Draft:Vladimir Arlazarov (computer vision)

  1. Home
  2. Wiki
  • Comment: Entirely unreferenced, apart from the 'Selected publications' section which cites the subject's own works. Where is all this information coming from? DoubleGrazing (talk) 06:10, 15 April 2025 (UTC)



Vladimir Viktorovich Arlazarov (Russian: Владимир Викторович Арлазаров, born September 24, 1976, Moscow) is a Russian scientist and entrepreneur, Dr. of Engineering, Associate Professor. He is the founder and CEO of Smart Engines (Russian developer of artificial intelligence technologies). Specialist in the fields of pattern recognition, artificial intelligence, computer vision and computational tomography. He is the grandson of Vladimir Lvovich Arlazarov, a Soviet and Russian scientist and creator of the Kaissa chess program[1].

Biography

[edit]

Vladimir Arlazarov was born on September 24, 1976 in Moscow. His grandfather is Vladimir Lvovich Arlazarov, Soviet and Russian scientist in the field of system programming, game theory, artificial intelligence, database management systems and information technology, corresponding member of the Russian Academy of Sciences, creator of the chess program "Kaissa".

In 1993 he entered the National University of Science and Technology (MISiS), Faculty of Informatics and Economics, Department of Engineering Cybernetics, specializing in applied mathematics[2]. In 1999 he graduated from MISiS with the qualification of mathematician-engineer. In the same year he entered the postgraduate program, which he completed in 2003. From 1998 to 2015 worked at Cognitive Technologies.

In 2005, he defended his PhD thesis at MISiS on "Structuring visual representations of the information environment and methods for determining the reliability of recognition". In 2023, he defended his doctoral dissertation on "Mobile recognition and its application to the system of input of identification documents" with the title of Doctor of Engineering.

In 2016, he founded Smart Engines, a research and production company engaged in the development and implementation of high-precision recognition systems[3].

Research work

[edit]

Since 1998, Arlazarov has been working in the system of the Russian Academy of Sciences[4]. From 1998 to 2017 in ISA RAS, since 2017 in Federal Research Center Informatics and Management of the Russian Academy of Sciences. From 2018 to 2023 he worked at The Institute for Information Transmission Problems of RAS as a leading researcher at the Laboratory of Visual Systems[5].

In 2023, he defended his doctoral dissertation on mobile recognition and its application to an ID input system. The new universal system proposed by Arlazarov allowed to effectively highlight a document on a complex background, search for a pattern and map the document to a template, highlight and recognize individual fields of the document, and perform authentication.

From 2007 to 2023 he taught at Moscow Institute of Physics and Technology at the Department of Cognitive Technologies, in 2023 he was awarded the title of associate professor[6].

He developed a methodology for creating realistic sets of photo and video images of secure identification documents, allowing to create high-quality training and test samples. On its basis, he created and published the MIDV (Mobile Identity Document Video) series of data packages: MIDV-500, MIDV-2019, MIDV-LAIT, MIDV-2020, DLC-2021 and MIDV-Holo[7][8][9];

Arlazarov proposed a novel 4.6-bit quantization scheme for fast and accurate neural network Inference on CPUs[10].

Vladimir Arlazarov is general co-chair of the International Conference on Machine Vision (ICMV)[11].

Author of 145 printed scientific papers, 99 of which are indexed by Scopus[12] and Web of Science[13], as well as 54 received patents and patent applications[14], 8 US patents[15].

Selected publications

[edit]

Vladimir Arlazarov's scientific results relate to the following areas:

  • methods for accelerating and improving the quality of image recognition on mobile and edge computing devices, including deep learning methods[16][17][18];
  • processing and recognition methods for high-performance universal document recognition systems[19][20];
  • intelligent computational tomography methods[21][22][23].

