Product Specification

Version Q3-2021

Product Description

Incoresoft VEZHA works in security systems, safe and smart cities with high traffic flow at speeds up to 250 km/hr. It works using neural networks, which automatically give higher recognition accuracy. The minimum width requirement for a European license plate is 60 pixels with a 2MP camera resolution. Furthermore, it scales perfectly with an increase in recognition channels. This is personally developed by the company and offers continuous support, product updates, improvements in recognition accuracy, and quality. It's possible to adapt to any license plate.

License Plate Recognition Features

  • The accuracy of License plate recognition goes up to 98%
  • Our LPR solution doesn’t have any limitations with lane quantity.
  • ALPR consists of unlimited lists quantity with different rules
  • The plates number can be recognized irrespective of dirty, blurred, unfocused, dark, or light our system can still recognize the plate numbers
  • Simple integration without any special settings
  • Make, model, color, and direction recognition
  • Intelligent analysis of columns and the ability to track vehicles
  • Multi-line license plate recognition support

Camera Compatibility

The solution is compatible with all cameras, that return the RTSP stream.

A common choice for effective license plate recognition: AXIS P1455-LE.

Camera Installation Requirements

  • Camera installation height requirements: recommended - 3 m or 5 m (Minimum - 1.5 m; Maximum - 10 m)
  • License plate image of moving vehicle should have no high-speed "blurring" effect visible to the eye
  • Symbols of license plate number must be applied in font and size in full accordance with the standard adopted in the country that issued this number
  • License plate numbers must meet the requirements for cleanliness and legibility: all symbols must be clearly visible and not obstructed by anything
  • License plate images should be of sufficient contrast; the difference in contrast between characters of the number and background must be visible by eye
  • The size of a single-line number on the image must be at least 100 * 20 (width * height) pixels on FullHD

Sensor Resolution Requirements for Cameras

  • 1 lane (~ 4 m) - 1 MP (HD, 720p)
  • 2 lanes (~ 8 m) - 2 MP (Full HD, 1080p)
  • 3 lanes (~ 12 m) - 5MP

Requirements for a Video Stream



Minimum frame rate


Frame rate


Support for various video formats: AVI, .MKV, .MPEG4, .MOV, .WMV, .DVR, .ASF, .RT4, .DIVX, .264, .GE5, .TS, .3GP, .XBA (single & multi-stream), .MP4, .FLV+

h.263 codec support


h.264 codec support


h.265 codec support


Technical Specifications

Cross-platform solution


Centralized management


The ability to work with different versions of video data sources


Capture and license plate recognition for 8-30 m/s


Finding and navigating the vehicle route


Definition of one- and two-line, ordinary, inverse, and special

types of license plates


Real-time video analytics and alarm settings


Ability to process statistics and generate reports

(Microsoft Power BI, Google Data Studio, and others)


License plate recognition module


Working with lists


Filter license plates by country


The ability to receive reports by the hour, day, week, or month


Notification settings: sending to the system, by Email / Telegram / SMS


API integration


Database import (CSV) and export support (EXCEL / PDF / СSV / JSON)


100+ countries license plate support


Minimum Software Requirements

Operating System - Ubuntu 18.04 or Windows 7 / Windows Server 2008 R2

Databases - MySQL 5.5 and newer, PostgreSQL 9.3 and newer, Oracle Express Edition 10g and newer, SQL Server Express Edition 2008 and newer

Minimum Hardware Requirements


Intel Core i5-8250U @ 1.60GHz and with higher performance




20 GB / day


Any from the list below or higher with better performance:

GTX 1660 6GB or

RTX 2060 SUPER 8GB or

RTX 2070 SUPER 8GB or

RTX 2080TI 11GB or

RTX 3070 8GB or

RTX 3080 10GB or

RTX 3090 24GB


5 Mb/s per 1 video analytic or higher (- for example, if the network connection is 100 Mb/s, not more than 20 analytics may work properly at the same time (5 Mb/s * 20 = 100 Mb/s)

Response time (local network)

200 ms or faster

Security Features

Restrict access to a specific group of users


Storing passwords of internal users of the system as a hash function


Encryption of information within the system with dynamic keys that change each time the module is started


Integration with a single search base of the vehicle "Harpoon"


The presence of a system of building business logic


Support for NVIDIA CUDA technology


Integration with various VMS - Milestone XProtect, Nx Meta, Luxriot Evo


Availability of plug-ins - Milestone XProtect, Nx Witness


Personal data protection

98 %

Vehicle recognition factor

up to 30°

Support for various interface languages



1080 px or higher

The size of the license plate in width

minimum: 60px, recommended 100 and above

Number plate rotation

up to 25°

The maximum number of license plates that can be recognized in one frame

Not limited

Camera position

up to 30º, horizontal or vertical

Adjusting the filter accuracy


Filter objects according to an arbitrary route


Background change filter


Creation of statistics based on the analyzed data


Combination with analyzed data from third-party sources (ERP)


Ability to store the database on a dedicated server


Alarms and Events

Alarms based on comparison with the list


Alarms with sending events to other resources


Alarms for scheduled vehicle detection


Alarms based on object classification: vehicle


Alarms based on meters


Open tools for integration and development


Integration with third-party resources - JSON messages via HTTP, MQ, TCP


Software Licenses

The license model works per channel (on-premise or perpetual).





Incoresoft VEZHA LPR


Plate Image Characteristics

  • Image quality must be at least average
  • There should be no significant compression artifacts
  • Image resolution should be HD or FullHD format or higher with an aspect ratio equals 16:9