Face Recognition - Watchlist
Upgrade your video surveillance with Scylla Face Recognition that harnesses the power of computer vision and artificial intelligence for the safety of your premises and people.
Book a demoRelated materials
FAQ
The face recognition watchlist system utilizes two distinct databases. The first is a vector database, which stores non-reversible face vectors - ensuring that the original image cannot be reconstructed from these vectors. The second one is a standard database used to store actual images, though storing images is optional. The system can operate exclusively with the vector database if the client prefers.
Face Recognition accuracy is indeed impaired by partial obscuration. However, in good setup conditions (camera, illumination, proximity, etc.) the system is still capable of accurate face recognition (shown in a number of tests).
Yes, a pilot program can be conducted. Success is measured by the percentage of successful detections under various conditions, aiming for results close to 100%. The evaluation is based on the acceptance criteria for visual recognition detailed in the technical whitepaper.
For Full HD streams, 250 PPM (pixels per meter) is required, which typically corresponds to a detection range of approximately 4 meters. Latency ranges from 3 to 4 seconds, depending on the specific system setup.
Yes, the system is designed to perform efficiently even with significant transformations or changes in appearance. Detailed accuracy metrics for such scenarios are outlined in the technical whitepaper
The training set minimizes detection failures with people of diverse backgrounds. There have been reports of some face recognition models not working well with people of color and women due to imbalanced data sets used for training. Many facial recognition systems are trained on images of white males only. Scylla has deliberately built ethnically and gender balanced datasets in order to eliminate bias in face recognition. Learn more about our ethical approach.
Facial recognition technology can be seamlessly integrated with Scylla Access Control solution and most modern video management systems.
The watchlist solution is designed for the precise identification of pre-enrolled individuals, enabling immediate action when flagged individuals are recognized. Enrollment is manual and carefully curated, making it ideal for real-time recognition in settings such as airports, transportation hubs, law enforcement operations, and event security.
In contrast, the auto-enrollment solution is tailored for high-traffic environments like casinos and retail spaces. It dynamically tracks individuals and generates actionable data to derive behavioral insights. The database is automatically built, eliminating the need for manual input, making it an excellent choice for casinos, retailers, and corporate campuses.