LICENSE PLATE RECOGNITION SYSTEM BASED ON MASK R-CNN

Automatic license plate recognition (ALPR) systems can be found in many different applications. If a person has driving license, the probably had already seen smart road camera after speed limit sign or on crossroad. Every year number of cars roads growth very fast. It is also obvious that such used out-of-road situations. For instance, this type for automatic access control private property parking, even log system are being literally everywhere. Because popularity ALPR systems, there two main goals, which pursued by researches: and accuracy recognition. Speed detection important real-time systems. Accuracy every system. The more accurate is, reliable it is. example, car accident should as possible order to used, because no one wants get billed with wrongdoing, wasn’t committed them.
 purpose study develop high precision extraction possibilities. In achieve goal modern solutions technologies were studied solution presented. technology project artificial intelligence and, specifically, convolutional neural network. As algorithm Mask R-CNN detection. To present reasonable research, was tested hardware (CPU, GPU, Raspberry PI 4) datasets.