References

[edit]
  1. ^ "The chess games of Kaissa (Computer)". www.chessgames.com. Retrieved 2025-04-18.
  2. ^ "Арлазаров Владимир Викторович | ComNews "Кто есть кто"". whoiswho.comnews.ru. Retrieved 2025-04-18.
  3. ^ "The Computer Vision Company". Smart Engines. Retrieved 2025-04-18.
  4. ^ "Vladimir V. Arlazarov". scholar.google.ru. Retrieved 2025-04-18.
  5. ^ "About the IITP RAS". iitp.ru. Retrieved 2025-04-18.
  6. ^ Wealqa. "Арлазаров Владимир Викторович: преподаватель в МФТИ". vuzopedia.ru. Retrieved 2025-04-18.
  7. ^ "MIDV-2020". l3i-share.univ-lr.fr. Retrieved 2025-04-18.
  8. ^ "Papers with Code - MIDV-500: A Dataset for Identity Documents Analysis and Recognition on Mobile Devices in Video Stream". paperswithcode.com. Retrieved 2025-04-18.
  9. ^ "Papers with Code - MIDV-2019: Challenges of the modern mobile-based document OCR". paperswithcode.com. Retrieved 2025-04-18.
  10. ^ Gonzalez, Bianca (2024-04-26). "Smart Engines says new method boosts neural network efficiency by 40% | Biometric Update". www.biometricupdate.com. Retrieved 2025-04-18.
  11. ^ "ICMV 2025". icmv.org. Retrieved 2025-04-18.
  12. ^ "Vladimir Victorovich Arlazarov on Scopus".
  13. ^ "Vladimir Viktorovich Arlazarov on WoS". Web of Science.
  14. ^ "Google Patents". patents.google.com. Retrieved 2025-04-18.
  15. ^ "Vladimir Viktorovich ARLAZAROV Inventions, Patents and Patent Applications - Justia Patents Search". patents.justia.com. Retrieved 2025-04-18.
  16. ^ A. V. Trusov, E. E. Limonova, D. P. Nikolaev, V. V. Arlazarov. On Fast Computing of Neural Networks Using Central Processing Units (англ.) // Pattern Recognition and Image Analysis. — 2023-12. — Vol. 33, iss. 4. — P. 756–768. — ISSN 1054-6618. — doi:10.1134/S105466182304048X.
  17. ^ Anton Trusov, Elena Limonova, Dmitry Nikolaev, Vladimir V. Arlazarov. 4.6-Bit Quantization for Fast and Accurate Neural Network Inference on CPUs (англ.) // Mathematics. — 2024-02-23. — Vol. 12, iss. 5. — P. 651. — ISSN 2227-7390. — doi:10.3390/math12050651.
  18. ^ Artem Sher, Anton Trusov, Elena Limonova, Dmitry Nikolaev, Vladimir V. Arlazarov. Neuron-by-Neuron Quantization for Efficient Low-Bit QNN Training // Mathematics. — 2023-04-29. — Vol. 11, iss. 9. — P. 2112. — ISSN 2227-7390. — doi:10.3390/math11092112.
  19. ^ Konstantin Bulatov, Nikita Razumnyi, Vladimir V. Arlazarov. On optimal stopping strategies for text recognition in a video stream as an application of a monotone sequential decision model // International Journal on Document Analysis and Recognition (IJDAR). — 2019-09. — Vol. 22, iss. 3. — P. 303–314. — ISSN 1433-2833. — doi:10.1007/s10032-019-00333-0.
  20. ^ Alexander Gayer, Daria Ershova, Vladimir V. Arlazarov. An accurate approach to real-time machine-readable zone detection with mobile devices // International Journal on Document Analysis and Recognition (IJDAR). — 2023-09. — Vol. 26, iss. 3. — P. 321–334. — ISSN 1433-2833. — doi:10.1007/s10032-023-00435-w.
  21. ^ Marat Gilmanov, Konstantin Bulatov, Oleg Bugai, Anastasia Ingacheva, Marina Chukalina, Dmitrii Nikolaev, Vladimir Arlazarov. Applicability and potential of monitored reconstruction in computed tomography // PLOS ONE / Don S. — 2024-07-22. — Vol. 19, iss. 7. — P. e0307231. — ISSN 1932-6203. — doi:10.1371/journal.pone.0307231.
  22. ^ Konstantin B. Bulatov, Anastasia S. Ingacheva, Marat I. Gilmanov, Marina V. Chukalina, Dmitry P. Nikolaev, Vladimir V. Arlazarov. Reducing radiation dose for NN-based COVID-19 detection in helical chest CT using real-time monitored reconstruction // Expert Systems with Applications. — 2023-11. — Vol. 229. — P. 120425. — doi:10.1016/j.eswa.2023.120425.
  23. ^ "Scientists Have Found a Way to Stop AI and Patented Their Technology in the USA". Aithority.com. 23 November 2023.