TENSOR AND VECTOR APPROACHES TO OBJECTS RECOGNITION BY INVERSE FEATURE FILTERS
Roman Kvуetnyy
rkvetny@sprava.netVinnytsia National Technical University (Ukraine)
https://orcid.org/0000-0002-9192-9258
Yuriy Bunyak
Vinnytsia Mykhailo Kotsiubynskyi State Pedagogical University (Ukraine)
https://orcid.org/0000-0002-0862-880X
Olga Sofina
Vinnitsia National Technical University (Ukraine)
https://orcid.org/0000-0003-3774-9819
Volodymyr Kotsiubynskyi
Vinnitsia National Technical University (Ukraine)
https://orcid.org/0000-0001-6759-5078
Tetiana Piliavoz
Vinnitsia National Technical University (Ukraine)
https://orcid.org/0000-0001-7535-7360
Olena Stoliarenko
Vinnytsia Mykhailo Kotsiubynskyi State Pedagogical University (Ukraine)
https://orcid.org/0000-0002-1899-8089
Saule Kumargazhanova
D. Serikbayev East Kazakhstan Technical University (Kazakhstan)
https://orcid.org/0000-0002-6744-4023
Abstract
The investigation of the extraction of image objects features by filters based on tensor and vector data presentation is considered. The tensor data is obtained as a sum of rank-one tensors, given by the tensor product of the vector of lexicographic representation of image fragments pixels with itself. The accumulated tensor is approximated by one rank tensor obtained using singular values decomposition. It has been shown that the main vector of the decomposition can be considered as the object feature vector. The vector data is obtained by accumulating analogous vectors of image fragments pixels. The accumulated vector is also considered as an object feature. The filter banks of a set of objects are obtained by regularized inversion of the matrices compiled by object features vectors. Optimized regularization of the inversion is used to expand the regions of object features capture with minimal error. The object fragments and corresponding feature vectors are selected through a training iterative process. The tensor and vector approaches create two channels for recognition. High efficiency of object recognition can be achieved by choosing the filter capture band and creating filter branches according to the given bands. The filters create a convolutional network to recognize a set of objects. It has been shown that the obtained filters have an advantage over known correlation filters when recognizing objects with small fragments.
Keywords:
objects recognition, objects feature, image data tensor, image data vector, inverse filters, optimized regularizationReferences
Andaló F. A. et al.: Shape feature extraction and description based on tensor scale. Pattern Recognition 43(1), 2010, 26–36 [https://doi.org/10.1016/j.patcog.2009.06.012].
Google Scholar
Avrunin O. G. et al.: Features of image segmentation of the upper respiratory tract for planning of rhinosurgical surgery. 39th International Conference on Electronics and Nanotechnology, ELNANO 2019, 485–488.
Google Scholar
Deng Y., Tang X., Qu A.: Correlation Tensor Decomposition and Its Application in Spatial Imaging Data. J. of the American Statistical Association 118(541), 2023, 440–456 [https://doi.org/10.1080/01621459.2021.1938083].
Google Scholar
De Lathauwer L.: Signal Processing based on Multilinear Algebra. PhD thesis, Katholieke Universiteit Leuven, 1997.
Google Scholar
Dubrovin B. A., Fomenko A. T., Novikov S. P.: Modern Geometry – Methods and Applications Pt. 1. Springer, New York 1992.
Google Scholar
Comon P.: Tensor decomposition: State of the art and applications. V. J. G. McWhirter, I. K. Proudler (eds): Mathematics in Signal Processing, Oxford University Press, Oxford 2002.
Google Scholar
Fernandez J. A. et al.: Zero-Aliasing Correlation Filters for Object Recognition. IEEE Trans. on Pattern Analysis and Machine Intelligence 37(8), 2015, 1702–1715.
Google Scholar
Fu Y., Huang T. S.: Image Classification Using Correlation Tensor Analysis. IEEE Trans on Image Processing 17(2), 2008, 226–234.
