Tesseract.js
Languages and libraries
ocr library
SHOW HN2016
727points
97comments
#12of 2,264 in 2016
Top 1%of 2016 by points
How HN took it
MixedNo clear lean
7 positive, 22 neutral or asking, 1 mixed, 16 critical, out of 46 comments about the project. Thread score -0.19.
Performance: 1 for, 11 againstIdea: 4 for, 1 againstDocs: 0 for, 2 againstExecution: 0 for, 1 againstDesign: 0 for, 1 against
The thread, comment by comment
Each row is a top-level comment and its replies, in HN's order. Select a cell to open that comment on HN.
positive neutral or mixed critical about another commenter or something else the maker
What HN said
What people liked
Useful client-side OCR that is easy to use from JavaScript
From 3 comments
Does this mean I can implement Tesseract on my home server without using php's shell_exec to perform magic on my files? I can just use Jscript instead? Cool! My current HRCloud2…
zelon88 on HNYep, this is completely client side :) You can even host the external language files yourself as described in the readme: https://github.com/naptha/tesseract.js#local-installation
bijection on HNI've always wanted to use Tesseract on .NET projects but it was always clumsy (wrappers). This looks like it'll make things easier. Thanks for putting this out.
gentleteblor on HN
Impressive that it runs as pure JS
From 1 comment
Impressive that this is pure JS, however trying an image cut from the page itself gave this result > Dropan Enghsh Wage on (Ms page to OCR m Should be > Drop an English image on…
KiwiCoder on HN
Objections
Accuracy is poor on small or screen-resolution text
From 4 comments
The text detection is lacking in comparison to Google's Vision API. Here is a real-life comparison between Tesseract and Google's Vision API, based on a PDF a user of our website…
pyronite on HNYour comment (zoomed in Chrome on Win 10): http://i.imgur.com/uuFhw90.png Tesseract.js analysis: ``` Although Googie's API is certaihiy better, Tesseract.js should work simiiarly…
jaytaylor on HNExcited about this... but the OCR quality seems to be very bad. Maybe it's not optimized for recognizing black text on a white background. For example, I took a screenshot of…
greenpizza13 on HNImpressive that this is pure JS, however trying an image cut from the page itself gave this result > Dropan Enghsh Wage on (Ms page to OCR m Should be > Drop an English image on…
KiwiCoder on HN
Much worse than Google Cloud Vision
From 2 comments
The text detection is lacking in comparison to Google's Vision API. Here is a real-life comparison between Tesseract and Google's Vision API, based on a PDF a user of our website…
pyronite on HNWe spent a decent amount of time evaluating Abbyy vs Tesseract vs Cloud Vision. Cloud Vision wins hands down and is very reasonably priced.
driverdan on HN
Described as pure JS is misleading since it is compiled C++
From 1 comment
The title and description are very misleading: this is technically "pure JavaScript" but the JS is compiled from the original C++ library of the same name using emscripten. I…
daliwali on HN
Name overlaps with the existing tesseract-ocr project
From 1 comment
Is this at all affiliated with the already-existing tesseract OCR library? It doesn't seem to be from my cursory check so if not you need to rename your library, because you're…
employee8000 on HN
Requests
Stroke width transform preprocessing
From 1 comment
This would be really cool! We would welcome a pull request and / or link to any downstream project working on this. In a similar vein, we've been considering adding the stroke…
bijection on HN
More documentation on training
From 1 comment
More instructions, like how to train it, would be nice.
z3t4 on HN
Promise interface with progress support
From 1 comment
Why the promise-like interface? If it returned a promise with a this-returning progress method monkey-patched onto it, then you could use it otherwise like a regular promise: ```…
AgentME on HN
Questions
Is it slower than the command-line Tesseract?
From 1 comment
Is it true, that original implementation of tesseract exexuted from commandline is faster than javascript translated version?
codemode on HN
How does it compare with Ocrad.js?
From 1 comment
How does it compare with Ocrad.js?
niutech on HN
Alternatives named
Google Cloud Vision API
From 2 comments
The text detection is lacking in comparison to Google's Vision API. Here is a real-life comparison between Tesseract and Google's Vision API, based on a PDF a user of our website…
pyronite on HNWe spent a decent amount of time evaluating Abbyy vs Tesseract vs Cloud Vision. Cloud Vision wins hands down and is very reasonably priced.
driverdan on HN
Tesseract (tesseract-ocr)
From 1 comment
Your comment (zoomed in Chrome on Win 10): http://i.imgur.com/uuFhw90.png Tesseract.js analysis: ``` Although Googie's API is certaihiy better, Tesseract.js should work simiiarly…
jaytaylor on HN
ABBYY
From 1 comment
We spent a decent amount of time evaluating Abbyy vs Tesseract vs Cloud Vision. Cloud Vision wins hands down and is very reasonably priced.
driverdan on HN
OCR.space API
From 1 comment
This is the correct pricing. One caveat: Even the free tier requires you to enter a credit card. For higher volumes, there is also the OCR.space api. It offers 25,000 free…
noteone on HN
Ocrad.js
From 1 comment
How does it compare with Ocrad.js?
niutech on HN