Abstract
Image motion blur can severely affect the performance of the image recognition model. Traditional methods to tackle this problem usually involve image motion deblurring to improve the image quality before its recognition. However, traditional motion deblurring methods try to minimize the pixel-level distance between the deblurred image and the original image, which is not directly designed for improving the image recognition accuracy of the deblurred image. In this paper, we propose a joint motion deblurring and classification loss-aware solution. First, we introduce recognition loss into the motion deblurring model to improve the semantic quality of the deblurred image. Furthermore, we design a motion-blurred image recognition framework that involves both a motion deblurring module and an image recognition module, which enables the joint learning of the two modules. Finally, we propose to enhance the motion deblurring network with parameterized shortcut connections (PSCs) for balancing the importance between low-level and high-level features in the deblurring process. Experiments on our synthesized datasets have shown the effectiveness of our methods, with significant improvement in both SSIM and classification accuracy, as well as the perceptual quality of the deblurred images.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Boracchi, G., Foi, A.: Modeling the performance of image restoration from motion blur. IEEE Trans. Image Process. 21(8), 3502–3517 (2012)
Cai, D., Chen, K., Qian, Y., Kämäräinen, J.K.: Convolutional low-resolution fine-grained classification. Pattern Recogn. Lett. 119, 166–171 (2019)
Chan, T.F., Wong, C.K.: Total variation blind deconvolution. IEEE Trans. Image Process. Publ. IEEE Signal Process. Soc. 7(3), 370 (1998)
Everingham, M., Van Gool, L., Williams, C.K.I., Winn, J., Zisserman, A.: The PASCAL visual object classes challenge 2012 (VOC2012) results (2012). http://www.pascal-network.org/challenges/VOC/voc2012/workshop/index.html
Griffin, G., Holub, A., Perona, P.: The caltech 256 (technical report). Caltech Computation and Neural Systems (2006)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. IEEE (2016)
Huang, G., Liu, Z., Laurens, V., Weinberger, K.Q.: Densely connected convolutional networks. IEEE Computer Society (2016)
Kai, Z., Zuo, W., Gu, S., Lei, Z.: Learning deep CNN denoiser prior for image restoration. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)
Kupyn, O., Budzan, V., Mykhailych, M., Mishkin, D., Matas, J.: DeblurGAN: blind motion deblurring using conditional adversarial networks. In: 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2018)
Kupyn, O., Martyniuk, T., Wu, J., Wang, Z.: DeblurGAN-v2: deblurring (orders-of-magnitude) faster and better. IEEE (2019)
Liu, D., Cheng, B., Wang, Z., Zhang, H., Huang, T.S.: Enhance visual recognition under adverse conditions via deep networks. IEEE Trans. Image Process. 28(9), 4401–4412 (2017)
Liu, D., Wen, B., Liu, X., Wang, Z., Huang, T.S.: When image denoising meets high-level vision tasks: a deep learning approach (2017)
Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 39(4), 640–651 (2015)
Nah, S., Hyun Kim, T., Mu Lee, K.: Deep multi-scale convolutional neural network for dynamic scene deblurring. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3883–3891 (2017)
Pan, J., Sun, D., Pfister, H., Yang, M.H.: Blind image deblurring using dark channel prior. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016)
Pei, Y., Huang, Y., Zou, Q., Zang, H., Zhang, X., Wang, S.: Effects of image degradations to CNN-based image classification. arXiv preprint arXiv:1810.05552 (2018)
Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234–241. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-24574-4_28
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. Computer Science (2014)
Srivastava, R.K., Greff, K., Schmidhuber, J.: Highway networks. Computer Science (2015)
Szegedy, C., Wei, L., Jia, Y., Sermanet, P., Rabinovich, A.: Going deeper with convolutions. IEEE Computer Society (2014)
Tao, X., Gao, H., Wang, Y., Shen, X., Wang, J., Jia, J.: Scale-recurrent network for deep image deblurring. In: 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition (2018)
Acknowledgements
This work is supported in part by NSFC (Grant No. 61872215), Shenzhen Science and Technology Program (Grant No. RCYX20200714114523079), and Shenzhen Nanshan District Ling-Hang Team Project (Grant No. LHTD20170005).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Zhang, W., Wang, Z. (2021). Blurred Image Recognition: A Joint Motion Deblurring and Classification Loss-Aware Approach. In: Farkaš, I., Masulli, P., Otte, S., Wermter, S. (eds) Artificial Neural Networks and Machine Learning – ICANN 2021. ICANN 2021. Lecture Notes in Computer Science(), vol 12892. Springer, Cham. https://doi.org/10.1007/978-3-030-86340-1_9
Download citation
DOI: https://doi.org/10.1007/978-3-030-86340-1_9
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-86339-5
Online ISBN: 978-3-030-86340-1
eBook Packages: Computer ScienceComputer Science (R0)