Manually correcting rough OCR-ed documents (English)
- or -
Post a project like this3058
$
- Posted:
- Proposals: 12
- Remote
- #970457
- Awarded
◕ Data Entry ◕ Web Research ◕ Virtual Assistant ◕ Data Extraction ◕ Data Conversion ◕ MS Word ◕ MS Excel ◕ Product Upload ◕ JIRA Admin ◕ PDF to word/excel ◕ Word to PDF ◕ Oracle PL/SQL
Colombo
Data Entry Operator, Word, Excel Expert | Fillable PDF Form | Edit PDF | Audio Editer
Colombo
Email Findings, Lead generation , Contact Building , LinkedIn Prospecting, Data Gathering & Processing, Products upload to Online platforms Such as Amazon, eBay, Etsy & Shopify.
Hyderabad
Email Deliverability, DNS, Google Workspace, Office 365, DMARC, Website Migration Expert
Accra
109778728487931870132395238031257152675639386560186577010461301108802
Description
Experience Level: Entry
Anyone who knows English can do this (tedious) job.
The original PDF documents are bi-lingual (Hebrew-English). A rough OCR was done for the whole document producing a dirty copy with loads of extra gibberish (for pictures, Hebrew, etc.)
It will be your job to compare the OCR-ed copy with the original and:
- clean the copy so that ONLY the English text remains
- compare the remaining English text with the original and manually correct any OCR related mistakes
- unify the formatting so that a running text is created
You will stay in contact with me throughout the process and verify with me any question you might have.
I expect a clean copy that is true to the original with at least 95% accuracy.
For the right price, this could become a recurrent project.
Example attached below.
Explicit instructions with be given from which page to start (eg in the attached example the text I am interested in starts at the bottom of page 3)
The original PDF documents are bi-lingual (Hebrew-English). A rough OCR was done for the whole document producing a dirty copy with loads of extra gibberish (for pictures, Hebrew, etc.)
It will be your job to compare the OCR-ed copy with the original and:
- clean the copy so that ONLY the English text remains
- compare the remaining English text with the original and manually correct any OCR related mistakes
- unify the formatting so that a running text is created
You will stay in contact with me throughout the process and verify with me any question you might have.
I expect a clean copy that is true to the original with at least 95% accuracy.
For the right price, this could become a recurrent project.
Example attached below.
Explicit instructions with be given from which page to start (eg in the attached example the text I am interested in starts at the bottom of page 3)
Avraham R.
100% (38)Projects Completed
47
Freelancers worked with
11
Projects awarded
88%
Last project
29 Aug 2023
Israel
New Proposal
Login to your account and send a proposal now to get this project.
Log inClarification Board Ask a Question
-
There are no clarification messages.
We collect cookies to enable the proper functioning and security of our website, and to enhance your experience. By clicking on 'Accept All Cookies', you consent to the use of these cookies. You can change your 'Cookies Settings' at any time. For more information, please read ourCookie Policy
Cookie Settings
Accept All Cookies