REVISOR is a neural network-based software package that uses computer vision technology to monitor electoral procedures and count the number of actual voters. This software can be deployed during election observation missions for a fraction of the cost of traditional methods. The Revisor system tracks physical objects, detects voting events, and distinguishes them from other activities at a polling station with high precision (up to 98% accuracy). It is also a trainable neural network, which means that customers can teach it to work with different types of voting procedures, elections, and electoral systems in any country. The system can detect multiple types of violations and speed up manual recounts. The software can be applied to operations based on video recordings, producing results immediately after an election and/or months and years later. Revisor is a fast, reliable, and inexpensive system that is designed to detect ballot boxes on video records, count the number of voters who cast their ballots, identify polling stations with falsified turnout, draft a formal complaint, and speed up manual recounts. Results from Revisor are evidenced in the success stories where it has detected discrepancies between the official and actual turnout at polling stations, reporting them to users who can resolve crimes that lead to the observed anomaly. Overall, Revisor is an effective AI tool that leverages neural networks for election monitoring and compliance with electoral procedures.
Pros And Cons Of Revisor
Pros
High precision tracking
98% accuracy
Trainable neural network
Customizable to different procedures
Detects multiple violation types
Speeds up manual recounts
Applicable to video operations
Immediate and long-term results
Fast
reliable
inexpensive
Detects ballot boxes on video
Counts actual voter turnout
Identifies falsified polling stations
Drafts formal complaints
Works in any country
No scale limits
Processing of million hours videos
Discrepancy detection between official/actual turnout
Can work with different electoral systems
Results in success stories
Observation mission deployment
Cost fraction of traditional methods
Poll watcher replacement
Cons
Requires video recordings
Accuracy depends on camera setup
Can't detect all violation types
Doesn't auto-resolve detected discrepancies
Possible false positives/negatives
Expensive storage for video data
Need to manually train system
Depends on quality of video
May miss subtle violations
Requires high computational power
Pricing Of Revisor
FQA From Revisor
What is Revisor?
Revisor is a neural network-based software package that uses computer vision technology to monitor electoral procedures and count the number of actual voters. It's a fast, reliable, and inexpensive system that can detect violations, speed up manual recounts and even generate a formal complaint.
How does Revisor work?
Revisor works using a trainable neural network that recognizes physical objects, tracks their relative movements and distinguishes voting events from other activities at a polling station. It can independently count the number of voters with high precision when it's deployed in election observation missions.
What can Revisor do?
Revisor can detect ballot boxes on video recordings, count the number of voters who cast their ballots, identify polling stations with falsified turnout, draft a formal complaint, and also speed up manual recounts.
What key features does Revisor have?
Revisor's key features include the ability to detect and outline ballot boxes on video records, accurately count the number of voters, identify falsified turnouts at polling stations, detect different types of violations and draft a formal complaint. It can also speed up manual recounts.
How does Revisor detect electoral procedure violations?
Revisor detects electoral procedure violations by utilizing neural networks to recognize physical objects and identify voting events at polling stations. It detects discrepancies between the official and actual turnout at polling stations and reports these anomalies.
Can Revisor be used in any country?
Yes, Revisor can be used in any country. The system is trainable, meaning customers can teach it to work with different types of voting procedures, elections, and electoral systems.
How reliable is Revisor in detecting electoral violations?
Revisor is highly reliable in detecting electoral violations. It has reported anomalies and discrepancies with up to 98% accuracy, depending on the relative positions of cameras and ballot boxes in a polling station.
Can Revisor be trained to work with different types of voting procedures?
Yes, Revisor can be trained to work with different types of voting procedures. The system is a trainable neural network and customers can customize it to suit various election procedures and systems.
What types of elections can Revisor be used for?
Revisor can be used for various types of elections as it's a versatile system that can adapt to a wide range of voting procedures, elections, and electoral systems.
Does Revisor also speed up manual recounts?
Yes, Revisor can help in speeding up manual recounts. It's designed to function effectively in conduct recount processes swiftly.
What technology does Revisor use to monitor electoral procedures?
Revisor uses a combination of neural network and computer vision technology to monitor electoral procedures. It uses these technologies for tracking physical objects, detecting voting events, distinguishing them from other activities at polling stations and detecting violations.
Does Revisor identify polling stations with falsified turnout?
Yes, Revisor can identify polling stations with falsified turnout by comparing the actual voter turnout observed in the video records to the officially published results.
How accurate is Revisor?
Revisor has an accuracy rate of up to 98%, depending on the relative positions of cameras and ballot boxes in a polling station.
Can Revisor results be applied to video records after an election?
Yes, Revisor's results can be applied to video records even months and years after an election. The software functions based on video recordings, thereby allowing for retroactive examination and assessment of election data.
What are Revisor's system development stages?
The Revisor system underwent several development stages: December 2019 – July 2020 the Prototype stage. August 2020 – September 2021 the System Finalization stage. The current time is the multiple voting detection module stage.
What is the cost of using Revisor?
The price for using Revisor isn't indicated on their website. However, it's mentioned that Revisor is an inexpensive solution and offers its services for a fraction of the cost of traditional methods.
Can Revisor detect multiple types of electoral violations?
Yes, Revisor can detect multiple types of electoral violations. It has the ability to recognize physical objects, track their movements and distinguish voting events, which allows for a varied range of violation detection.
How long does it take for Revisor to process election data?
The duration taken to process election data with Revisor isn't specifically stated on their website, it is stated that immediate results can be obtained after an election from the software.
How does Revisor help in drafting a formal complaint?
Revisor assists in drafting a formal complaint by identifying polling stations with falsified turnout by comparing the real turnout to the officially published results. The precise details of this complaint drafting process aren't specified on their website.
Are there any successful stories where Revisor has been used?
Yes, there are success stories about Revisor, such as processing more than 1 million hours of video records from Duma elections held in 2021. It revealed 30% of falsified votes in the provided sample, leading journalists to conclusions about the whole country.
