在Tess-Two上获取单词列表

Question

I'm developing an app that utilizes OCR on Android. The tess-two sample is working pretty good and I can get the full OCR text but I want to know how I can get the individual words inside the boxes that Tesseract actually outputs. I can use getWords().getBoxRects() to get a list of the bounding boxes and it seems that the getWords() function does what I want but it returns a Pixa object and I'm not sure how a word list (of whatever words are contained inside the boxes) will be obtained from that.

The output I am looking for is a map with the following key-value:

Word : Bounding box

Any tips would be great.

Answer 1

You can parse the hOCR output to obtain the words and their coordinates. See Export HOCR output for tesseract OCR in android .

Or use ResultIterator API, if tess-two supports it.