Google Scholar
Grasedyck L.: Hierarchical Singular Value Decomposition of Tensors. SIAM Journal on Matrix Analysis and Applications 31(4), 2010 2029–2054 [https://doi.org/10.1137/090764189].
Google Scholar
Kolda T. G., Bader B. W.: Tensor decompositions and applications. SIAM Rev. 51, 2009, 455–500.
Google Scholar
Kvуetnyy R. et al.: Inverse correlation filters of objects features with optimized regularization for image processing. Proc. SPIE 12476, 2022, 124760Q [https://doi.org/10.1117/12.2664497].
Google Scholar
Orazayeva A. et al.: Biomedical image segmentation method based on contour preparation. Proc. SPIE 12476, 2022, 1247605 [https://doi.org/10.1117/12.2657929].
Google Scholar
Oseledets I. V.: Tensor-train decomposition. SIAM Journal on Scientific Computing 33(5), 2011, 2295–2317 [https://doi.org/10.1137/090752286].
Google Scholar
Pavlov S. V.: Information Technology in Medical Diagnostics. W. Wójcik, A. Smolarz (eds), CRC Press, 2017.
Google Scholar
Panagakis Y. et al.: Тensor Methods in Computer Vision and Deep Learning. Proceedings of the IEEE 105(5), 2021, 863–890 [https://doi.org/10.1109/JPROC.2021.3074329].
Google Scholar
Phan A. H., Cichocki A.: Tensor decompositions for feature extraction and classification of high dimensional datasets. Nonlinear Theory and Its Applications IEICE 1(1), 2010, 37–68 [https://doi.org/10.1587/nolta.1.37].
Google Scholar
Timchenko L. I. et al.: Q-processors for real-time image processing. Proc. SPIE 11581, 2020, 115810F [https://doi.org/10.1117/12.2580230].
Google Scholar
Tucker L. R.: Some mathematical notes on three mode factor analysis. Psychometrika 31(3), 1966, 279–311 [https://doi.org/10.1007/BF02289464].
Google Scholar
Vijaya Кumar B. V. K., Mahalanobis A., Juday R. D.: Correlation pattern recognition. Cambridge University Press, Cambridge 2005.
Google Scholar
Wilkinson J. H., Reinsch C.: Handbook for Automatic Computation. Linear Algebra. Heidelberg New York, Springer Verlag, Berlin, 1974.
Google Scholar
Authors
Roman Kvуetnyyrkvetny@sprava.net
Vinnytsia National Technical University Ukraine
https://orcid.org/0000-0002-9192-9258
Authors
Yuriy BunyakVinnytsia Mykhailo Kotsiubynskyi State Pedagogical University Ukraine
https://orcid.org/0000-0002-0862-880X
Authors
Olga SofinaVinnitsia National Technical University Ukraine
https://orcid.org/0000-0003-3774-9819
Authors
Volodymyr KotsiubynskyiVinnitsia National Technical University Ukraine
https://orcid.org/0000-0001-6759-5078
Authors
Tetiana PiliavozVinnitsia National Technical University Ukraine
https://orcid.org/0000-0001-7535-7360
Authors
Olena StoliarenkoVinnytsia Mykhailo Kotsiubynskyi State Pedagogical University Ukraine
https://orcid.org/0000-0002-1899-8089
Authors
Saule KumargazhanovaD. Serikbayev East Kazakhstan Technical University Kazakhstan
https://orcid.org/0000-0002-6744-4023
Statistics
Abstract views: 112PDF downloads: 136
