Faceter is a system that makes video surveillance smart by providing computer vision, facial recognition, object detection, and video content analysis to cameras in real time. In the next phase, all these capabilities will be merged into one – to "understand" the current situation and then react to it. The team calls this concept the "event security model."

Project Vision

After Faceter is adopted by the market, it can be used to maintain whitelists in various services; for example, on a website, employees are hired to do some housework. In addition to comments, the Faceter system can also store links to blockchain records containing biometric data. The same approach could be used to store records of store visitors and check the integrity of buyers, sellers or couriers.
If all cameras connected to Faceter are integrated with police and rescue service databases, information about wanted criminals, missing children or people in difficulty can be sent immediately through the system to their relatives and places of residence. In such emergencies, the police and special services will also be able to access the system in order to discover "pictures" of people in the video archives of Faceter users, without revealing confidential information, as the system will only use the data from the camera owners Agree.

Project Features

1. Object and facial recognition and the resulting behavioral analysis have greatly enhanced the ability of video surveillance systems to detect potential customers and specific employees. The technology's algorithms have been proven by LFW and MegaFace tests, they are the most trustworthy in the industry.
2. A convenient application for any computer or mobile device allows users to access the video surveillance system from anywhere without having to master complex and slow interfaces.
3. Fog Computing - By enabling miners of cryptocurrencies to enter a decentralized computing network to perform identification calculations, it provides miners with higher income-generating opportunities, thereby greatly reducing the cost of the product.
4. Blockchain-Faceter uses all opportunities of smart contracts to provide flexible and transparent payment options and identification mechanisms for the fog computing network. This is Faceter's contribution to the development of the encryption industry.
5. Machine Learning - Using Neural Networks, you can teach Faceter to react to changes in certain events.
6. Data Protection - Faceter does not expose source video streams outside of a trusted environment; only anonymized data can be transferred to the decentralized network.
7.Faceter token is the "fuel" of the decentralized network, providing a flexible, transparent, cross-border settlement mechanism for all participants.

Application field

B2C
Software designed for home use in apartments, offices, country houses, as well as in home shops and restaurants. The payment method is based on a monthly or annual subscription, the maintenance rate depends on the number of cameras used and the workload (number of recognized faces per unit of time). Faceter's solution for individual users:
– Increased level of security;
– Affordability;
– Wide applicability (combination with smart home technology).
B2B
The software can be used in factories, warehouses, large corporations, hotels, casinos, shopping centers, banks and restaurant chains, thanks to the cooperation with home, office and industrial equipment suppliers Signed technical cooperation agreement, as well as smart device sensor and other component manufacturer management system.
B2G
Municipal software can be used to analyze video streams on streets and roads, as well as in crowded places such as stations and airports. It can also be combined with database monitoring.
Faceter hypothetically recognizes a perpetrator's face and runs it through a database of archival records to reveal where the person has recently visited. The solution can automatically control compliance with norms and regulations in transportation and public places, which will increase the speed of solving crimes and ensure a higher level of automatic police control.

Technical Overview

1. Data processing
The Faceter software complex is designed in the form of a set of modules, each of which executes at a different system level and is responsible for various phases of platform operation, The language for ML component development is C++11. Also, GPU acceleration is actively used.
Stages of Facial Recognition Processing
Receive and process decoded video stream from camera;
Face detection (if camera is not equipped with built-in face detection technology);
Facial frames for better recognition;
>Using a deep convolutional neural network to obtain feature vectors for each person;
vector clustering, comparison of feature vectors with available databases and their location in the storage system;
result output via API.
2.Faceter Distributed Network
Due to the rapid growth of decentralized services, including blockchain-based businesses, Faceter plans to attract individual owners of GPU resources and use affordable Solutions to build your own computing network, such as SONM or Golem, instead of expensive cloud services. So there is no need to use expensive monopoly services like Amazon, Microsoft, Google etc.
The use of miner resources or other idle computing power is very beneficial to both the owners of these resources and consumers. Even a cursory comparison of the cost of renting a GPU server on Amazon Web Services versus calculating the amount of compensation paid to miners for a mining farm shows huge differences. In addition, the complexity of the network is adjusted every few months to reduce miner rewards, and with the new consensus mechanism, GPU computing is not required at all.
The main participants in the Faceter network are the owners of GPU resources (nodes). A smart contract will be displayed at the end of each node. This contract will be used to provide compensation for computing power.
Decentralized environments require special verification of the trustworthiness of connecting nodes. To ensure the quality of the computations performed, less productive nodes will verify the performance of other nodes and perform computations repeatedly. High performing nodes should be fully loaded with tasks, while less powerful nodes will be given shards of the same tasks.
Calculations will be compared via smart contracts, and if participants have enough confirmations, each of them will receive their part of the reward from the formed balance.
If the validating node receives a different computed hash, this will confirm the dishonesty of the miner and will cause them to disconnect between new computers and redistribute the accumulated rewards. Faceter calls the concept "validation recognition."
The distribution of work performance and validation of tasks will be through special coordinator nodes (video hubs) that also act as video hubs and obfuscators for sensitive data. These nodes will be in a trusted zone, not using worthless non-personal data like all other nodes.
3. Personal data protection
The users of the video surveillance system are usually those who connect the camera to the cloud platform. There are dozens (sometimes millions) of companies on the market that provide such cloud application services: Ivideon, Camcloud, XMEye, vMEyeSuper, etc.
All of these services offer CCTV cameras, but in practice none of them have developed clear policies for handling user data; often, there are no means in place to control access to the data.
Faceter's modular architecture allows users to work with raw video streams in a trusted environment: on the camera owner's device, on Faceter's servers, or in the camera itself, with only obfuscation (non- Personal) data is used to perform tasks on a decentralized network. In other words, the data cannot be converted to the original format with reference to the owner.
4. Faceter Token Usage Model
The effective operation of a decentralized network requires flexible, transparent and cross-border settlement mechanisms for all participants. Traditional methods of using fiat currencies are not feasible in this particular case because they do not fully meet any of the above requirements.
This means that every potential network participant must pass extended KYC checks, open their own bank to open a foreign exchange account, and execute international transactions to comply with all requirements of local laws, which makes it possible to create a large-scale decentralized Computing infrastructure is next to impossible.
The solution to this problem is Faceter's own token as the basis for payment between consumers of smart video surveillance services and network participants. The integration plan for introducing the Faceter platform into the blockchain technology is implemented in the following stages:
Phase 1: Issue tokens on Ethereum for free sale and internal economic use of the project, and to node owners (“miners ”) to pay remuneration.
Phase 2: Development and launch of blockchain and possible token migration. This step should solve the problem of distributed task allocation, improve the operating speed of the system, ensure the independence of the Ethereum blockchain, and reduce transaction costs in the platform.
System function model
Faceter's services can be paid with tokens or other payment tools (bank cards, electronic wallets, cryptocurrencies). To guarantee the proper functioning of the latter, Faceter will implement an instantaneous conversion mechanism for payment tokens. Camera maintenance costs are set by Faceter in USD and can be revised quarterly.

Related links:
https://www.qukuaiwang.com.cn/news/6777.html

*The above content is organized by YouToCoin official. If reprinted, please indicate the source.