I've had this idea for a while, but as an iPhone app. The case where I could have used it the most was when I would be studying and looking through textbooks for a particular word or phrase. It would be so convenient to just take a picture, input the text to look for, and see a highlight. If this were a mobile app and I were still in college, I would most certainly buy it.
Show HN: Convert scanned documents into searchable PDFs
11–20 of 22 posts
Re: Show HN: Convert scanned documents into searchable PDFs
#12Been hanging here in Firefox now for about 5-10 minutes its a receipt for my insurance (no private info) about 2 pages in length.
Either way, super cool idea. My Dad will be stoked about this as he's been OCR'ing his way into oblivion for the past few years.
Re: Show HN: Convert scanned documents into searchable PDFs
#13Is this Web site accessible (say, via screen-reader)? Scanned PDFs can be a huge problem for people who are visually impaired.
Re: Show HN: Convert scanned documents into searchable PDFs
#14I use PDFScanner on my Mac. Works great at scanning time or post-scanning. No, it's not free but it's worth it. Pay the $15, ya cheap bastiches! :-)
BTW, how is this news?
Re: Show HN: Convert scanned documents into searchable PDFs
#15Earlier quoted context omitted.
Given that the OCR'ed PDFs use the "GlyphLessFont" font, it seems that tesseract [1] is used. [1] https://github.com/tesseract-ocr/tesseract
I hope not. Tesseract delivers bad results on high quality scans, far below the same OCR quality achieved by services like Google Books. What the OCR market needs is someone who will bring that level of OCR quality - or better - to the masses (perhaps some deep learning grad student with time to kill?), not yet another wrapper around Tesseract. We have those already!
Have you looked into ocropy[0]?
Here's a nice intro[1] that later talks about how it achieves higher accuracy using an LSTM model[2].
[0] https://github.com/tmbdev/ocropy
[1] http://www.danvk.org/2015/01/09/extracting-text-from-an-imag...
[2] http://www.danvk.org/2015/01/11/training-an-ocropus-ocr-mode...
Re: Show HN: Convert scanned documents into searchable PDFs
#16I use PDFScanner on my Mac. Works great at scanning time or post-scanning. No, it's not free but it's worth it. Pay the $15, ya cheap bastiches! :-) BTW, how is this news?
HN is not just for news. It's for whatever you deem worthy of sharing.
It comes down to how many people agree it's interesting by upvoting :)
Re: Show HN: Convert scanned documents into searchable PDFs
#17I just use the OCR function built in to Adobe Acrobat. Don't know it the OCR function is available in the reader version.
Same here, have been using acrobat x for this purpose for years, very impressed how good the OCR is.
Re: Show HN: Convert scanned documents into searchable PDFs
#18Earlier quoted context omitted.
Given that the OCR'ed PDFs use the "GlyphLessFont" font, it seems that tesseract [1] is used. [1] https://github.com/tesseract-ocr/tesseract
I hope not. Tesseract delivers bad results on high quality scans, far below the same OCR quality achieved by services like Google Books. What the OCR market needs is someone who will bring that level of OCR quality - or better - to the masses (perhaps some deep learning grad student with time to kill?), not yet another wrapper around Tesseract. We have those already!
Is the problem really Tesseract or the fact that it doesn't have a robust front-end performing segmentation, de-skewing, better binarization, etc? I've heard that Google Books is actually using the Tesseract engine but has seen better results in part from better training but mostly from a more advanced system breaking each page into the blocks of text which are actually OCRed.
Re: Show HN: Convert scanned documents into searchable PDFs
#19Earlier quoted context omitted.
I hope not. Tesseract delivers bad results on high quality scans, far below the same OCR quality achieved by services like Google Books. What the OCR market needs is someone who will bring that level of OCR quality - or better - to the masses (perhaps some deep learning grad student with time to kill?), not yet another wrapper around Tesseract. We have those already!
Have you looked into ocropy[0]? Here's a nice intro[1] that later talks about how it achieves higher accuracy using an LSTM model[2]. [0] https://github.com/tmbdev/ocropy [1] http://www.danvk.org/2015/01/09/extracting-text-from-an-imag... [2] http://www.danvk.org/2015/01/11/training-an-ocropus-ocr-mode...
I have not. It sounds interesting but raw and unsuitable for end-users. I hope the quality improves and they can get it packaged up in a way that existing document scanners can plug into easily.
Re: Show HN: Convert scanned documents into searchable PDFs
#20Earlier quoted context omitted.
I hope not. Tesseract delivers bad results on high quality scans, far below the same OCR quality achieved by services like Google Books. What the OCR market needs is someone who will bring that level of OCR quality - or better - to the masses (perhaps some deep learning grad student with time to kill?), not yet another wrapper around Tesseract. We have those already!
I have had great result using tesseract via gimagereader. Are you sure your configuration is good?
Possible to upload an example image + result?