A powerful optical character recognition (OCR) extension to capture and convert images to text
OCR - Image Reader: Edge's Optical Character Recognition Add-On
"OCR - Image Reader" is an Edge extension that introduces an OCR tool in your browser, allowing users to select a region from their active window to capture and recognise text data. Using a robust OCR engine powered by the 'tesseract.js' library, this add-on supports over 100 languages and automatic text orientation. Despite OCR's inherent slowness, this extension keeps users in the loop with progress bar updates. The extension works offline, maintaining user privacy. It is also capable of extracting text from images and restricted webpages.
Add-on stats
Manifest V3
Permissions:
- storage
- unlimitedStorage
- activeTab
- notifications
- scripting
Host permissions:
- https://tessdata.projectnaptha.com/*.gz
- https://github.com/naptha/tessdata/blob/gh-pages/*.gz?raw=true
Size: 2.71M
URLs: Website ,Privacy policy
Full description: See detailed description
Ranking
# 661 ▼ 6
User reviews
Pros
- Works accurately with text recognition
- Simple to use and effective
- No additional purchases required
- Fast performance for the most part
- Useful for students and general users
Cons
- Performance issues reported, especially in text capture accuracy
- Slow downloading of trained data
- Speed complaints highlighted by multiple users
- Limited access to local files and lack of clipboard support
Most mentioned
- Accuracy issues
- Speed of processing
- Ease of use
- Free to use without purchases
- Local file access limitations
User reviews
This is the result of the best accuracy mode:
Bin. “TITI KIAT AK BUWTILI TI NNE GR DHENGE NK LK. TDER PU WE NKE—ANDI— DINI KEKENAN AS ENEK TUT
by Felix, 2025-02-11
It stopped working properly recently, and now barely captures any of the text accurately.
by Brian, 2025-01-29
Funciona bem.
by Iuri, 2025-01-02
Add-on safety
Risk impact
OCR - Image Reader requires a few sensitive permissions. Exercise caution before installing.
Risk impact analysis details
- Critical Request access to the following domains: projectnaptha.com, github.com
- Medium ******* ******* ************* ***** *** ** ******* *** **** ******* ****** ******** *******
Risk likelihood
OCR - Image Reader is probably trust-worthy. Prefer other publishers if available. Exercise caution when installing this add-on.
Risk likelihood analysis details
- High This extension has low user count. Unpopular extensions may not be stable or safe.
- Medium **** ********* *** ******* ** *** **** * ******* *** ******* *** *** ** ****** ** *****
- Low **** ********* *** ***** **** **** * ****** **** ***** ********** *** **** ****** ** ** ****** *** *****
- Good **** ********* *** **** **** *******
Upgrade to see full risk analysis details
Promo images
Similar add-ons
Here are some Edge add-ons that are similar to OCR - Image Reader:
techlo9
3K
Leonardo Compson
2K
GPicy
3K
Oren Chen
18K
GPicy
667
GPicy
1K
Hitesh Saini
14K
OCR Editor
8K
iDooy
33K