Abstract.

Recognition and machine vision systems have long been widely used in many disciplines to automate various processes of life and industry. Input images of optical recognition systems can be subjected to a large number of different distortions, especially in uncontrolled or natural shooting conditions, which leads to unpredictable results of recognition systems, making it impossible to assess their reliability. For this reason, it is necessary to perform quality control of the input data of recognition systems, which is facilitated by modern progress in the field of image quality evaluation. In this paper, we investigate the approach to designing optical recognition systems with built-in input image quality estimation modules and feedback, for which the necessary definitions are introduced and a model for describing such systems is constructed. The efficiency of the approach is illustrated by the example of solving the problem of selecting the best frames for recognition in a video stream. Experimental results are presented with the system of recognition of identity documents, showing a significant increase in the accuracy and speed of the system under simulated conditions of automatic camera focusing, leading to blurring of frames.

Keywords:

recognition systems, image quality assessment, video stream, blur, defocus, systems analysis.

PP. 71-82.

References

1. H. Golnabi and A. Asadpour, “Design and application of industrial machine vision systems,” Robotics and Computer- Integrated Manufacturing, vol. 23, no. 6, pp. 630–637, 2007.
2. O. Russakovsky et al., “Imagenet large scale visual recognition challenge,” International Journal of Computer Vision, vol.  115, no. 3, pp. 211–252, 2015.
3. K. B. Bulatov and D. V. Polevoy, “Reducing overconfidence in neural networks by dynamic variation of recognizer relevance.” in ECMS, 2015, pp. 488–491.
4. V. Arlazarov, K. Bulatov, and S. Karpenko, “A method for estimating reliability of embossed symbols recognition,” Institute for Systems Analysis RAS Journal 63(3), 117–122 (2013).
5. V. Arlazarov, A. Zhukovsky, V. Krivtsov, D. Nikolaev, and D. Polevoy, “Analysis of specifics of using stationary and mobile small-sized digital cameras for document recognition,” Information Technologies and Systems (3) (2014).
6. S. F. Dodge and L. J. Karam, “Understanding how image quality affects deep neural networks,” CoRR, vol. abs/1604.04004, 2016.
7. P. Mohammadi, A. Ebrahimi-Moghadam, and S. Shirani, “Subjective and objective quality assessment of image: A survey,” CoRR, vol. abs/1406.7799, 2014.
8. A. Dutta, R. N. J. Veldhuis, and L. J. Spreeuwers, “Predicting face recognition performance using image quality,” CoRR, vol. abs/1510.07119, 2015.
9. P. Ye and D. Doermann, “Document Image Quality Assessment: A Brief Survey,” 2013 12th International Conference on Document Analysis and Recognition, pp. 723–727, 2013.
10. G. J. Awcock and R. Thomas, Applied image processing. McGraw-Hill, Inc., 1995.
11. S. T. Bow, Pattern recognition and image preprocessing. CRC press, 2002.
12. M. A. Povolotskiy, E. G. Kuznetsova, and T. M. Khanipov, “Russian license plate segmentation based on dynamic time warping,” in European conference on modelling and simulation, 2017, proceedings., 2017, pp. 285–291.
13. C. Gürel and A. Erden, “Design of a face recognition system,” in Proc. The 15th int. Conference on machine design and  production (umtik 2012), 2012.
14. K. Bulatov, V. Arlazarov, T. Chernov, O. Slavin, and D. Nikolaev, “Smart IDReader: Document recognition in video stream,” in 7th international workshop on camera based document analysis and recognition, 2017.
15. F. Schroff, D. Kalenichenko, and J. Philbin, “Facenet: A unified embedding for face recognition and clustering,” in  Proceedings of the IEEE conference on computer vision and pattern recognition, 2015, pp. 815–823.
16. T. Manzhikov, O. Slavin, I. Faradzhev, and I. Janiszewski, “N-grams algorithm application for the correction of recognition results,” Вестник Российского фонда фундаментальных исследований, vol. 92, no. 4, pp. 116–123, 2016.
17. J. G. Fiscus, “A post-processing system to yield reduced word error rates: Recognizer output voting error reduction (rover),” in Automatic speech recognition and understanding, 1997. Proceedings., 1997, pp. 347–354.
18. A. Minkina, D. Nikolaev, S. Usilin, and V. Kozyrev, “Generalization of the viola-jones method as a decision tree of strong classifiers for real-time object recognition in video stream,” in ICMV 2014, proceedings., 2015.
19. X. Wang et al., “Client side filtering of card ocr images.” Google Patents, dec~2-2014.
20. E. A. Shvets and D. P. Nikolaev, “Complex approach to long-term multi-agent mapping in low dynamic environments,” in 8’th international conference on machine vision, 2015.
21. X. Xu, Y. Wang, J. Tang, X. Zhang, and X. Liu, “Robust automatic focus algorithm for low contrast images using a new contrast measure,” Sensors, vol. 11, no. 9, pp. 8281–8294, 2011.