Skip to main content

Kapsch upgrades North America ANPR engine

It will ID licence plates from 58 jurisdictions in US, Mexico and Canada
By Adam Hill February 27, 2025 Read time: 2 mins
Over 150 plate types can now be accurately identified (© Swisshippo | Dreamstime.com)

Kapsch TrafficCom has upgraded its automatic number plate recognition (ANPR) engine for the US and Canada as part of its tolling offering, with deployment in several projects underway.

The company introduced regional ANPR engines in Europe and Australia in 2023.

“A newly-developed deep neural network - specifically for North America - ensures precise identification of licence plates from 58 jurisdictions, including all mainland US states, Hawaii, Mexico, and the most relevant Canadian provinces,” explains Chris Jones, director of video transaction optimisation at Kapsch TrafficCom North America. 

Unlike traditional project-specific engines, the new product "is designed to serve multiple projects across the region, offering unparalleled accuracy and reliability".

JB Kendrick, president at Kapsch TrafficCom North America, adds: “Our newest and most robust engine can accurately identify over 150 plate types, focusing on the most widely used designs and ensuring easy scalability to include additional types as needed."

It will reduce manual review costs by improving the percentage of plates read automatically and represents "a key building block for our existing and future roadside tolling clients", Kendrick says.

The company says North America presents "unique challenges" for ANPR systems because of the sheer variety of licence plate designs, syntaxes and allowed characters. The new ANPR engine has been "meticulously trained" to handle this complexity, the manufacturer insists.

For more information on companies in this article

Related Content

  • Vision Components’ ANPR library identifies damaged plates
    October 29, 2014
    Vision Components’ Carrida software engine is a powerful OEM Library, which is easy to integrate into existing security and surveillance applications, including access control, toll control and traffic analysis. The high-performance, hardware-independent software tool assures reliable high speed recognition of vehicle number plates. With a typical processing time of 30ms and a recognition accuracy of more than 96%, the ALPR/ ANPR library precisely and reliably identifies number plates, even if dirty, dam
  • On-road and in-vehicle are not in competition
    May 18, 2018
    The integrity and accuracy of data that can be verified by weigh-in-motion technology has been improving for decades – and the range of WIM applications is increasing at a tremendous pace. Chris Koniditsiotis, president of the International Society for Weigh-in-Motion (ISWIM) and CEO of Transport Certification Australia (TCA), began his career in 1985 as a pavements engineer. “When I joined this portfolio, the integrity, accuracy, and sampling frequency of mass information delivered at best an estimate, us
  • Kapsch prioritises bus transport in Vitoria
    June 12, 2025
    Traffic signal prioritisation is at key intersection in the Spanish city
  • Camera technology a flexible and cost-effective option
    June 7, 2012
    Perceptions of machine vision being an expensive solution are being challenged by developments in both core technologies and ancillaries. Here, Jason Barnes and David Crawford look at the latest developments in the sector. A notable aspect of machine vision is the flexibility it offers in terms of how and how much data is passed around a network. With smart cameras, processing capabilities at the front end mean that only that which is valid need be communicated back to a central processor of any descripti