Robustness and prediction accuracy of Machine Learning for objective visual quality assessment. Hines, A., Kendrick, P., Barri, A., Narwaria, M., & Redi, J. A. In 2014 22nd European Signal Processing Conference (EUSIPCO), pages 2130-2134, Sep., 2014. Paper abstract bibtex Machine Learning (ML) is a powerful tool to support the development of objective visual quality assessment metrics, serving as a substitute model for the perceptual mechanisms acting in visual quality appreciation. Nevertheless, the reliability of ML-based techniques within objective quality assessment metrics is often questioned. In this study, the robustness of ML in supporting objective quality assessment is investigated, specifically when the feature set adopted for prediction is suboptimal. A Principal Component Regression based algorithm and a Feed Forward Neural Network are compared when pooling the Structural Similarity Index (SSIM) features perturbed with noise. The neural network adapts better with noise and intrinsically favours features according to their salient content.
@InProceedings{6952766,
author = {A. Hines and P. Kendrick and A. Barri and M. Narwaria and J. A. Redi},
booktitle = {2014 22nd European Signal Processing Conference (EUSIPCO)},
title = {Robustness and prediction accuracy of Machine Learning for objective visual quality assessment},
year = {2014},
pages = {2130-2134},
abstract = {Machine Learning (ML) is a powerful tool to support the development of objective visual quality assessment metrics, serving as a substitute model for the perceptual mechanisms acting in visual quality appreciation. Nevertheless, the reliability of ML-based techniques within objective quality assessment metrics is often questioned. In this study, the robustness of ML in supporting objective quality assessment is investigated, specifically when the feature set adopted for prediction is suboptimal. A Principal Component Regression based algorithm and a Feed Forward Neural Network are compared when pooling the Structural Similarity Index (SSIM) features perturbed with noise. The neural network adapts better with noise and intrinsically favours features according to their salient content.},
keywords = {feedforward neural nets;image processing;learning (artificial intelligence);principal component analysis;regression analysis;objective visual quality assessment metrics;substitute model;perceptual mechanisms;visual quality appreciation;ML-based techniques;feature set;principal component regression based algorithm;feed forward neural network;structural similarity index features;SSIM features;salient content;prediction accuracy;Noise;Sensitivity;Quality assessment;Image quality;Noise level;Noise measurement;image quality assessment;SSIM;neural networks;machine learning},
issn = {2076-1465},
month = {Sep.},
url = {https://www.eurasip.org/proceedings/eusipco/eusipco2014/html/papers/1569923531.pdf},
}
Downloads: 0
{"_id":"7WdpC6dzdm7z2yQZT","bibbaseid":"hines-kendrick-barri-narwaria-redi-robustnessandpredictionaccuracyofmachinelearningforobjectivevisualqualityassessment-2014","authorIDs":[],"author_short":["Hines, A.","Kendrick, P.","Barri, A.","Narwaria, M.","Redi, J. A."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","author":[{"firstnames":["A."],"propositions":[],"lastnames":["Hines"],"suffixes":[]},{"firstnames":["P."],"propositions":[],"lastnames":["Kendrick"],"suffixes":[]},{"firstnames":["A."],"propositions":[],"lastnames":["Barri"],"suffixes":[]},{"firstnames":["M."],"propositions":[],"lastnames":["Narwaria"],"suffixes":[]},{"firstnames":["J.","A."],"propositions":[],"lastnames":["Redi"],"suffixes":[]}],"booktitle":"2014 22nd European Signal Processing Conference (EUSIPCO)","title":"Robustness and prediction accuracy of Machine Learning for objective visual quality assessment","year":"2014","pages":"2130-2134","abstract":"Machine Learning (ML) is a powerful tool to support the development of objective visual quality assessment metrics, serving as a substitute model for the perceptual mechanisms acting in visual quality appreciation. Nevertheless, the reliability of ML-based techniques within objective quality assessment metrics is often questioned. In this study, the robustness of ML in supporting objective quality assessment is investigated, specifically when the feature set adopted for prediction is suboptimal. A Principal Component Regression based algorithm and a Feed Forward Neural Network are compared when pooling the Structural Similarity Index (SSIM) features perturbed with noise. The neural network adapts better with noise and intrinsically favours features according to their salient content.","keywords":"feedforward