I need an OCR software/service that allows me to scan large png images, detect specific words and output the position (X and Y) of the specific words. Can I do this using the free OCR API?
I have no idea how to do this, I’m a total beginner, so any suggestions would be appreciated!
Our free ocr api as the option to return the complete overlay data. If the parameter isOverlayRequired=true, then the ocr result includes the “bounding box” for each word. These are the x/y coordinates you need.
It seems you are not looking for an OCR API (= a tool for developers), but simply a good OCR software. If so, I can recommend the Copyfish Free OCR Software - it is an open-source browser extension that uses our OCR API “inside”.
well I just tried copyfish extension and it doesn’t give me the x y location of words, can it do that?
I’m happy to learn to use the API, if copyfish won’t give me the location, it appears like its my only option, so what are the steps required for me to get it up and running?