<div>
	PATTERN RECOGNITION METHODS IN CASE OF VISUAL INFORMATION SEMANTIC INTEGRITY VIOLATIONS</div>

Yulia V. Kim, Anastasia A. Matveeva, Viksnin Ilya  I.

doi:10.17586/2226-1494-2018-18-5-809-816

2018 , VOLUME 18, NUMBER 5 ( September-October )

ISSN 2226-1494 (print), ISSN 2500-0373 (online)

Publications

Editor-in-Chief

Nikiforov
Vladimir O.
D.Sc., Prof.

Partners

doi: 10.17586/2226-1494-2018-18-5-809-816

PATTERN RECOGNITION METHODS IN CASE OF VISUAL INFORMATION SEMANTIC INTEGRITY VIOLATIONS

Y. V. Kim, A. A. Matveeva, I. I. Viksnin

Read the full article

Article in Russian

For citation:

Kim I.V., Matveeva A.A., Viksnin I.I. Pattern recognition methods in case of visual information semantic integrity violations. Scientific and Technical Journal of Information Technologies, Mechanics and Optics, 2018, vol. 18, no. 5, pp. 809–816 (in Russian). doi: 10.17586/2226-1494-2018-18-5-809-816

Abstract

We consider computer vision issues with a view to embed it into vehicles and automate the traffic process by detecting of objects and road users. Three basic stages of pattern recognition in the image are enumerated: image preparation for analysis, analysis, object classification. The search of methods that improve pattern recognition quality and provide visual information semantic integrity was carried out respectively for each stage. We propose to use normalization for the first stage, which allows making image objects insensitive to the light changes. For the second stage clustering method based on particle swarm optimization and k-means was developed that provides automatic tuning of clustering parameters. During the third stage Haar cascades with normalized training samples are proposed for application providing object unification and giving an opportunity to use less amount of training samples. Car images provided by Stanford University laboratory and publicly available were used for training and testing. To assess the effectiveness of the developed pattern recognition algorithm, 300 test images were blurred. We compared the results of the proposed algorithm operation with Haar cascades operating results without normalized training samples and without preparation for classification. Haar cascades with non-normalized training images provided correct car recognition in 8% of cases, meanwhile, the proposed algorithm recognized 72% of cases including those 8% of images. Visual information semantic integrity preservation is an important aspect in context of road traffic, because incorrect object detection can cause fatal consequences. The proposed algorithm of image analysis reduces the probability of error occurrences during pattern recognition.

Keywords: computer vision, semantic integrity, information security, visual information, pattern recognition

References

Dunjko V., Briegel H.J. Machine learning & artificial intelligence in the quantum domain: a review of recent progress. Reports on Progress in Physics, 2018, vol. 81, no. 7, art. 074001. doi: 10.1088/1361-6633/aab406
Forsyth D.A., Ponce J. Computer Vision: A Modern Approach. Prentice Hall, 2003.
Neto U.B., Dougherty E.R. Error Estimation for Pattern Recognition. NY, Wiley, 2015, 321 p.
Akinin M.V., Akinina A.V., Sokolov A.V., Tarasov A.S. Application of EM algorithm in problems of pattern recognition on satellite images. Proc. 6^th Mediterranean Conference on Embedded Computing. Bar, Montenegro, 2017, 4 p. doi: 10.1109/meco.2017.7977190
Jovanov I., Pajic M. Sporadic data integrity for secure state estimation. Proc. IEEE 56^th Annual Conference on Decision and Control. Melbourne, Australia, 2017, pp. 163–169. doi: 10.1109/cdc.2017.8263660
Santra P., Roy A., Majumder K. A Comparative analysis of cloud forensic techniques in IaaS. Advances in Intelligent Systems and Computing, 2017, vol. 554, pp. 207–215. doi: 10.1007/978-981-10-3773-3_20
Singh S., Sinha M. Pattern recognition based on specific weights. International Journal of Applied Pattern Recognition, 2018, vol. 5, pp. 1–10. doi: 10.1504/ijapr.2018.090518
Israfilov H.S. Research of methods for binarization of images. Herald of Science and Education, 2017, vol. 2, no. 6, pp. 43–50. (in Russian)
Tsvetkov V.I. Semantics of Messages in Telecommunication Systems. Available at: http://window.edu.ru/catalog/pdf2txt/178/56178/27141?p_page=2 (accessed: 03.09.2018).
Aly A.A., Deris S.B., Zaki N. Research review for digital image segmentation techniques. International Journal of Computer Science & Information Technology, 2011, vol. 3, no. 5, pp. 99–105. doi: 10.5121/ijcsit.2011.3509
Li N., Liu M., Li Y. Image segmentation algorithm using watershed transform and level set method. Proc. IEEE Int. Conf. on Acoustics, Speech and Signal Processing. Honolulu, 2007, pp. 613–616. doi: 10.1109/icassp.2007.365982
Guo Y., Liu Y., Georgiou T., Lew M.S. A review of semantic segmentation using deep neural networks. International Journal of Multimedia Information Retrieval, 2017, vol. 7, no. 2, pp. 87–93. doi: 10.1007/s13735-017-0141-z
Fachrurrozi E.M., Fiqih A., Saputra B.R., Algani R., Primanita A. Content based image retrieval for multi-objects fruits recognition using k-means and k-nearest neighbor. Proc. Int. Conf. on Data and Software Engineering. Palembang, Indonesia, 2017. doi: 10.1109/icodse.2017.8285855
Karpenko A.P., Seliverstov E.Y. Overview of the particle swarm methods for the global optimization problem. Science and Education: a scientific edition of the Bauman Moscow State Technical University, 2009, vol. 3, p. 2. (in Russian)
Viksnin I.I., Drannik A.L., Iureva R.A., Komarov I.I. Flocking factors' assessment in case of destructive impact on swarm robotic systems. Proc. 18^th Conference of Open Innovations Association and Seminar on Information Security and Protection of Information Technology. St. Petersburg, Russia, 2016, pp. 357–363. doi: 10.1109/fruct-ispit.2016.7561550
Leng K. An improved non-local means algorithm for image denoising. Proc. IEEE 2^nd Int. Conf. on Signal and Image Processing, 2017, pp. 149–153. doi: 10.1109/siprocess.2017.8124523
Cars Dataset. URL: https://ai.stanford.edu/~jkrause/cars/car_dataset.html (accessed: 15.02.2018).
Ke R., Li Z., Tang J., Pan Z., Wang Y. Real-time traffic flow parameter estimation from UAV video based on ensemble classifier and optical flow. IEEE Transactions on Intelligent Transportation Systems, 2018, pp. 1–11. doi: 10.1109/tits.2018.2797697

This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License