I’ve done the character recognition. To recognize characters from an image,you need to find characters in the image (scanned image with noise) and I don’t know how to do this.
There is an example that shows how to find house numbers in pictures: https://github.com/eclipse/deeplearning4j-examples/blob/master/dl4j-examples/src/main/java/org/deeplearning4j/examples/convolution/objectdetection/HouseNumberDetection.java
However, there is no example that does full OCR over a document.