Blotch detection for digital archives restoration based on the fusion of spatial and temporal detectors

This paper proposes a method based on the Dempster-Shafer evidence theory for the detection of blotches in digitized archive film sequences. The detection scheme relies on the fusion of two uncorrelated fast, no motion compensated, spatio-temporal blotch detectors. The imprecision and uncertainty of botch detectors are modeled using Dempster-Shafer evidence theory, which improves the decision, by taking into acoount the …

Accidental Wow Defect Evaluation Using Sinusoidal Analysis Enhanced by Artificial Neural Networks

A method for evaluation of parasitic frequency modulation (wow) in archival audio is presented in this paper, published in the PrestoSPACE project. The proposed approach utilizes sinusoidal components as their variations are highly correlated with the distortion variations. The sinusoidal components are extracted from audio signal by means of sinusoidal modeling procedures being often severely distorted and in case of …

Evaluation of the maximal modulation frequency for wow and flutter detection

Author of this paper participated in the development of several algorithms for wow and flutter characteristic determination. The algorithms were found useful in some real-life restoration procedures, however, there was no study of their capabilities in terms of the maximal determined modulation frequency. This paper presents such a study for three algorithms, i.e. the power-line hum tracker, high frequency bias …

Determining techniques for “wow”distortion

Algorithms for determining the wow distortion characteristic are proposed. These are the power-line-hum tracking algorithm, the high-frequency-bias tracking algorithm, and the algorithm based on an adaptive analysis of the center of gravity of the spectrum of the distorted signal. All of the algorithms presented allow a hardware- or software-based implementation.