I have tried tessdata_fast, the result in English better but get worse in
Arabic
Result :
SimplifiedArabic
?ع?
?ao oe " "? اموه
?جوجا ( ?Google? يستعد لاقتحام أدمغتنا
?الاحد 9 سبتمبر 2018 1
?الاقتصادية" من الزياض"
?و ابه سب
?هل حدث وأن بحثت عن منتج معين عبر الإنترنت وتفاجأت باقتراحات عدي
>
> Please try with tessdata_fast
--
You received this message because you are subscribed to the Google Groups
"tesseract-ocr" group.
To unsubscribe from this group and stop receiving emails from it, send an email
to tesseract-ocr+unsubscr...@googlegroups.com.
To post to this group, send email
Yes, using best data
From: Adrian Owen
Sent: Tuesday, October 16, 2018 3:44 PM
To: tesseract-ocr@googlegroups.com
Subject: RE: [tesseract-ocr] Multiple Languages
Are you using the best data: https://github.com/tesseract-ocr/tessdata_best ?
From: tesseract-ocr@googlegroups.com [mailto:tesseract
Are you using the best data: https://github.com/tesseract-ocr/tessdata_best ?
From: tesseract-ocr@googlegroups.com [mailto:tesseract-ocr@googlegroups.com] On
Behalf Of MariamHi
Sent: 16 October 2018 13:19
To: tesseract-ocr@googlegroups.com
Subject: RE: [tesseract-ocr] Multiple Languages
Result
0658 855108160؛ أن الكثير من خدمات جوجل على
أجهزة آيفون 10110106 وآندرويد 8001010 تخزّن بيانات
مواقع المستخدمين» حتى وإن قاموا بإيقاف تشغيل خدمات تحديد الموقع الجغرافي بتغيير
إعدادات الخصوصية المتوفرة في تلك الأجهزة.
From: MariamHi
Sent: Tuesday, October 16, 2018 3:17 PM
To: tesseract-ocr@goog
ي بتغيير
إعدادات الخصوصية المتوفرة في تلك الأجهزة.
From: Adrian Owen<mailto:adrian.o...@eesm.com>
Sent: Tuesday, October 16, 2018 1:23 PM
To: tesseract-ocr@googlegroups.com<mailto:tesseract-ocr@googlegroups.com>
Subject: RE: [tesseract-ocr] Multiple Languages
try PageSegmentationMode.AU
: Adrian Owen
Sent: Tuesday, October 16, 2018 1:23 PM
To: tesseract-ocr@googlegroups.com
Subject: RE: [tesseract-ocr] Multiple Languages
try PageSegmentationMode.AUTO
You may need to enlarge to 300, what’s original DPI?
From: tesseract-ocr@googlegroups.com [mailto:tesseract-ocr@googlegroups.com]
try PageSegmentationMode.AUTO
You may need to enlarge to 300, what’s original DPI?
From: tesseract-ocr@googlegroups.com [mailto:tesseract-ocr@googlegroups.com] On
Behalf Of MariamHi
Sent: 16 October 2018 11:07
To: tesseract-ocr@googlegroups.com
Subject: RE: [tesseract-ocr] Multiple Languages
Try changing order: English+Arabic
Any better ?
From: tesseract-ocr@googlegroups.com [mailto:tesseract-ocr@googlegroups.com] On
Behalf Of MariamHi
Sent: 16 October 2018 08:27
To: tesseract-ocr@googlegroups.com
Subject: RE: [tesseract-ocr] Multiple Languages
When I did pre-processing I get
: Adrian Owen
Sent: Monday, October 15, 2018 3:42 PM
To: tesseract-ocr@googlegroups.com
Subject: RE: [tesseract-ocr] Multiple Languages
Gimp is your friend:
https://stackoverflow.com/questions/9480013/image-processing-to-improve-tesseract-ocr-accuracy
If your programming, use KalikoImage library
)
YES: resize to 300DPI
YES: Apply filters
Hope helps, Adrian
From: tesseract-ocr@googlegroups.com [mailto:tesseract-ocr@googlegroups.com] On
Behalf Of MariamHi
Sent: 15 October 2018 13:38
To: tesseract-ocr@googlegroups.com
Subject: RE: [tesseract-ocr] Multiple Languages
I did this but I have Bad
I did this but I have Bad recognition for English word .. what is the accuracy
for multiple languages and how to improve it ?
From: Adrian Owen
Sent: Monday, October 15, 2018 3:35 PM
To: tesseract-ocr
Subject: Re: [tesseract-ocr] Multiple Languages
Just list locales using + delimiter.
Sent from
Just list locales using + delimiter.
Sent from my Huawei Mobile
Original Message
Subject: [tesseract-ocr] Multiple Languages
From: Mariam Hijazi
To: tesseract-ocr
CC:
Does tesseract support recognize multiple language in one document ? and how
would do that ?
Regards.
--
You
Does tesseract support recognize multiple language in one document ? and
how would do that ?
Regards.
--
You received this message because you are subscribed to the Google Groups
"tesseract-ocr" group.
To unsubscribe from this group and stop receiving emails from it, send an email
to tesseract
14 matches
Mail list logo
