Function Signal Generator Based on Sound Card

In this paper, the use of Lab VIEW virtual instrument development platform, designs the virtual function signal generator based on sound card. The instrument can generate sine wave, square wave, saw tooth wave, triangle wave, gauss white noise, superposition of sine wave, custom formula waveform, it can be arbitrarily set parameter as frequency, amplitude, phase, the noise standard deviation, it has simple operation, good interaction, it save the cost and can be widely used in scientific research and experiment teaching.

ESTIMATION OF FRAME SEQUENCE NOISE WITH REMOVAL OF JPEG ARTIFACTS

This paper proposes a method to remove JPEG noise artifacts from frame sequences. Using extensive experimental results we show how an online system with periodic noise estimation functionality can estimate the real frame noise even if the images are in JPEG format. We present the mathematical basis of the methodology and show in real content that we can have reliable measurements. We also present the results obtained on a real network camera and show that our method can provide a much better estimation of the noise standard deviation compared to common practice but comparable inter-channel and spatial intra-channel correlation estimates. We also provide some guidelines for capturing datasets necessary to apply computer vision tasks. Our approach exploits the well known stochastic linearization phenomenon which we prove that is present in our case.

NOISE-IMPROVED SIGNAL CORRELATION IN AN ARRAY OF AUTOREGRESSIVE MODELS OF ORDER ONE

This paper discusses noise-improved signal correlation through an array of autoregressive models of order one [AR (1)]. In a single model, when the input is a square wave or a cosine with a higher frequency, stochastic resonance (SR) exists. When the input is a cosine with a lower frequency, SR and suprathreshold stochastic resonance (SSR) both exist. SSR can also exist for a cosine with a higher frequency or a square wave through an array of AR (1) models. The efficacy of SR and SSR increases as the number of AR (1) models is raised or as the threshold is lowered in the array. There is a range of values of noise standard deviation where the correlation coefficient between the input and output signals is greater than that of the input signal and the noisy signal.