License plate recognition is widely used in various industries and areas of the world. Therefore, there are already many systems and solutions for this application. In this paper, a plate detector for stationary vehicles was implemented using an OpenMV H7 Plus camera. The computer vision techniques used are OpenCV, Keras, TensorFlow Lite, Haar Cascades, MicroPython, etc. Numerous software tools were also used for training the classifiers and neural networks, as well as for image processing and system implementation. Some of them are the Cascade Trainer GUI, used to train Haar’s classifier, and Edge Impulse, used to train neural networks. The microcontroller is programmed using OpenMV IDE, which is made specifically for the OpenMV camera. Files containing the classifier and .tflite files of neural networks are loaded directly into the editor. The OpenMV IDE works with the camera in real time so the complete implementation is tested directly on the camera. The ultimate goal was to prove that this particular application can be done with the OpenMV H7 Plus camera, so the end results are positive. Additional improvements are possible in the form of training with a much larger and better data set, automating the detection and classification of characters from the table frame and enabling night work.