Compressed image restoration based on edge enhancement field of experts

Learning-based image restoration for compressed images

Higher-order Markov Random Fields, which can capture important properties of natural images, have become increasingly important in computer vision. While graph cuts work well for first-order MRF's, until recently they have rarely been effective for higher-order MRF's. Ishikawa's graph cut technique [1], [2] shows great promise for many higher-order MRF's. His method transforms an arbitrary higher-order MRF with binary labels into a first-order one with the same minima. If all the terms are submodular the exact solution can be easily found; otherwise, pseudoboolean optimization techniques can produce an optimal labeling for a subset of the variables. We present a new transformation with better performance than [1], [2], both theoretically and experimentally. While [1], [2] transforms each higher-order term independently, we use the underlying hypergraph structure of the MRF to transform a group of terms at once. For n binary variables, each of which appears in terms with k other variables, at worst we produce n non-submodular terms, while [1], [2] produces O(nk). We identify a local completeness property under which our method perform even better, and show that under certain assumptions several important vision problems (including common variants of fusion moves) have this property. We show experimentally that our method produces smaller weight of non-submodular edges, and that this metric is directly related to the effectiveness of QPBO [3]. Running on the same field of experts dataset used in [1], [2] we optimally label significantly more variables (96 versus 80 percent) and converge more rapidly to a lower energy. Preliminary experiments suggest that some other higher-order MRF's used in stereo [4] and segmentation [5] are also locally complete and would thus benefit from our work.

Scan integration as a labelling problem

Current image compression techniques such as JPEG and WebP are widely applied in the age of information. However, lossy compression like JPEG in its nature will introduce visually annoying artifacts while saving Internet bandwidth and storage space. The artifacts such as blocking and ringing are especially sharp at low bitrates. In this paper, we propose a novel dual-residual network to reduce compression artifacts caused by lossy compression codecs. This network directly learns an end-to-end mapping between the distorted image processed by JPEG or other compression methods and the original image, which takes decompressed images with blocking artifacts as input and produces clearer images with less artifacts. Experiments results on the test dataset demonstrate the efficiency of the proposed model, especially at very low bitrates.

Performance analysis and experimental verification of SPAD receivers without photon counting for optical wireless communications

Image restoration is the process of recovering the original image from the degraded image. Aspire of the project is to restore the blurred/degraded images using Blind Deconvolution algorithm. The fundamental task of Image deblurring is to de-convolute the degraded image with the PSF that exactly describe the distortion. Firstly, the original image is degraded using the Degradation Model. It can be done by Gaussian filter which is a low-pass filter used to blur an image. In the edges of the blurred image, the ringing effect can be detected using Canny Edge Detection method and then it can be removed before restoration process. Blind Deconvolution algorithm is applied to the blurred image. It is possible to renovate the original image without having specific knowledge of degradation filter, additive noise and PSF. To get the effective results, the Penalized Maximum Likelihood (PML) Estimation Technique is used with our proposed Blind Deconvolution Algorithm.

Recent work on early vision such as image segmentation, image restoration, stereo matching, and optical flow models these problems using Markov Random Fields. Although this formulation yields an NP-hard energy minimization problem, good heuristics have been developed based on graph cuts and belief propagation. Nevertheless both approaches still require tens of seconds to solve stereo problems on recent PCs. Such running times are impractical for optical flow and many image segmentation and restoration problems. We show how to reduce the computational complexity of belief propagation by applying the Four Color Theorem to limit the maximum number of labels in the underlying image segmentation to at most four. We show that this provides substantial speed improvements for large inputs to a variety of vision problems, while maintaining competitive result quality.KeywordsImage SegmentationBelief PropagationMarkov Random FieldsImage RestorationStereo MatchThese keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Pre-stack seismic inversion has inherently supremacy and is a complicated problem. It is a simultaneous inversion for multi-parameters and is ill-posed and band-limited. Thus the results are of non-unique and its process is unstable. Combining the full Zoeppritz equation with both section constant V S /V P and the edge-preserving regularization can relieve these problems. Here we provided an inverted strategy constructing a new objective function based on the edge-preserving regularization and Markov random field (MRF). The method needs to gain reflectivity by the full Zoeppritz equation, and applies fast simulated annealing (FSA) to nonlinear optimization problem. Combining high- with low- orders MRF can improve the inverted results, namely utilize high-order MRF at the early stage and low-order MRF at late iterations. Moreover, to the transverse isotropy layered model, a large coefficient in horizontal direction is helpful to improve lateral continuity, and a small coefficient in vertical direction can preserve large longitudinal gradient. We test the method on field data example. The inverted results of multiple-order MRF are better than that of single-order MRF, and they match well with logging data.

