![]() After detecting the license plates, our AI needs to read them using another computer vision task called Optical Character Recognition (OCR). There are many subfields of Computer Vision, such as Image Classification, Instance Segmentation and Text-to-image Generation (like the amazing DALLE-2, Midjourney and Stable Diffusion), but as we specified in the plan, our license plate recognition system will need to detect all the license plates in the frames streamed from the camera, and that can be done using a computer vision task called Object Detection. Then, each frame containing at least one license plate will be saved in a local folder called "license-plates" along with its corresponding JSON file consisting of the detection information (position, size and text of the license plate). Our program runs our AI model to detect and read license plates every 2 seconds. ![]() Points the camera to a place where vehicles will pass through. ![]() The user connects a camera to the computer and starts our program. Let’s think for a minute how our ANPR / ALPR system should work before we get started.
0 Comments
Leave a Reply. |