Reducing blocking artifacts in JPEG-compressed images using an adaptive neural network-based algorithm

When a high compression ratio is required, the block discrete cosine transform (BDCT) decoded image suffers from the blocking effect: boundaries between adjacent image blocks visible for low bit rates. A blocking effect reduction algorithm based on DCT transform and Markov random field (MRF) is proposed to reduce blocking artifacts as many as possible, while preserving edge information. In this paper, the characteristic of human visual system (HVS) is sufficiently utilized. A visibility function of blocking artifacts is proposed based on the activity masking and brightness masking properties of HVS. The blocks which visibility of the blocking artifacts is less than the threshold do not need any processing. The proper threshold value for Huber function plays an important role in MRF method. The linear regression is used to adaptively estimate the threshold value. Experimental results show the proposed algorithm can significantly reduce blocking artifacts while preserving edge and texture information

A simple, non-iterative, wavelet-based deblocking algorithm is proposed to reduce both the blocking and ringing artifacts in JPEG compressed images. The algorithm exploits the fact that block discontinuities are constrained by the dc quantization interval of the quantization table, as well as the behavior of the wavelet modulus maxima evolution across scales for singular image structures, to derive appropriate threshold maps at different wavelet scales. Simulation results have shown that the proposed algorithm is able to smooth out both block discontinuities and ringing artifacts while preserving true edges and textural information.

Summary form only given. Block-based Discrete Cosine Transform (BDCT) has been widely used in image and video compression due to its energy compacting property and relative ease of implementation. However, BDCT has a major drawback, which is usually referred to as blocking artifacts. Blocking artifacts appear as grid noise along the block boundaries because each block is transformed and quantized independently. Image deblocking techniques can reduce these distortions and alleviate the conflict between bit rate reduction and visual quality preservation. Many state-of-the-art image deblocking algorithms treated the blocking artifacts reduction of the compressed image as an inverse restoration problem. Natural image prior models are well utilized into the blocking artifacts reduction processing, such as the local sparsity prior model and non-local similarity property of natural images. These two local and non-local models characterize the image prior information in two complementary perspectives. Therefore, it is necessary to combine these two models in a unified framework. In this paper, we propose a novel method to reduce the blocking artifacts of blockcoded images via patch clustering and low-rank minimization, which simultaneously exploits the local and non-local sparse representations in a unified framework. First, the whole compressed image are divided into small patches. For each patch, we perform patch clustering to collect similar patches into a group. Then the whole group are simultaneously reconstructed by a low-rank minimization approach. Singular value thresholding (SVT) algorithm is employed to solve the low-rank minimization problem. To further improve the performance of the proposed algorithm, we adopt an iterative procedure to utilize the newly output data in each iteration and update the noise and signal variance adaptively. Experimental results show that the proposed method achieves higher PSNR and SSIM than the state-of-the-art methods. Comparing to the state-of-theart algorithms and, the proposed algorithm achieves about 0.37dB and 0.11dB improvement on average. For visual quality assessment, the deblocking images produced by the proposed algorithm reveal much more sharp edge structures and richer textures.

Coding of images or processing of images has played a momentous role in the success of digital communications and multimedia. Coding plays a major role is 3D mobile generation. The image processing methods have been exploited through the years to improve the quality of digital images. In the image processing system De-noising based coding is used extensively. As we know that, in low bit rate applications, the blocking artifacts problem arises, which severely reduce the visual quality of the image. Reducing blocking artifacts is essential to render the compressed visual data acceptable to the viewer. So, to detect and reduce noise from the image is a major task. So removing the noise from original signal is still a challenging problem for researchers. There have been several published algorithms and each approach has its assumptions, advantages, and limitations. For real-time applications like television, photo-phone, etc. it is essential to reduce the noise power as much as possible and to retain the fine details and the edges in the image as well. Moreover, it is very important to have very low computational complexity so that the filtering operation is performed in a short time for online and real-time applications. The main focus of this paper is first to define an algorithm and based on that a non linear threshold filter is described which not only preserve the actual image structures in the presence of different types of noises (Salt & peepers, Speckle and Gaussian Noise) as well as it provide better PSNR, MSE, MAE, & Time Complexity than others Classical algorithms.

Fast Image Restoration for Reducing Block Artifacts Based on Adaptive Constrained Optimization

Blocking effect reduction of compressed images using classification-based constrained optimization

In the proposed paper, a parallel structure type Generative Adversarial Network (GAN) using edge and texture information is proposed. In the existing GAN-based model, many learning iterations had to be given to obtaining an output that was somewhat close to the original data, and noise and distortion occurred in the output image even when learning was performed. To solve this problem, the proposed model consists of two generators and three discriminators to propose a network in the form of a parallel structure. In the network, each edge information and texture information were received as inputs, learning was performed, and each character was combined and outputted through the Combine Discriminator. Through this, edge information and distortion of the output image were improved even with fewer iterations than DCGAN, which is the existing GAN-based model. As a result of learning on the network of the proposed model, a clear image with improved contour and distortion of objects in the image was output from about 50,000 iterations.

