fdroiddata/metadata/edu.sfsu.cs.orange.ocr.txt

59 lines
2.7 KiB
Plaintext
Raw Normal View History

2012-10-14 22:11:10 +00:00
Category:Office
License:Apache2
2013-04-09 12:18:48 +00:00
Web Site:
2012-10-14 22:11:10 +00:00
Source Code:https://github.com/rmtheis/android-ocr
Issue Tracker:https://github.com/rmtheis/android-ocr/issues
2013-04-10 11:02:51 +00:00
Summary:Convert camera images to text
2012-10-14 22:11:10 +00:00
Description:
2013-04-10 11:02:51 +00:00
N.B. The direct translation function won't work as it requires API keys which are
2013-04-09 12:18:48 +00:00
not in the source.
2013-04-09 21:38:55 +00:00
It is possible to long-press the result to copy it, so that it can be pasted
2013-04-10 11:02:51 +00:00
into a browser or a dictionary.
Experimental app for optical character recognition (OCR).
2013-05-27 10:08:12 +00:00
Runs the Tesseract 3.02 OCR engine on your device to find text in images
2013-04-10 11:02:51 +00:00
captured by the device camera, without uploading your images to a server.
2013-05-27 10:08:12 +00:00
It is suitable for recognizing individual words or short phrases of text.
2013-04-10 11:02:51 +00:00
2013-05-27 10:08:12 +00:00
The default single-shot capture runs OCR on a snapshot image that's captured
2013-04-10 11:02:51 +00:00
when you click the shutter button, like a regular photo.
2013-05-27 10:08:12 +00:00
When the "continuous preview" checkbox is checked, the app shows a dynamic,
real-time display of what the device is recognizing right beside the camera
2013-04-10 11:02:51 +00:00
viewfinder. The continuous preview mode works best on a fast device. The
app supports x86 natively.
# Point the device at some text and touch the on-screen shutter button to start OCR
# To copy text to the clipboard or share text, long-press on the text after pressing the shutter button
# For recognizing individual Chinese/Japanese/Korean characters, access the settings and set the page segmentation mode to "single character"
RECOGNITION ACCURACY
* Various factors can cause the OCR to fail: uneven illumination, stylized text, or text without enough contrast from the background. Try to have good lighting
* Hold the device steady, and be sure the picture is in focus
* If you need to scan a large block of text or an entire document, consider using a flatbed document scanner
2013-05-27 10:08:12 +00:00
Supported languages for OCR: Arabic, Bulgarian, Catalan, Chinese (Simplified),
Chinese (Traditional), Czech, Danish, Dutch, English, Finnish, French, German,
Greek, Hindi, Hungarian, Indonesian, Italian, Japanese, Korean, Latvian,
Lithuanian, Polish, Portuguese, Romanian, Russian, Serbian (Latin), Slovak,
2013-04-10 11:02:51 +00:00
Slovenian, Spanish, Swedish, Tagalog, Thai, Turkish, Ukrainian, and Vietnamese.
2013-05-27 10:08:12 +00:00
Arabic OCR requires a large amount of RAM. If your device doesn't have enough
2013-04-10 11:02:51 +00:00
RAM, the app will quit during OCR. The preferred language can be chosen in
the settings.
2012-10-14 22:11:10 +00:00
.
Repo Type:git
Repo:https://github.com/rmtheis/android-ocr.git
2013-04-09 12:18:48 +00:00
Build Version:0.5.12,31,5ca566e5,\
subdir=android,srclibs=TessTwo@cbfa61eff0,prebuild=\
sed -i 's@\(rence.1=\).*@\1../tess-two@' project.properties && \
2013-05-27 10:08:12 +00:00
cp -r $$TessTwo$$ ../,build=$$NDK$$/ndk-build -C ../tess-two
2012-10-14 22:11:10 +00:00
Auto Update Mode:None
2013-04-09 12:18:48 +00:00
# not every version is published and there is no secondary check
Update Check Mode:Market
2012-10-14 22:11:10 +00:00
Current Version:0.5.12
Current Version Code:31