Novel method for objectively measuring video quality

A novel objective method for measuring the quality of video is proposed. This method is based on calculation mutual information between frame from original sequence and corresponding frame from test sequence. It was tested on the ‘Carphone’ video at QCIF resolution (176 × 144 pixels) coded in H.264 and compared with commonly used objective methods for measuring video quality (such as Video Quality Metric (VQM), Structural Similarity Index (SSIM), Peak Signal-to-Noise Ratio (PSNR)) and one distance metric (Minkowski-form distance). Results show that our method correlates with standardized method and distance metric, so it is possible to replace more complex method with our simpler method.

[1]  Miss A.O. Penney.  (b) , 1974, The New Yale Book of Quotations.

[2]  Ioannis Pitas,et al.  Entropy metrics used for video summarization , 2002, SCCG '02.

[3]  R. Dosselmann,et al.  A Formal Assessment of the Structural Similarity Index , 2008 .

[4]  Ioannis Pitas,et al.  A mutual information approach to articulated object tracking , 2003, Proceedings of the 2003 International Symposium on Circuits and Systems, 2003. ISCAS '03..

[5]  Kevin Barraclough,et al.  I and i , 2001, BMJ : British Medical Journal.

[6]  Stefan Winkler,et al.  Digital Video Quality: Vision Models and Metrics , 2005 .

[7]  Yubing Wang,et al.  Survey of Objective Video Quality Measurements , 2006 .

[8]  Andreas Christmann,et al.  Support vector machines , 2008, Data Mining and Knowledge Discovery Handbook.

[9]  Milos Oravec,et al.  SUPPORT VECTOR MACHINES, PCA AND LDA IN FACE RECOGNITION , 2008 .

[10]  Markus Rupp,et al.  Video Quality Estimation for Mobile H.264/AVC Video Streaming , 2008, J. Commun..

[11]  Leonidas J. Guibas,et al.  The Earth Mover's Distance as a Metric for Image Retrieval , 2000, International Journal of Computer Vision.

[12]  Yuukou Horita,et al.  NR objective continuous video quality assessment model based on frame quality measure , 2008, 2008 15th IEEE International Conference on Image Processing.