Smart Engines and GK Intek have introduced a family of Russian software-hardware scanner complexes designed for fast, secure document input and fraud detection. The devices handle passports, driver licences and other identity documents from Russia, CIS states and 235 additional jurisdictions.
The scanners perform automatic data capture and multi-spectral authenticity verification in a single pass. They examine documents under visible, ultraviolet and infrared illumination, analyse holograms and other security features, and read RFID chips when present. All processing occurs locally, eliminating the need to transmit images or personal data to external services.
Banks have already integrated the complexes to strengthen KYC and anti-fraud controls. At Genbank the solution reduced passport data entry to fractions of a second with 99.9 % accuracy. Severgazbank deployed the system to detect forged documents from Russia and 235 other countries, reporting a measurable drop in attempted fraud after integration in 2022.
At major airports the same technology operates inside the Sapsan border-control system. Modules equipped with the Sherlock neural ensemble now process passengers at Sheremetyevo, Vnukovo and Koltsovo, extracting data from Russian foreign passports, checking more than 600 authenticity features and identifying sophisticated fakes including deepfakes. After ten modules were installed at Sheremetyevo, average border-crossing time fell to 40 seconds and throughput increased six-fold.
Additional deployments cover automatic pass kiosks at seaports and river ports, electronic-signature issuance windows at Federal Tax Service offices, and the first pharmacy robot in Minsk that verifies customer age before dispensing restricted medicines. The scanners also support domestic hardware platforms including Komdiv, Elbrus and Baikal processors together with Russian operating systems.
Two U.S. patents further strengthen the offering: one detects hidden digital edits by analysing an image’s digital “handwriting” rather than its visual content; the second identifies optically variable devices from visible-light images taken under varying illumination angles, exposing copies and replicas.
