Abstract
Blur is a common phenomenon in image acquisition that negatively influences the recognition rate of most classifiers. This paper studies the influence of image blurring of various types and sizes on the recognition rate achieved by a deep convolutional network. We confirm that the blur significantly decreases the performance if the network has been trained on clear images only. When the training set is augmented with blurred samples, the recognition rate becomes sufficiently high even if the blur in query images is of different size than the blur used for training. However, this is mostly not true if query images contain blur of a different type from the one used for training.
This work was supported by the Czech Science Foundation (Grant No. GA21-03921S) and by the Praemium Academiae.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Campisi, P., Egiazarian, K.: Blind Image Deconvolution: Theory and Applications. CRC, Boca Raton (2007)
Rajagopalan, A.N., Chellappa, R.: Motion Deblurring: Algorithms and Systems. Cambridge University Press, Cambridge (2014)
Flusser, J., Suk, T., Zitová, B.: 2D and 3D Image Analysis by Moments. Wiley, Chichester (2016)
Zhang, Z., Klassen, E., Srivastava, A.: Gaussian blurring-invariant comparison of signals and images. IEEE Trans. Image Process. 22(8), 3145–3157 (2013)
Gopalan, R., Turaga, P., Chellappa, R.: A blur-robust descriptor with applications to face recognition. IEEE Trans. Pattern Anal. Mach. Intell. 34(6), 1220–1226 (2012)
Vageeswaran, P., Mitra, K., Chellappa, R.: Blur and illumination robust face recognition via set-theoretic characterization. IEEE Trans. Image Process. 22(4), 1362–1372 (2013)
Lébl, M., Šroubek, F., Kautský, J., Flusser, J.: Blur invariant template matching using projection onto convex sets. In: Proceedings of 18th International Conference on Computer Analysis of Images and Patterns, CAIP 2019, pp. 351–362 (2019)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Los Alamitos, CA, USA, June 2016, pp. 770–778. IEEE Computer Society (2016)
Georghiades, A.S., Belhumeur, P.N., Kriegman, D.J.: From few to many: illumination cone models for face recognition under variable lighting and pose. IEEE Trans. Pattern Anal. Mach. Intelligence 23(6), 643–660 (2001)
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., Fei-Fei, L.: Imagenet: a large-scale hierarchical image database. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 248–255 (2009)
Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. Commun. ACM 60(6), 84–90 (2017)
Cubuk, E.D., Zoph, B., Mané, D., Vasudevan, V., Le, Q.V.: Autoaugment: learning augmentation strategies from data. In: IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 113–123 (2019)
Vasiljevic, I., Chakrabarti, A., Shakhnarovich, G.: Examining the impact of blur on recognition by convolutional networks. arXiv preprint arXiv:1611.05760 (2016)
Zhou, Y., Song, S., Cheung, N.: On classification of distorted images with deep convolutional neural networks. In: 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 1213–1217. IEEE (2017)
Dodge, S., Karam, L.: Understanding how image quality affects deep neural networks. In: 2016 Eighth International Conference on Quality of Multimedia Experience (QoMEX), pp. 1–6. IEEE (2016)
Pei, Y., Huang, Y., Zou, Q., Zhang, X., Wang, S.: Effects of image degradation and degradation removal to CNN-based image classification. IEEE Transactions on Pattern Analysis and Machine Intelligence 43(4), 1239–1253 (2021)
Paszke, A., et al.: Pytorch: an imperative style, high-performance deep learning library. In: Wallach, H., Larochelle, H., Beygelzimer, A., Alché-Buc, F., Fox, E., Garnett, R. (eds.) Advances in Neural Information Processing Systems, vol. 32, pp. 8024–8035. Curran Associates Inc. (2019)
Flusser, J., Suk, T., Boldyš, J., Zitová, B.: Projection operators and moment invariants to image blurring. IEEE Trans. Pattern Anal. Mach. Intell. 37(4), 786–802 (2015)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Lébl, M., Šroubek, F., Flusser, J. (2023). Impact of Image Blur on Classification and Augmentation of Deep Convolutional Networks. In: Gade, R., Felsberg, M., Kämäräinen, JK. (eds) Image Analysis. SCIA 2023. Lecture Notes in Computer Science, vol 13886. Springer, Cham. https://doi.org/10.1007/978-3-031-31438-4_8
Download citation
DOI: https://doi.org/10.1007/978-3-031-31438-4_8
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-31437-7
Online ISBN: 978-3-031-31438-4
eBook Packages: Computer ScienceComputer Science (R0)
