I instantiate the opencv filter but interact with it directly like a service. It seems to work easier to use capture frame which returns the image file name and then tesseract.ocr([image file name]) which return a text string of the identified words and the feed it in to MarySpeech.
I will work on some screenshots and attempt to upload some more code. Thanks!
It is just recognizing characters, it doesn't really care what the characters spell. I am guessing if it has patterns for the characters then it should be able to "read" it. I will look in the documentation on tess4j I am guessing it is not English only.
Ahahah .. yes awesome magic
Ahahah .. yes awesome magic ;)
It be nice to post diagram (ie go to the gui tab and spread out all the little boxes - the screenshot and post the pictures)
There a tesseract service if I remember correctly, and a filter in OpenCV .. are you using the filter ?
The short answer is, Yes!
I instantiate the opencv filter but interact with it directly like a service. It seems to work easier to use capture frame which returns the image file name and then tesseract.ocr([image file name]) which return a text string of the identified words and the feed it in to MarySpeech.
I will work on some screenshots and attempt to upload some more code. Thanks!
I love it ! Do you think
I love it ! Do you think tesseract can parse other languages ?
Good Question Moz!
It is just recognizing characters, it doesn't really care what the characters spell. I am guessing if it has patterns for the characters then it should be able to "read" it. I will look in the documentation on tess4j I am guessing it is not English only.