A. Aldahdooh, E. Masala, G. Wallendael, P. Lambert, Marcus Barkowsky
Improving relevant subjective testing for validation: Comparing machine learning algorithms for finding similarities in VQA datasets using objective measures
Signal Processing: Image Communication, vol. 74, no. May, pp. 32-41
Subjective quality assessment is a necessary activity to validate objective measures or to assess the performance of innovative video processing technologies. However, designing and performing comprehensive tests requires expertise and a large effort especially for the execution part. In this work we propose a methodology that, given a set of processed video sequences prepared by video quality experts, attempts to reduce the number of subjective tests by selecting a subset with minimum size which is expected to yield the same conclusions of the larger set. To this aim, we combine information coming from different types of objective quality metrics with clustering and machine learning algorithms that perform the actual selection, therefore reducing the required subjective assessment effort while trying to preserve the variety of content and conditions needed to ensure the validity of the conclusions. Experiments are conducted on one of the largest publicly available subjectively annotated video sequence dataset. As performance criterion, we chose the validation criteria for video quality measurement algorithms established by the International Telecommunication Union.
DigitalElektrotechnik und Medientechnik
A. Aldahdooh, E. Masala, O. Janssens, G. Wallendael, Marcus Barkowsky, P. Callet, G. van Wallendael, P. Lambert
Improved Performance Measures for Video Quality Assessment Algorithms Using Training and Validation Sets
IEEE Transactions on Multimedia, vol. 74, pp. 32-41
Due to the three-dimensional spatiotemporal regularities of natural videos and small-scale video quality databases, effective objective video quality assessment (VQA) metrics are difficult to obtain but highly desirable. In this paper, we propose a general-purpose no-reference VQA framework that is based on weakly supervised learning with convolutional neural network (CNN) and resampling strategy. First, an eight-layer CNN is trained by weakly supervised learning to construct the relationship between the deformations of the three dimensional discrete cosine transform of video blocks and corresponding weak labels judged by a full-reference (FR) VQA metric. Thus, the CNN obtains the quality assessment capacity converted from the FR-VQA metric, and the effective features of the distorted videos can be extracted through the trained network. Then, we map the frequency histogram calculated from the quality score vectors predicted by the trained network onto the perceptual quality. Specially, to improve the performance of the mapping function, we transfer the frequency histogram of the distorted images and videos to resample the training set. The experiments are carried out on several widely used video quality assessment databases. The experimental results demonstrate that the proposed method is on a par with some state-of-the-art VQA metrics and has promising robustness.