FindFace

FindFace is a face recognition technology developed by the Russian company NtechLab that specializes in neural network tools. The company provides a line of services for the state and various business sectors based on FindFace algorithm. Previously, the technology was used as a web service that helped to find people on the VK social network using their photos.

FindFace
Type of site
Social networking service
Available inRussian, English
OwnerNtech Lab Ltd
Created byArtem Kukharenko, Alexander Kabakov, Maxim Perlin
URLfindface.pro
RegistrationOptional
Launched2016 (2016)
Current statusactive

Technology

In 2015 NTechLab algorithm won The MegaFace Benchmark challenge, organized by University of Washington.[1]

In May 2016, NtechLab was admitted to the official testing of biometrics technology by NIST among the three Russian companies. According to the results of testing, the algorithm took the first position in the ranking of the global benchmark Facial Recognition Vendor Test.[2]

In the spring of 2017, NtechLabs algorithm again has been ranked first in the Facial Recognition Vendor Test.[3]

Also in March 2017, NtechLabs FindFace algorithm won in the EmotionNet Challenge automatic emotion recognition competition organized by Ohio State University.[4] 37 development teams took part in the competition, and only 2 of them were able to fulfill the conditions in full.

In the fall of 2017, NtechLab won the facial recognition technology competition organized jointly by NIST and IARPA, in two nominations out of three (“Identification Speed” and “Verification Accuracy”).[5]

In September 2018, the NtechLab algorithm for recognizing pedestrian silhouettes won a prize in the Wider Pedestrian Challenge, a competition for detecting pedestrians and cyclists organized by Amazon and SenseTime.[6]

FindFace employs a facial recognition neural network[7] algorithm developed by N-Tech.Lab[8][9] to match faces in the photographs uploaded by its users against faces in photographs published on VK,[10] with a reported accuracy of 70 percent.[11] Different sources pointing NTech Lab's technology accuracy from 85.081%[12] to 99%[13]

History

The technology was made public as a web service that helps to find people on the social network VK using their photos in February of 2016.[14]

In May 2016, the number of visitors to the service exceeded 1 million people.[15]

In August 2016 NtechLab co-founder Artyom Kukharenko, handed over the post of head of the company to Mikhail Ivanov.[16]

On September 2018, the service stopped providing a facility to search people's social profiles, as it was transformed by NtechLab into a line of services for various business sectors .

Application cases

In 2016–2018 NtechLab presented several scenarios for using FindFace technology, which later formed the basis of the company's commercial products:

• In June 2016, the FindFace service was introduced at the Alfa Future People festival: guests of the event could identify themselves with the use of an application, and then obtain the possibility to receive their photos, taken during the event, through their social network profiles. Participation in the experiment was voluntary and did not violate the confidentiality of festival visitors.[17]

• In 2017, NtechLab face recognition algorithms were built into the Moscow city video surveillance system operated by the Moscow Department of Information Technology . The system uses the database of the Ministry of Internal Affairs to find correspondences to it on video. The alleged use of the system is the search for criminals and the fight against terrorism.[18]

• In February 2018, it became known that NtechLab technologies will be used in Tatarstan. As it was announced in early 2019, a pilot project in Almetyevsk showed the effectiveness of technology in ensuring public safety.[19]

• In April 2018, it has been announced that the NtechLab face recognition algorithm will be implemented in the large Leto shopping and entertainment complex in St.Petersburg. The Leto authorities will collect a non-personal information on visitors without identifying them. The analysis will help to determine the demographic composition of customers, identify repeated visits, estimate the amount of time spent by visitors on purchases, compare customer behavior in different stores .

• In July 2018, the NtechLab application has been implemented in the water amusement park Līvu Akvaparks in Jurmala. After visiting the park, his clients were able to simplify the search for all the photographs containing their image .

• The FindFace Security application, implemented in several cities during the FIFA 2018 World Cup in Russia, made it possible to detain more than 180 people included in the offenders' bases, some of whom were on the federal wanted list .

