Reorganized DCT-based image representation for reduced reference stereoscopic image quality assessment

The Use of Generalized Gaussian Distribution in Vibroacoustic Detection of Power Transformer Core Damage

Vibroacoustic diagnostics (VM—Vibroacoustic Method) is one of the methods for diagnosing the active part of power transformers. Measurement technologies have been refined over the past several years, but the methods of analyzing data obtained in VM diagnostics are still in development. In most cases, they are based on a simple frequency spectrum analysis, and the diagnostic conclusions are subjective and depend on the expert’s professional experience. The article presents an objective method for the detection of transformer unit core damage, based on the analysis of the statistical properties of the vibration signal registered on the surface of the tank of an unloaded transformer in the steady state of vibrations (VM). The algorithm for proceeding further is: FFT analysis of the vibroacoustic signal, with the determination of the relative changes in vibration power as a function of frequency P r ( f ) and, finally, the determination of the statistic properties of the dataset P r ( f ) . The Generalized Gaussian Distribution (GGD) is used to describe the P r ( f ) set. The detector output values are the λ and p parameters of the GGD distribution. These two numerical values form the basis for the classification of the technical condition of the transformer unit core. The correctness of the described solution was verified on the example of ten pieces of 16 MVA power transformers with different operating times and degrees of wear.

Study of Subjective Quality and Objective Blind Quality Prediction of Stereoscopic Videos

We present a new subjective and objective study on full high-definition (HD) stereoscopic (3D or S3D) video quality. In subjective study, we constructed an S3D video dataset with 12 pristine and 288 test videos, and the test videos are generated by applying the H.264 and H.265 compression, blur and frame freeze artifacts. We also propose a no reference (NR) objective video quality assessment (QA) algorithm that relies on measurements of the statistical dependencies between the motion and disparity subband coefficients of S3D videos. Inspired by the Generalized Gaussian Distribution (GGD) approach in liu2011statistical, we model the joint statistical dependencies between the motion and disparity components as following a Bivariate Generalized Gaussian Distribution (BGGD). We estimate the BGGD model parameters (α,β) and the coherence measure (Ψ) from the eigenvalues of the sample covariance matrix (M) of the BGGD. In turn, we model the BGGD parameters of pristine S3D videos using a Multivariate Gaussian (MVG) distribution. The likelihood of a test video's MVG model parameters coming from the pristine MVG model is computed and shown to play a key role in the overall quality estimation. We also estimate the global motion content of each video by averaging the SSIM scores between pairs of successive video frames. To estimate the test S3D video's spatial quality, we apply the popular 2D NR unsupervised NIQE image QA model on a frame-by-frame basis on both views. The overall quality of a test S3D video is finally computed by pooling the test S3D video's likelihood estimates, global motion strength and spatial quality scores. The proposed algorithm, which is 'completely blind' (requiring no reference videos or training on subjective scores) is called the Motion and Disparity based 3D video quality evaluator (MoDi3D). We show that MoDi3D delivers competitive performance over a wide variety of datasets including the IRCCYN dataset, the WaterlooIVC Phase I dataset, the LFOVIA dataset and our proposed LFOVIAS3DPh2 S3D video dataset.

A shallow convolutional neural network for blind image sharpness assessment

Blind image quality assessment can be modeled as feature extraction followed by score prediction. It necessitates considerable expertise and efforts to handcraft features for optimal representation of perceptual image quality. This paper addresses blind image sharpness assessment by using a shallow convolutional neural network (CNN). The network takes single feature layer to unearth intrinsic features for image sharpness representation and utilizes multilayer perceptron (MLP) to rate image quality. Different from traditional methods, CNN integrates feature extraction and score prediction into an optimization procedure and retrieves features automatically from raw images. Moreover, its prediction performance can be enhanced by replacing MLP with general regression neural network (GRNN) and support vector regression (SVR). Experiments on Gaussian blur images from LIVE-II, CSIQ, TID2008 and TID2013 demonstrate that CNN features with SVR achieves the best overall performance, indicating high correlation with human subjective judgment.