Characteristics of high frequency (HF) component based on heart rate variability (HRV) in a large general population remain unclear, particularly on the relationship with daily physical activity. We aimed to characterize the distribution of HF component and examine the association with daily physical activity among community residents. We performed spectral analysis of HRV from 10-second ECG recordings among 9135 residents aged 30 to 74 years in Nagahama City, Japan. HF components were log-transformed to consider the distribution. Simple correlations between HF and age were determined. Age-adjusted mean values of HF component were calculated for each questionnaire item related to daily physical activity. Multiple regression analysis was performed to examine the effect of daily physical activity on HF component value. Mean values of logarithmically-transformed HF component (lnHF) were higher in women than in men (p < 0.001). lnHF was inversely associated with age (r = -0.40, -0.49 for men, women, respectively). Adjusted mean lnHF for physically active people was significantly higher than that in inactive people (p < 0.001). HF components from 10-second ECG recordings were moderately and negatively correlated with age in both sexes, and positively correlated with daily physical activity in the general adult population. Maintaining the level of daily physical activity, especially to exercise regularly could keep the parasympathetic function high.

We present a framework based on modular integration and multiresolution for restoring images. We model the image as a Markov random field (MRF) and propose a restoration algorithm. In essence, the problem of image restoration requires learning of the MRF model and noise parameters which are used to restore degraded images. In the developed scheme, there exists interaction between the model learning module and the image restoration module. A method based on homotopy continuation is used for unsupervised model learning and the restoration is achieved through the minimization of an energy function.

A new feedforward control method to control encod-ing parameters is proposed for low bit rate video encoding. At low transmission bit rates, all input video frames cannot be transmitted and an encoding frame interval varies with the information amount in each encoded frame. Subjective video quality is evaluated from both picture degradation and encoding frame intervals. Because picture degradation and encoding frame intervals are traded off, encoding parameter control is very important. The proposed method is based on a hybrid transform predictive coding scheme with adaptive coefficient selection. The method estimates the amount of information for some encoding parameters and selects parameters so that given control characteristics can be achieved. Computer simulations for both the proposed method and a conventional feedback method show the effectiveness of the new method. This method will be applied to an NETEC series low bit rate video codec.

A new method for the automated extraction of pipelines and other linear objects from Synthetic Aperture Radar (SAR) scenes is presented. It combines intensity data with coherence data from an interferometric evaluation of a SAR scene pair. The fusion is based on Bayesian statistics and is part of a Markov random field (MRF) model for line extraction. Both intensity and coherence data are evaluated using rotating templates. The different statistical properties of intensity and coherence are taken into account by a multiplicative noise model and an additive noise model respectively. The MRF model introduces prior knowledge about the continuity and the narrowness of lines. Posterior odds resulting from the MRF method are input to a method based on ziplock snakes for linear object extraction. This processing step is controlled interactively which is necessary as fully automatic processing of the given noisy data does not provide sufficiently predictable results. The method is applied to data of the ERS tandem mission.

This paper presents an efficient orthogonal sparse 8 × 8 transform matrix for colour image compression particularly at lower bit rate applications. The transform matrix implemented in Xilinx XC2VP30 FPGA device indicates that a significant saving in computation and hardware resources over Discrete Cosine Transform (DCT), Signed Discrete Cosine Transform (SDCT), approximate DCT and matrix proposed by Bouguezel. By using various natural test images, it is demonstrated that the subjective and objective qualities are comparable with the above–mentioned transforms at lower bit rates. Furthermore, it outperforms SDCT by a large margin almost at all bit rates for most of the images.

Image restoration and its different variations are important topics in low-level image processing. One of the main challenges in image restoration is dependency of current methods to the corruption characteristics. In this paper, we have proposed an image restoration architecture that enables us to address different types of corruption, regardless of type, amount and location. The main intuition behind our approach is restoring original images from abstracted perceptual features. Using an encoder-decoder architecture, image restoration can be defined as an image transformation task. Abstraction of perceptual features is done in the encoder part of the model and determines the sampling point within original images' Probability Density Function (PDF). The PDF of original images is learned in the decoder section by using a Generative Adversarial Network (GAN) that receives the sampling point from the encoder part. Concretely, sampling from the learned PDF restores original image from its corrupted version. Pretrained network extracts perceptual features and Restricted Boltzmann Machine (RBM) makes the abstraction over them in the encoder section. By developing a new algorithm for training the RBM, the features of the corrupted images have been refined. In the decoder, the Generator network restores original images from abstracted perceptual features while Discriminator determines how good the restoration result is. The proposed approach has been compared with both traditional approaches like BM3D and with modern deep models like IRCNN and NCSR. We have also considered three different categories of corruption including denoising, inpainting and deblurring. Experimental results confirm performance of the model.

The purpose of this study was to investigate whether objective models can be equally accurate for expert and non-expert viewers. We measured in both expert and non-expert viewers the subjective video quality of several high definition video sequences, which had been processed at several bit-rates using MPEG-2 and H.264 codecs. The results showed only a small but statistically significant difference, particularly at low bit-rates, in perceived quality between experts and non-experts. These subjective data were then compared to objective quality measurements obtained with a JND-based model and the standard PSNR. We found that the JND model performed better than the PSNR, but its predictive performance differed significantly for expert and non-expert viewers.