You are using an outdated browser. Please upgrade your browser to improve your experience.
Enter your details to request a FREE site security survey.
Automatic Number Plate Recognition (ANPR) is achieved through video cameras capturing images that are analysed using Optical Character Recognition (OCR), which scans each group of pixels within the images and estimates whether or not it could be a letter and replaces the pixels with the ASCII* code for the letter. (*) American Standard Code for Information Interchange.
OCR is the fundamental technology used in ANPR and provides the capability to store and sort data. ANPR cameras need to be of a special type and set up within certain designated parameters.
As a vehicle approaches the camera the software takes a series of ‘snapshots’ and stores them in a file. When the number plate is of sufficient size for the OCR software the frame is scanned and the registration number is converted to ASCII code and held in a list. This continues for a series of images according to the speed and position of the vehicle ensuring that the optimum view of the license plate is achieved.
ANPR capture is totally dependent on the correct set up of camera, lens, illumination, angle of view and configuration.
Colour or monochrome cameras viewing license plates have to contend with a huge variety of lighting conditions, daytime, night-time, sunlight, backlight, headlights, and so on. One configuration simply wouldn’t cope with all conditions, so there is a requirement to provide a constant level and direction of illumination irrespective of any other conditions, and in order for continuous capture of number plate data, specific camera types are needed.
The camera must be sensitive to the infrared part of the light spectrum and be fitted with a filter to restrict the visible part of the spectrum. The lens would be set with wide open iris and fast shutter speed and an infrared source fitted adjacent to the camera.
Because of the retro-reflective characteristics of number plates, infra red illumination will be reflected directly back to the camera without any visible light, other reflections or light refraction. The picture viewed displays detail of the license plate with the OCR software then converting the image to usable code.
The size of a UK license plate on cars and commercial vehicles is approximately 510mm long x 110mm high. Motorcycles are different being approximately 255 x 200. Plates which have been traditionally difficult to capture are easily recognised if cameras are correctly set up, including those at high compound angles, square plates, inverse plates from classic or military vehicles and plates which have no rectangular border.
Just capturing number plates and storing them is not much use by itself. Each new vehicle is automatically displayed upon detection within the event panel, checked against thedatabase and any matches are automatically displayed in the vehicle panel. Report alarms are also checked and displayed together with any special guidance message for the vehicle.
The database stores vehicle and driver details complete with optional images to assist operators when presented with a recognition event. The database is fully searchable by full or part plate (starting, ending, containing), by group or by any key word such as a person’s name, company, vehicle model or colour.