• Thanks to the FindFace Security application, it was possible to prevent the theft of the Bud sponsorship cup as part of one of the matches of the FIFA World Cup 2018 in Russia. With the help of video cameras, it was possible to restore the chain of events and identify those involved, one of whom was discovered and detained at one of the subsequent matches.[20]

Developers

The NtechLab company that created the service was founded in 2015 by a graduate of the Moscow State University Faculty of Computational Mathematics and Cybernetics Artyom Kukharenko and businessman Alexander Kabakov.

Controversial use

In 2016, FindFace generated controversy because it was once used to deanonymize Russian pornography actresses and alleged prostitutes.[7][21] These efforts were organized by users of a Russian imageboard Dvach who claimed that women in the sex industry are “corrupt and deceptive”, according to Global Voices.[22] In addition, FindFace has been characterized as a major step in the erosion of anonymity.[8][23]

References

  1. BiometricUpdate.com. Russian startup tops UW facial recognition challenge. Dec 17, 2015.
  2. Lenta.ru Алгоритм NtechLab занял первое место в рейтинге Минторга США. 29.05.2017
  3. HighTech FM. В США российский алгоритм распознавания лиц признали самым точным. Ильдар Нигматуллин. 31 мая 2017
  4. Emotion Challenge Results
  5. Russia No. 1 In Facial Recognition, According To Official Washington Spycraft Techies. Kenneth Rapoza. Nov 28, 2017. Forbes.
  6. Wider Pedestrian Challenge official site.
  7. Chiel, Ethan (2016-04-29). "This Face Recognition Company Is Causing Havoc in Russia—and Could Come to the U.S. Soon". Fusion. Retrieved 2016-07-05.
  8. Frankle, Jonathan (2016-05-23). "How Russia's New Facial Recognition App Could End Anonymity". The Atlantic. Retrieved 2016-07-05.
  9. Findface.ru. "FindFace.ru - сервис знакомств по фотографии". FindFace. Retrieved 2016-07-05.
  10. Walker, Shaun (2016-05-17). "Face recognition app taking Russia by storm may bring end to public anonymity". The Guardian. Retrieved 2016-07-05.
  11. Guarino, Ben (2016-05-18). "Russia's new FindFace app identifies strangers in a crowd with 70 percent accuracy". Washington Post. Retrieved 2016-07-05.
  12. Megaface FaceScrub Results
  13. "Picking Out One from a Billion: the Face Recognition System From NTechlab". Intel Tech Innovation. 2016-09-27.
  14. Russia’s new FindFace app identifies strangers in a crowd with 70 percent accuracy. Ben Guarino. May 18, 2016. The Washington Post
  15. Аудитория сервиса FindFace превысила миллион человек. May 17 2016. Lenta.ru
  16. 20 молодых и перспективных: герои завтрашнего дня. May 25 2017 RBC.
  17. Российский стартап FindFace продаст «Билайну» для фестиваля Alfa Future People услуги по распознаванию лиц посетителей. Andrey Frolov. 29 Jun 2016 VC.RU
  18. Devin Coldewey. Moscow officially turns on facial recognition for its city wide camera network. Techcrunch
  19. Система распознавания лиц в Альметьевске обнаружила шестерых разыскиваемых. Полина Петрова, "Ъ-Казань".
  20. «Дочка» «Ростеха» не дала украсть в России кубок чемпионата мира по футболу. CNEWS. 26 Jul 2018
  21. Cuthbertson, Anthony (2016-04-29). "Porn stars and sex workers targeted with facial recognition app". Newsweek. Retrieved 2016-07-05.
  22. Rothrock, Kevin (2016-04-22). "Facial Recognition Service Becomes a Weapon Against Russian Porn Actresses". Global Voices Advocacy. Retrieved 2016-07-05.
  23. Burgett, Gannon (2016-05-18). "FindFace is a new facial recognition app that could end public privacy". Digital Trends. Retrieved 2016-07-05.
This article is issued from Wikipedia. The text is licensed under Creative Commons - Attribution - Sharealike. Additional terms may apply for the media files.