neural nets;image processing;learning (artificial intelligence);principal component analysis;regression analysis;objective visual quality assessment metrics;substitute model;perceptual mechanisms;visual quality appreciation;ML-based techniques;feature set;principal component regression based algorithm;feed forward neural network;structural similarity index features;SSIM features;salient content;prediction accuracy;Noise;Sensitivity;Quality assessment;Image quality;Noise level;Noise measurement;image quality assessment;SSIM;neural networks;machine learning","issn":"2076-1465","month":"Sep.","url":"https://www.eurasip.org/proceedings/eusipco/eusipco2014/html/papers/1569923531.pdf","bibtex":"@InProceedings{6952766,\n author = {A. Hines and P. Kendrick and A. Barri and M. Narwaria and J. A. Redi},\n booktitle = {2014 22nd European Signal Processing Conference (EUSIPCO)},\n title = {Robustness and prediction accuracy of Machine Learning for objective visual quality assessment},\n year = {2014},\n pages = {2130-2134},\n abstract = {Machine Learning (ML) is a powerful tool to support the development of objective visual quality assessment metrics, serving as a substitute model for the perceptual mechanisms acting in visual quality appreciation. Nevertheless, the reliability of ML-based techniques within objective quality assessment metrics is often questioned. In this study, the robustness of ML in supporting objective quality assessment is investigated, specifically when the feature set adopted for prediction is suboptimal. A Principal Component Regression based algorithm and a Feed Forward Neural Network are compared when pooling the Structural Similarity Index (SSIM) features perturbed with noise. The neural network adapts better with noise and intrinsically favours features according to their salient content.},\n keywords = {feedforward neural nets;image processing;learning (artificial intelligence);principal component analysis;regression analysis;objective visual quality assessment metrics;substitute model;perceptual mechanisms;visual quality appreciation;ML-based techniques;feature set;principal component regression based algorithm;feed forward neural network;structural similarity index features;SSIM features;salient content;prediction accuracy;Noise;Sensitivity;Quality assessment;Image quality;Noise level;Noise measurement;image quality assessment;SSIM;neural networks;machine learning},\n issn = {2076-1465},\n month = {Sep.},\n url = {https://www.eurasip.org/proceedings/eusipco/eusipco2014/html/papers/1569923531.pdf},\n}\n\n","author_short":["Hines, A.","Kendrick, P.","Barri, A.","Narwaria, M.","Redi, J. A."],"key":"6952766","id":"6952766","bibbaseid":"hines-kendrick-barri-narwaria-redi-robustnessandpredictionaccuracyofmachinelearningforobjectivevisualqualityassessment-2014","role":"author","urls":{"Paper":"https://www.eurasip.org/proceedings/eusipco/eusipco2014/html/papers/1569923531.pdf"},"keyword":["feedforward neural nets;image processing;learning (artificial intelligence);principal component analysis;regression analysis;objective visual quality assessment metrics;substitute model;perceptual mechanisms;visual quality appreciation;ML-based techniques;feature set;principal component regression based algorithm;feed forward neural network;structural similarity index features;SSIM features;salient content;prediction accuracy;Noise;Sensitivity;Quality assessment;Image quality;Noise level;Noise measurement;image quality assessment;SSIM;neural networks;machine learning"],"metadata":{"authorlinks":{}},"downloads":0},"bibtype":"inproceedings","biburl":"https://raw.githubusercontent.com/Roznn/EUSIPCO/main/eusipco2014url.bib","creationDate":"2021-02-13T17:43:41.771Z","downloads":0,"keywords":["feedforward neural nets;image processing;learning (artificial intelligence);principal component analysis;regression analysis;objective visual quality assessment metrics;substitute model;perceptual mechanisms;visual quality appreciation;ml-based techniques;feature set;principal component regression based algorithm;feed forward neural network;structural similarity index features;ssim features;salient content;prediction accuracy;noise;sensitivity;quality assessment;image quality;noise level;noise measurement;image quality assessment;ssim;neural networks;machine learning"],"search_terms":["robustness","prediction","accuracy","machine","learning","objective","visual","quality","assessment","hines","kendrick","barri","narwaria","redi"],"title":"Robustness and prediction accuracy of Machine Learning for objective visual quality assessment","year":2014,"dataSources":["A2ezyFL6GG6na7bbs","oZFG3eQZPXnykPgnE"]}