Most read articles by the same author(s)
- Roman Kvуetnyy, Yuriy Bunyak, Olga Sofina, Oleksandr Kaduk, Orken Mamyrbayev, Vladyslav Baklaiev, Bakhyt Yeraliyeva, ADVERTISING BIDDING OPTIMIZATION BY TARGETING BASED ON SELF-LEARNING DATABASE , Informatyka, Automatyka, Pomiary w Gospodarce i Ochronie Środowiska: Vol. 13 No. 4 (2023)
- Madina Bazarova, Waldemar Wójcik, Gulnaz Zhomartkyzy, Saule Kumargazhanova, Galina Popova , KNOWLEDGE TRANSFER AS ONE OF THE FACTORS OF INCREASING UNIVERSITY COMPETITIVENESS , Informatyka, Automatyka, Pomiary w Gospodarce i Ochronie Środowiska: Vol. 9 No. 3 (2019)
- Roman Obertyukh, Andrіі Slabkyі, Leonid Polishchuk, Oleksandr Povstianoi, Saule Kumargazhanova, Maxatbek Satymbekov, DYNAMIC AND MATHEMATICAL MODELS OF THE HYDROIMPULSIVE VIBRO-CUTTING DEVICE WITH A PRESSURE PULSE GENERATOR BULT INTO THE RING SPRING , Informatyka, Automatyka, Pomiary w Gospodarce i Ochronie Środowiska: Vol. 12 No. 3 (2022)
- Yosyp Bilynsky, Aleksandr Nikolskyy, Viktor Revenok, Vasyl Pogorilyi, Saule Smailova, Oksana Voloshina, Saule Kumargazhanova, CONVOLUTIONAL NEURAL NETWORKS FOR EARLY COMPUTER DIAGNOSIS OF CHILD DYSPLASIA , Informatyka, Automatyka, Pomiary w Gospodarce i Ochronie Środowiska: Vol. 13 No. 2 (2023)
- Leonid Timchenko, Natalia Kokriatskaia, Volodymyr Tverdomed, Natalia Kalashnik, Iryna Shvarts, Vladyslav Plisenko, Dmytro Zhuk, Saule Kumargazhanova, LOCAL DIFFERENCE THRESHOLD LEARNING IN FILTERING NORMAL WHITE NOISE , Informatyka, Automatyka, Pomiary w Gospodarce i Ochronie Środowiska: Vol. 13 No. 2 (2023)
- Anna Vitiuk, Leonid Polishchuk, Nataliia B. Savina, Oksana O. Adler, Gulzhan Kashaganova, Saule Kumargazhanova, ENGINEERING AND TECHNICAL ASSESSMENT OF THE COMPETITIVENESS OF UKRAINIAN MECHANICAL ENGINEERING ENTERPRISES BASED ON THE APPLICATION OF REGRESSION MODELS , Informatyka, Automatyka, Pomiary w Gospodarce i Ochronie Środowiska: Vol. 13 No. 3 (2023)
- Vira Petruk, Olena Prozor, Yuliia Sabadosh, Iryna Baranovska, Maksim Palii, Yevheniia Moroz, Saule Kumargazhanova, Dinara Mussayeva, STATISTICAL METHODS FOR EVALUATING EXPERIMENTAL DATA ON THE USE OF MATHEMATICAL COMPETENCIES IN STUDY FOR A RESILIENT ECONOMY , Informatyka, Automatyka, Pomiary w Gospodarce i Ochronie Środowiska: Vol. 13 No. 2 (2023)
- Olexandra Litvinenko, Victor Paliy, Olena Vуsotska, Inna Vishtak, Saule Kumargazhanova, POLARIZATION TOMOGRAPHY OF THE POLYCRYSTALINNE STRUCTURE OF HISTOLOGICAL SECTIONS OF HUMAN ORGANS IN DETERMINATION OF THE OLD DAMAGE , Informatyka, Automatyka, Pomiary w Gospodarce i Ochronie Środowiska: Vol. 12 No. 4 (2022)
- Kateryna Barandych, Sergii Vysloukh, Grygoriy Tymchyk, Oleksandr Murashchenko, Saule Smailova, Saule Kumargazhanova, OPTIMIZATION OF PARTS CUTTING PROCESS PARAMETERS WORKING IN CONDITIONS OF CYCLIC LOADS , Informatyka, Automatyka, Pomiary w Gospodarce i Ochronie Środowiska: Vol. 13 No. 3 (2023)
