Video quality assessment and machine learning: Performance and interpretability

In this work we compare a simple and a complex Machine Learning (ML) method used for the purpose of Video Quality Assessment (VQA). The simple ML method chosen is the Elastic Net (EN), which is a regularized linear regression model and easier to interpret. The more complex method chosen is Support Vector Regression (SVR), which has gained popularity in VQA research. Additionally, we present an ML-based feature selection method. Also, it is investigated how well the methods perform when tested on videos from other datasets. Our results show that content-independent cross-validation performance on a single dataset can be misleading and that in the case of very limited training and test data, especially in regards to different content as is the case for many video datasets, a simple ML approach is the better choice.

[1]  Amy R. Reibman,et al.  The Challenge of Estimating Video Quality in Video Communication Applications [In the Spotlight] , 2012, IEEE Signal Processing Magazine.

[2]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[3]  Methods , metrics and procedures for statistical evaluation , qualification and comparison of objective quality prediction models , 2013 .

[4]  Christophe Charrier,et al.  Blind Prediction of Natural Video Quality , 2014, IEEE Transactions on Image Processing.

[5]  Alan C. Bovik,et al.  No-Reference Image Quality Assessment in the Spatial Domain , 2012, IEEE Transactions on Image Processing.

[6]  Jinbo Bi,et al.  Dimensionality Reduction via Sparse Support Vector Machines , 2003, J. Mach. Learn. Res..

[7]  H. Zou,et al.  Regularization and variable selection via the elastic net , 2005 .

[8]  Weisi Lin,et al.  Low-Complexity Video Quality Assessment Using Temporal Quality Variations , 2012, IEEE Transactions on Multimedia.

[9]  R. Brereton,et al.  Support vector machines for classification and regression. , 2010, The Analyst.

[10]  Weisi Lin,et al.  SVD-Based Quality Metric for Image and Video Using Machine Learning , 2012, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[11]  King Ngi Ngan,et al.  Full-Reference Video Quality Assessment by Decoupling Detail Losses and Additive Impairments , 2012, IEEE Transactions on Circuits and Systems for Video Technology.

[12]  Alan C. Bovik,et al.  Video Quality Pooling Adaptive to Perceptual Distortion Severity , 2013, IEEE Transactions on Image Processing.

[13]  Christian Viard-Gaudin,et al.  A Convolutional Neural Network Approach for Objective Video Quality Assessment , 2006, IEEE Transactions on Neural Networks.

[14]  Rajiv Soundararajan,et al.  Study of Subjective and Objective Quality Assessment of Video , 2010, IEEE Transactions on Image Processing.

[15]  Alexander Raake,et al.  No-reference video quality assessment for SD and HD H.264/AVC sequences based on continuous estimates of packet loss visibility , 2011, 2011 Third International Workshop on Quality of Multimedia Experience.

[16]  Vijayan K. Asari,et al.  A no-reference video quality assessment based on Laplacian pyramids , 2013, 2013 IEEE International Conference on Image Processing.

[17]  Piet Demeester,et al.  Constructing a No-Reference H.264/AVC Bitstream-Based Video Quality Metric Using Genetic Programming-Based Symbolic Regression , 2013, IEEE Transactions on Circuits and Systems for Video Technology.

[18]  Jacob Søgaard,et al.  No-Reference Video Quality Assessment Using Codec Analysis , 2015, IEEE Transactions on Circuits and Systems for Video Technology.

[19]  Paolo Gastaldo,et al.  Objective assessment of MPEG-video quality: a neural-network approach , 2001, IJCNN'01. International Joint Conference on Neural Networks. Proceedings (Cat. No.01CH37222).

[20]  Alan C. Bovik,et al.  Making a “Completely Blind” Image Quality Analyzer , 2013, IEEE Signal Processing Letters.

[21]  Hans-Peter Kriegel,et al.  OPTICS: ordering points to identify the clustering structure , 1999, SIGMOD '99.

[22]  Tiago Rosa Maria Paula Queluz,et al.  No-Reference Quality Assessment of H.264/AVC Encoded Video , 2010, IEEE Transactions on Circuits and Systems for Video Technology.

[23]  Gerardo Rubino,et al.  A study of real-time packet video quality using random neural networks , 2002, IEEE Trans. Circuits Syst. Video Technol..