EEG-based Quality Assessment

Subjective quality assessment is a standard method employed to measure the quality of an image or a video based on the subject's perception. These quality scores are gained from asking the subject to rate a given stimuli based on a predefined rating scale. Since these measures of the quality are not independent of the subject's intension and cognition, i.e. may be easily biased, and require a high amount of concentration, we develop EEG-based technoloqy for extracting brain correlations for user’s perceived quality.

Our goal is the development of an objective qualification of 3D/2D images and videos. The main focus of our work lies on

  • Extracting features from EEG which correlate with the images/videos quality.
  • Analyzing the EEG responses concerning ERPs, SSVEPs and connectivity measures.
  • Source reconstruction and neurophysiological interpretation of results.
  • Application to video compression and 3D visualization.

Publications

  1. S. Scholler, S. Bosse, M. S. Treder, B. Blankertz, G. Curio, K.-R. Muller, and T. Wiegand, “Toward a Direct Measure of Video Quality Perception Using EEG”, IEEE Transactions on Image Processing, vol. 21, issue 5, pp. 2619-2629, May 2012.
  2. L. Acqualagna, S. Bosse, A. K. Porbadnigk, G. Curio, K.-R. Müller, T. Wiegand, and B. Blankertz, “EEG-based classification of video quality perception using steady state visual evoked potentials (SSVEPs)”, Journal of Neural Engineering,12(2):026012, March 2015.
  3. S. Bosse, L. Acqualagna, A. K. Porbadnigk, B. Blankertz, G. Curio, K.-R. Müller, T. Wiegand, “Neurally informed assessment of perceived natural texture image quality”, Proceedings of the IEEE International Conference on Image Processing (ICIP), pp. 1987-1991, October 2014
  4. F. Shahbazi, A. Ewald, and G. Nolte, “Self-Consistent MUSIC: An approach to the localization of true brain interactions from EEG/MEG data”, NeuroImage, vol. 112, pp. 299-309, May 2015.