Recently, the necessity of video testing at the point of reception has become a challenge for video distributors. This paper presents a new system framework for managing the quality of video degradation detection. The system is based on objective video quality assessment metrics and unsupervised machine learning techniques that use the dimensionality reduction of time series. It was demonstrated that it is possible to detect anomalies in the video during video streaming in soft real time. In addition, the model discovers degradations based on the visible correlation between adjacent images in the video sequence regardless the quick or slow change of a scene in the sequence. With additional hardware manipulations on the equipment on the user side, the proposed solution can be used in practical implementations where the need for monitoring possible degradations during video streaming exists.

The blind additive white Gaussian noise level estimation is an important and a challenging area of digital image processing with numerous applications including image denoising and image segmentation. In this paper, a novel block-based noise level estimation algorithm is proposed. The algorithm relies on the artificial neural network to perform a complex image patch analysis in the singular value decomposition (SVD) domain and to evaluate noise level estimates. The algorithm exhibits the capacity to adjust the effective singular value tail length with respect to the observed noise levels. The results of comparative analysis show that the proposed ANN-based algorithm outperforms the alternative single stage block-based noise level estimating algorithm in the SVD domain in terms of mean square error (MSE) and average error for all considered choices of block size. The most significant improvements in MSE levels are obtained at low noise levels. For some test images, such as “Car” and “Girlface”, at σ = 1 , these improvements can be as high as 99% and 98.5%, respectively. In addition, the proposed algorithm eliminates the error-prone manual parameter fine-tuning and automates the entire noise level estimation process.