I'm interested in creating a convolutional neural network or LSTM to locate text in an image. I don't want to OCR the text yet, just find the text regions. Yes, I know Tesseract and other systems can do this, but I want to learn how it works by building my own. All of the tutorials and articles I've seen so far have the CNN output to a classification - "image contains a cat", "image contains a dog". Okay that's nice, but it doesn't say anything about where it was found.

Can anyone point me to some information that describes the output layer of a NN that can give location information? Like, x-y co-ordinates of text boxes?


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.