I’m totally new to image recognition. I’m looking for a way to build very basic number recognition like NPR but for a 4 digit number like on a cows ear tag. I have a powerful laptop and basic programming abilities , I was hoping I could use raspberry pi or similar to start this off.
Can someone suggest what hardware and software I could use to get me going please.
You can indeed do this sort of task with a Raspberry Pi, Python and OpenCV there are a number of write-ups on how to do this on the PyImageSearch site such as https://www.pyimagesearch.com/2017/02/13/recognizing-digits-with-opencv-and-python/ (dealing with number recognition) and https://www.pyimagesearch.com/2018/08/20/opencv-text-detection-east-text-detector/ (locating text in images/video streams).
If you're just trying to convert an image of alphanumeric characters to text, you need Optical Character Recognition (OCR) software. There are a number of free OCR applications that run on Windows or Linux , though I'm not sure a Pi can handle them. Try FreeOCR or alternatives.
Some scanners come with OCR software, such ABBYY FineReader, but commercial products are ~US$200 or more.
The accuracy of OCR depends on the font, image quality and other factors.
