Methods for automatic number plate recognition systems

A method and system (1, fig.1) for automatic number plate recognition (ANPR). A plurality of images of vehicles (6, fig.1) with visible number plates are captured. An algorithm determines probabilities that one or more symbols on the number plates have been correctly recognised based on confidence values associated with the symbols. The accuracy of the ANPR system is estimated based on the probabilities. An alert may be issued or maintenance may be scheduled on the system if the accuracy is below a predetermined threshold. The method may be carried out on images captured during a first time-period (402 fig.4) and then repeated with images captured in a second time period (404 fig.4) to determine a change in accuracy. An alert may be issued or maintenance may be scheduled if the change in accuracy is greater than predetermined thresholds. The probability of correct symbol recognition may be calculated using a machine learning model trained to output a probability of accurate recognition ...