License plate digit recognition using 7×5 binary templates at an outdoor parking lot entrance

Digit recognition for license plate recognition is a core process, simplicity on the algorithm to recognize digits on the LPR context is of importance, given that there is an ever increasing vehicle flow and need for recognizing license plates on different environments and applications such as: unattended parking lots, automatic toll collection, traffic supervision, access control of restricted office and housing areas. This work uses digit templates as the means to recognize digits. These are 7x5 templates used to compare with binarized license plate digits and selecting one with the smallest difference. Uses image width of the segmented digit as a feature to a perfect recognition of digit ´1´. A segmented digit is reduced to a multi-valued 7x5 matrix, then binarized and compared to select one. 841 segmented digits form the license plates are the test set. Test images were taken at the entrance of an outdoor parking lot. Results show a 97.3% correct recognition on a real outdoor environment.