In the past few years, smart systems for parking lot access control are developed to control and register the car data. These systems might use cameras to identify vehicle and plates using CharacterRecognition. Therefore, this work has the main goal to develop a system to detect and recognize car plates on Brazilian pattern to control vehicle access, in which the registered users has the permission to entry the place. For this, were used techniques of Digital Image Processing to extract characters and techniques of Pattern Recognition to identify the numbers and letters.
The found characters are used to assign a grade to a registered plate, allowing the access only when the plate has the probability of 99%. The system was tested with 700 videos, granting the access only when the plate was registered, getting 98,5% hit rate on the tested cases. The movement detection step is linked to the system, making it faster, allowing its application to run real time. Thus, can be concluded that the system shows a high potential of commercial application development.