Abstract. 

The work is aimed at developing tools for automatic selection and filtering of blurry images. The paper describes a method of automatic generation of synthetic blurry images, which is based on the algorithm for specifying the point scattering function. Triple of scene images consists of clear,unfocused and blurred in motion images. The model base of various scene photographs was collected. This base is applied to test and evaluate the quality of methods and algorithms for detection of blurry images. The suggested method of blurry image generation can be used in methods of automatic image processing and machine learning.

Keywords: 

image processing, blurry image detection, blurry image generation

PP. 90-95.

DOI 10.14357/20718632200408

 

References

1. Alekseev A.V., Rozaliev V.L., Orlova Y.A. Automatic coloring of grayscale images based on intelligent scene analysis // Pattern Recognition and Image Analysis (Advances in Mathematical Theory and Applications). 2015. Vol.25. No.1. P.10-21.

2. Mavridaki E., Mezaris V. No-Reference blur assessment in natural images using Fourier transform and spatial pyramids // Proceedings of the IEEE International Conference on Image Processing. 2014.

3. Jianping Shi, Li Xu, Jiaya Jia. Discriminative blur detection features // Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. 2014.

4. Drutsa A., Farafonova V., Fedorova V., Megorskaya O., Zerminova E., Zhilinskaya O. Practice of efficient data collection via crowdsourcing at large-scale. 2019. https://arxiv.org/abs/1912.04444.

5. Alekseev A.V., Rozaliev V.L., Orlova Y.A., Zaboleeva-Zotova A.V. Context-sensitive image analysis for coloring nature images // Advances in Intelligent Systems and Computing. 2016. Vol. 451. P.133-141. Springer International Publishing.

6. Alekseev A.V., Orlova Y.A., Rozaliev V.L., Zaboleeva-Zotova A.V. Two-stage segmentation method for context-sensitive image analysis // Communications in Computer and Information Science. 2014. Vol.466. P.331-340. Springer International Publishing.

7. Kupyn O., Budzan V., Mykhailych M., Mishkin D., Matas J. DeblurGAN: Blind motion deblurring using conditional adversarial networks // Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. 2018. P.8183–8192. https://doi.org/10.1109/CVPR.2018.00854.

8. Bansal R., Raj G., Choudhury T. Blur image detection using Laplacian operator and Open-CV // International Conference System Modeling Advancement in Research Trends. 2016. P.63–67. https://doi.org/10.1109/SYSMART.2016.7894491.

9. Li L., Pan J., Lai W.S., Gao C., Sang N., Yang M.H. Blind image deblurring via deep discriminative priors // International Journal of Computer Vision. 2018. https://doi.org/10.1007/s11263-018-01146-0.

10. Zhang J., Pan J., Ren J., Song Y., Bao L., Lau W.H., Yang M.H. Dynamic scene deblurring using spatially variant recurrent neural networks // Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. 2018. P.2521–2529. https://doi.org/10.1109/CVPR.2018.00267.