Transform coding is the most popular image compression method. However, for high compression it produces noticeable blocking artifacts in the decoded image. This paper presents new algorithms for reducing blocking artifacts. The algorithms use piecewise self-similarity within different parts of the image as a priori to give reasonable modification to the block boundary pixels. The proposed postprocessing algorithm includes block classification in transform coefficient domain, and each block boundary area smoothing is performed by searching similar blocks. In experiments it outperforms an existing method and gives significant subjective and objective improvement over the decoded image.

The ADM(adaptive delta modulation) speech coder is generally used with a time-invariant low-pass filter at the decoder output. The purpose of this low-pass filter is to reject coder noise at frequencies above the fixed speech passband. The speech spectrum, however, tends to occupy only the lower frequencies within the passband during voiced speech, and is somewhat “high pass” during unvoiced speech. In this paper, we show how the quality of ADM may be significantly improved by adoptively filtering the coder output such as to follow the natural bandwidth of the speech. This was found to reduce drastically the perceived noise in the output of the ADM coding system at low bit rates. The use of an adaptive low-pass filter realizes almost all of this quality gain. (An adaptive high-pass filter seems to reject less audible noise components and seems more prone to introducing objectionable artifacts.) We also discuss a method for reducing the bit rate with little or no sacrifice in quality (relative to normal ADM) by adapting the sampling rate along with the time-varying low-pass filter.

Fragile watermarking is designed to protect content integrity of digital data, meaning to detect any change in the content as well as localize areas that have been changed. In this paper, we propose a fragile watermarking scheme, which embeds dual watermarks (one is naturally fragile and the other is actually robust) in JPEG-2000 compressed images with ROI (region of interest) selection. In this scheme, the fragile watermark is embedded in ROI coefficients at the first decomposition layer, while the robust watermark embedded in ROB (region of backgrounds) coefficients at the third decomposition layer. The combinational working of them is not only capable of detecting malicious changes precisely and flexibly but also estimating the degree of alteration to discriminate intended attacks from unintended ones (e.g., such normal image processing as compression, low-pass filtering, sharpening, etc). Experiments show that our functionally fragile watermarking scheme is scalable in view of detecting attack's intension as well as accuracy in localizing the tampered areas.

Depth images are often accompanied by unavoidable and unpredictable noise. Depth image denoising algorithms mainly attempt to fill hole data and optimise edges. In this paper, we study in detail the problem of effectively filtering the data of depth images under noise interference. The classical filtering algorithm tends to blur edge and texture information, whereas the fractional integral operator can retain more edge and texture information. In this paper, the Grünwald–Letnikov-type fractional integral denoising operator is introduced into the depth image denoising process, and the convolution template of this operator is studied and improved upon to build a fractional integral denoising model and algorithm for depth image denoising. Depth images from the Redwood dataset were used to add noise, and the mask constructed by the fractional integral denoising operator was used to denoise the images by convolution. The experimental results show that the fractional integration order with the best denoising effect was −0.4 ≤ ν ≤ −0.3 and that the peak signal-to-noise ratio was improved by +3 to +6 dB. Under the same environment, median filter denoising had −15 to −30 dB distortion. The filtered depth image was converted to a point cloud image, from which the denoising effect was subjectively evaluated. Overall, the results prove that the fractional integral denoising operator can effectively handle noise in depth images while preserving their edge and texture information and thus has an excellent denoising effect.

The authors propose a simple image coding algorithm using VQ (vector quantization) and clustering interpolation, which avoids an explicit interpolation operation by employing different but related codebooks at the encoder and the decoder of a vector quantizer. Computer simulations indicated that images reconstructed with clustering interpolation had smaller mean square errors than those obtained with linear or contour-based interpolation. In order to reduce coding artifacts and to improve reconstruction quality at low bit rates, an adaptive corrector stage with block classification is also included. Computer simulations demonstrate the effectiveness of the algorithm at about 0.3 b/pixel. >

Chaotic moving video quality enhancement based on deep in-loop filtering

Video quality assessment can be gotten by combination the distortion in the space area and the time area. As we all known that edge information is one of the most important features in image quality estimation. Based on the edge model in the perceived image quality estimation, we used it in the space and time area in the video, and get the edge information distorted model in space area and time area of the video. Using multilinear regression to combine the two models, we can get the video quality assessment model based on edge information. The proposed model only uses the edge information, and the consumption in both areas is small. After compared with other methods given by video quality estimation group, it’s found that our method is convenient and good at the 50 Hz video sequence of low bit rate(768kb/s -4.5 Mb/s).

A psychovisual experiment prescribes the quantization values in image compression. The quantization process is used as a threshold of the human visual system tolerance to reduce the amount of encoded transform coefficients. It is very challenging to generate an optimal quantization value based on the contribution of the transform coefficient at each frequency order. The psychovisual threshold represents the sensitivity of the human visual perception at each frequency order to the image reconstruction. An ideal contribution of the transform at each frequency order will be the primitive of the psychovisual threshold in image compression. This research study proposes a psychovisual threshold on the large discrete cosine transform (DCT) image block which will be used to automatically generate the much needed quantization tables. The proposed psychovisual threshold will be used to prescribe the quantization values at each frequency order. The psychovisual threshold on the large image block provides significant improvement in the quality of output images. The experimental results on large quantization tables from psychovisual threshold produce largely free artifacts in the visual output image. Besides, the experimental results show that the concept of psychovisual threshold produces better quality image at the higher compression rate than JPEG image compression.