Read tables with OpenCV & Tesseract OCR For PDF

₹12500-37500 INR

Cancelled

Posted

over 6 years ago

₹12500-37500 INR

Paid on delivery

Project Mission: Convert PDF of tables to EXCEL & CSV-formatted tables. Requirements: OpenCV (Python or Java) / Tesseract OCR V4 / .net / any other Language Want GUI / Command Based Batch Processing Docker A set PDF Files ( Indian regional Language ) be provided as input . It's important not to optimize the solution for these specific tables. The solution must be generic and will be tested against other pdf files It is a priority to handle regular tables with high precision. Proposed steps: 1. Analyze PDF using OpenCV or Any Other Technology to determine table cells (rows and columns). 2. Slice input image into multiple images based on cells. 2. Use Tesseract 4 to OCR text from each cell. 4. Output data to CSV / excel or As Shown / Attached below File Expected outcome: - Conversion is at least 95% accurate with our test-set. Standard tables but not provided to avoid over fitting. - Function / Script / API that takes an PDF and outputs Excel Formatted & Unformulated Readings / Links: Improving quality: Finding text blocks in an image using OpenCV: Table Analysis using with histogram: Docker OpenCV Image: Attached files:

C Programming

Java

Python

Software Architecture

Project ID: 15510457

About the project

16 proposals

Remote project

Active 6 yrs ago

Looking to make some money?

Email address

Benefits of bidding on Freelancer

Set your budget and timeframe

Get paid for your work

Outline your proposal

It's free to sign up and bid on jobs

16 freelancers are bidding on average ₹32,381 INR for this job

@ThanassisKalv

Hello, after checking your PDF layout, I can say with confidence that I can take such a project and achieve the accuracy % you except! Using Python tools and Tesseract, here in Freelancer.com I have already completed a similar enough project (check in this https://www.freelancer.com/projects/python/convert-image-columns-xlsx-python/) The requirement of block/table detection can be achieved robustly with OpenCV. I can provide a GUI with appropriate functionality too I am pretty sure that if we chat more you will understand that I am pretty confident for taking this task! Thanassis Thanks!

₹27,777 INR in 15 days

4.9

(138 reviews)

6.6

@jap2013

Hi, I can build Java application for this project. please check my previous work. thanks

₹30,555 INR in 7 days

5.0

(37 reviews)

6.0

@anuragiitk

I am an IITK graduate and I have 11 years of experience in software development. I have 100% completion rate and I have finished all the projects with the highest level of customer satisfaction. Relevant Skills and Experience I usually finish projects with ease on which other freelancers have already given up. I learn and understand new stuff very fast and finish the job with top quality and reliability. Proposed Milestones ₹27777 INR - First Milestone

₹27,777 INR in 10 days

3.7

(27 reviews)

5.8

@othmane7

I am ready to start working with you right now Relevant Skills and Experience java, pdf, excel, OCR, data parser Proposed Milestones ₹38888 INR - tasks

₹38,888 INR in 10 days

5.0

(6 reviews)

3.8

@hongyuwang76

Experimented java developper, i worked in large companies for several years on web technologies. - Java 8, REST web services, various web applications - Persistence management with Hibernate / Mybatis /SQL (Postgres, Mysql, Oracle) - Angular 2 developpement I also worked on JEE platforms with : Glassfish and JBoss/WildFly. If you find my profile interesting, don't hesitate to contact me.

₹22,222 INR in 15 days

5.0

(3 reviews)

2.8

@ZAHEERUDN

I am really interested in this project. I will do your project in reasonable budget. I am sure you will highly like my work.

₹20,000 INR in 7 days

5.0

(3 reviews)

0.9

@pulkitnigam

I have worked on similar projects to what you are looking for, and I am confident I can exceed your expectations. Relevant Skills and Experience java,javacv,Tesseract ,rxjava Proposed Milestones ₹10000 INR - initialize amount ₹45555 INR - deployment

₹55,555 INR in 45 days

0.0

(0 reviews)

0.0

@Rinkut

A proposal has not yet been provided

₹27,777 INR in 10 days

0.0

(0 reviews)

0.0

@nithanikesh

I can do this work with Python and opencv and the pdf tools of python in 10 days Relevant Skills and Experience Python, scipy, opencv,, signal and image processing Proposed Milestones ₹10000 INR - Development of Python code for automated reading of pdf files ₹10000 INR - Segmentation and drawing of Kannada text from the pdf files ₹7777 INR - Realigning the text into excel table

₹27,777 INR in 10 days

0.0

(0 reviews)

0.0

@davidrai9

Hello, I'm a individual Python/OpenCV/OCR developer with 7 year's experience. I'm a very responsive developer for communication. Have a good day! Kind Regards. Relevant Skills and Experience I hope to you look my portfolios. Proposed Milestones ₹33333 INR - After completion

₹33,333 INR in 10 days