Hindi OCR produces Junk

Discussion for the End User use uf OCR in PDF-XChange Editor and Viewer

Moderators: TrackerSupp-Daniel, Tracker Support, Vasyl-Tracker Dev Team, Sean - Tracker, Paul - Tracker Supp, Chris - Tracker Supp, Tracker Supp-Stefan, Ivan - Tracker Software

Post Reply
Posts: 7
Joined: Thu Sep 15, 2016 3:17 pm

Hindi OCR produces Junk

Post by vsrawat » Sat Sep 17, 2016 2:32 am

This is the output of half a page of Hindi OCR
Protocol Number: TZ-01-002 Dr Reddy’s Laboratories Ltd.
Supplementary Patient Information Sheet & Informed Consent Form for Extension Phase
(Ext Phase ICF)
Version 4.0 dated 11 February 2016

इस अनस'धमक/य पदनमत दर पर कय जए*:
म यह पष कत/कत द क मन' अधयन म भग लन क पकत, उदश, स'भक लभ एव उपयक रप रन पतशत
जखम क बर म रग क उस भष म पर तरह रन समझ दय ह, ज समझन यग एव उपयक ह, और म यह मनत/ममल
ह क रग न उक वरन क समझ लय ह. म यह पमणत कत/कत हक उस रग सचन पतक क एक पत द गई ह. म
यह पष कत/कत दक रग न,उसक सहमत क पतक क रप म, मर उपसत म यह अपन हरनकर कए ह.

अचस'धगक/पदनक क हरपकर मदत नम (सष अकर म) हसकर क तथ
* पदनमत - सचत सहमत चर सचलत' कन कअधक सल करचर

Confidential Page 4 of 4
Ext Phase ICF_Hindi_Version 4.0_14 Sep 2016

English part is coming ok, ub hindi is coming as junk. Nothing is clear.

The input was searchable hindi text in Shreedev 0702 font.

Seems lot more work is required in Hindi OCR.


User avatar
Will - Tracker Supp
Site Admin
Posts: 6905
Joined: Mon Oct 15, 2012 9:21 pm
Location: London, UK

Re: Hindi OCR produces Junk

Post by Will - Tracker Supp » Sat Sep 17, 2016 4:55 pm

Hi Rawat,

Thanks for the post - can you please post a specific example that you're OCRing? I'm afraid that we don't have any Hindi text to scan and use here.

If posting files to this forum, you must archive the files to a ZIP, RAR or 7z file or they will not be uploaded.
Thank you.

Best regards

Will Travaglini
Tracker Support (Europe)
Tracker Software Products Ltd.

Post Reply