Abstract
In this paper, we want to launch a first step for the classification of images according to their degree of blur based on the subjective measurement of DMOS image quality in the Gblur database. For this purpose, we have carried out a comparative study on several classifiers in order to build a robust learning model based on the transformation into a DCT. The class imbalanced has forced us to look for and find appropriate performance evaluation metrics so that the comparison is not biased. It has been found that random forests (RF) give the best overall performance but that other classifiers discriminate better between certain types of images (depending on the degree of blur) than others. Finally, we compared the classification by the proposed model with another classification based on the NIQE quality measurement algorithm. The results of the model proposed by its simplicity are very promising.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Wang, Z., Bovic, A.C., Sheikh, H.R., Simoncelli, E.P.: Image quality assessment from error visibility to structure similarity. IEEE Trans. Image Process. 4(113), 600–612 (2004)
George, A.G., Prabavathy, K.A.: A survey on different approaches used in image quality assessment. Int. J. Emerg. Technol. Adv. Eng. 3(2) (2013)
Ferzli, R., Karam, L.J.: A Human Visual System Based No-Reference Objective Image Sharpness Metric. In: Editor, F., IEEE International Conference on Image Processing, Atlanta, pp. 2949–2952 (2006)
Ferzli, R., Karam, L.J.: A No-reference objective image sharpness based on the notion of just-noticeable of blur (JNB). IEEE Trans. image processing 18(4), 717–728 (2009)
Zhu, X., Milanfar, P.: A No-Reference Sharpness Metric sensitive to blur and noise. In: First International Workshop on Quality Multimedia Experience, San Diego, pp. 64–69 (2009)
Marziliano, P., Dufaux, F., Winkler, S. and Ebrahimi, T.: A No-Reference Perceptual blur metric. In: International Conference on Image Processing, vol 3, pp. 57–60 (2002)
Ong, E.P, Lin, W.S, Lu, Z.K, Yao, S.S., Yang, X.K, Jiang, L.F.: No-Reference quality Metric for measuring image. In: Proceedings IEEE International Conference on Image Processing, vol. 1, pp. 469–472 (2003)
Caviedes, G.E., Oberti, F.: A new sharpness metric based on local kurtosis, edge and energy information. Sign. Process. Image Commun. 19, 147–163 (2004)
Marichal, X., Ma, W.Y., Zhang, H.: Blur determination in the compressed domain using DCT information. In: Conference: Image Processing, ICIP 99, vol. 2 (1999)
Zhang, N., Vladar, A., Postek, M., Larrabee, B.: A Kurtosis-based statistical for two dimensional process and its application to image sharpness. In: Proceedings Section of physical and engineering Sciences of American Statistical Society, pp. 4730–4736 (2003)
Tang, H., Ming Jing, L. I., Zhang, H.J, Zhang, C.: Blur Detection for Images Using Wavelet Transform Conference of Multimedia and Expositions, vol. 1, pp 17–20 (2009)
Kerrouh, F., Serir, A.: A no-reference quality metric for evaluating blur image in wavelet domain. Int. J. Digital Inf. Wireless Commun. (IJDIWC) 1(4), 767–776 (2012)
Tang, H., Ming Jing, L I., Zhang, H.J, Zhang, C.: Blur Detection for Images using Wavelet Transform. In: Conference of Multimedia and Expositions, vol. 1, pp. 17–20 (2009)
Kerrouh, F.: A No-Reference Quality measure of blurred images (videos), PhD Thesis in Electronics, Univ, Algiers (2014)
Bae, S.H., Kim, M.: A novel DCT-based JND model for luminance adaptation effect in DCT frequency. IEEE Sign. Process. Lett. 20(9), 893–896 (2013)
Cheriet, M., Kharma, N., Liu, C.L., Suen, C.Y.: Character Recognition Systems. Wiley, New Jersey (2007)
Theodoridis, S., Koutroumbas, K.: Pattern Recognition, Fourth Edition, Edited by Academic Press, Elsevier Inc. (2009)
Duda, R.O., Hart, P.O. Stork, D.G.: Pattern Classification, snd Ed. Wiley, New Jersey (1997)
de Sá, J.P.M.: Pattern Recognition. In: Concepts, Methods and Applications. Edited by Springer (2001)
Witten, I.H, Frank, E.: Data Mining, Practical Machine Learning Tools and Technics. Morgan Kauffman Publishers, Elsevier, Burlington (2005)
Vapnick, V.: The Nature of Statistical Learning Theory. Springer, New York (2000)
Mathieu-Dupas, E.: Algorithmes des k plus proches voisins pondérés et application en diagnostic. 42èmes Journées de Statistique, 2010, Marseille, France (2010)
Breiman, L.: Random Forests Machine Learning, vol. 45, no. 1, pp. 5–32. Kluwer academic Publishers, Berlin (2001)
Hamdi, F.: Learning in unbalanced distributions, Doctorate Thesis in Computer Sciences, Univ Paris, vol. 13 (2012)
He, H., Garcia, E.A.: Learning from imbalanced data. IEEE Trans. Knowl. Data Eng. 21(9), 1263–1284 (2009)
Sokolova, M., Japkowicz, N., Szpakowicz, S.: Beyond accuracy, F-score and ROC: a family of discriminant measures for performance evaluation. In: Australasian Joint Conference on Artificial Intelligence, pp. 1015–1021 (2006)
Tharwat, A.: Classification assessment methods. Journal homepage. http://www.sciencedirect.com. Accessed August 2019
Saito, T., Rehmsmeier, M.: The precision-recall plot is more informative than the ROC plot when evaluating binary classifiers on imbalanced datasets, vol. 10, no. 3 (2015)
Davis, J., Goadrich, M.: The relationship between precision-recall and ROC curves. In: Conference: Proceedings of the 23rd International Conference on Machine Learning, pp. 233–240 (2006)
Mittal, A., Soundararajan, R., Bovik, A.C.: Making a “completely blind” image quality analyzer. IEEE Signal Process. Lett. 20(3), 209–212 (2013)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Gueraichi, R., Serir, A. (2020). Comparative Study of Classifiers for Blurred Images. In: Arai, K., Kapoor, S., Bhatia, R. (eds) Intelligent Computing. SAI 2020. Advances in Intelligent Systems and Computing, vol 1229. Springer, Cham. https://doi.org/10.1007/978-3-030-52246-9_23
Download citation
DOI: https://doi.org/10.1007/978-3-030-52246-9_23
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-52245-2
Online ISBN: 978-3-030-52246-9
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)