Most accurate open-source OCR for Japanese?

Posted by Nicolas Raoul on Stack Overflow See other posts from Stack Overflow or by Nicolas Raoul
Published on 2010-04-01T02:11:48Z Indexed on 2010/04/01 2:13 UTC
Read the original article Hit count: 593

Filed under:

ocr

|

japanese

|

open-source

From your experience, what is the most accurate open-source Optical Character Recognition (OCR) library/software to read Japanese text?

I just tried nhocr, its mistake rate is over 2% even on an extremely clean high-definition document.

© Stack Overflow or respective owner

Related posts about ocr

free open-source linux screenshot & ocr tool

as seen on Super User - Search for 'Super User'
I'm looking for a tool which would be able to capture a screen region, pass it to OCR and put the result into clipboard. "import ppm:- | gocr -i - | xclip -selection c" works, but gocr is unreliable: simple text on a webpage has errors. It is a clear font but the OCR tool always misses "r" and replaces… >>> More
OCR, OCR-B Fonts in PHP?

as seen on Stack Overflow - Search for 'Stack Overflow'
Hello, I am looking for a good solution to parse OCR-B fonts off a PNG images fed from scanners. Any tips on a engine? In php >>> More
OCR with Neural network: data extraction

as seen on Stack Overflow - Search for 'Stack Overflow'
I'm using the AForge library framework and its neural network. At the moment when I train my network I create lots of images (one image per letter per font) at a big size (30 pt), cut out the actual letter, scale this down to a smaller size (10x10 px) and then save it to my harddisk. I can then go… >>> More
OCR: How to improve accuracy - existing libraries for removing non-text 'furniture', shapes, etc to

as seen on Stack Overflow - Search for 'Stack Overflow'
I want to remove rectangles etc that enclose text in a screenshot image, so that I can perform optical character recognition to get accurate text from the screenshot. Background: I doing this to extract data from a legacy application for use with other applications. This is the only way to get at… >>> More
OCR an RSA key fob (security token)

as seen on Stack Overflow - Search for 'Stack Overflow'
I put together a quick WinForm/embedded IE browser control which logs into our company's bank website each morning and scrapes/exports the desired deposit information (the bank is a smallish regional bank). Since we have a few dozen "pseudoaccounts" that draw from the same master account, this actually… >>> More

Related posts about japanese

Ubuntu 13.10 japanese keyboard layout intercepts Caps Lock

as seen on Ask Ubuntu - Search for 'Ask Ubuntu'
I've installed Ubuntu 13.10 (clean install on new machine), there are lot of changes for configuring keyboard layouts and I've tried to configure it as I've used earlier: Englis (US), Russian and Japanese (Anthy) with switching between them with Caps Lock key. (See screenshot) Caps Lock switching… >>> More
Software to rename files with Japanese or Korean character/letter filenames to their Romanized (Roma

as seen on Super User - Search for 'Super User'
Is there a program that will rename files with Japanese or Korean characters/letters in their filenames to their Romanized (Roman/Latin letters) equivalents (preferably Hepburn Romanization for Japanese and Revised Romanization for Korean). >>> More
Most accurate open-source OCR for Japanese?

as seen on Stack Overflow - Search for 'Stack Overflow'
From your experience, what is the most accurate open-source Optical Character Recognition (OCR) library/software to read Japanese text? I just tried nhocr, its mistake rate is over 2% even on an extremely clean high-definition document. >>> More
Japanese text garbled while passing to a http restlet service

as seen on Stack Overflow - Search for 'Stack Overflow'
Hi , I have a perl client which is calling a http restlet service (put method). Some of the parameters in this call contain japanese text. when I printed the contents of these request parameters in the restlet service I found these chars garbled ! This is my PERL client code: my %request_headers… >>> More
How can I get Japanese, Chinese and Korean input to work properly on Skype, aMsn and other softwares

as seen on Ask Ubuntu - Search for 'Ask Ubuntu'
I have installed the packages for Japanese (Anthy),and those for Chinese and Korean input. They work perfectly on most of the software that come with Ubuntu, such as the LibreOffice suite and the browsers, however, I cannot input any of these three languages on Skype, aMsn or almost any software I… >>> More