I gang

Looking for a developer who is familiar with OCR technologies to develop a software that will be capable of extracting text from pdf files / images and saving the output in a database -- 2

Hello everybody,

We need your help to develop a software that will be capable (through a wizard import) of extracting text from pdf files / images and saving the output in a database.

The files from which we should extrapolate the text are mainly CVs.

So the fields that interest us are Name, Surname, Date of Birth, Email, Address, Region, Education, Work Experience ...etc…

We know from the beginning how the files are visually made:

- European format curriculum;

- Linkedin Curriculum;

- Indeed CV.

But it would be better if we could build something using machine learning and train each time different model

The mechanism will mainly be like this:

Create a dashboard and distinguish two types of users-roles, Admin and SuperAdmin.

Admin Side:

1. The Admin log in on the portal;

2. Choose the type of Curriculum vitae (Eu format, Linkedin or Indeed);

3. Upload one or more files, for example 10 files at a time;

4. Start importing;

5. We should carry out the guided import more or less as it happens in this video ([login to view URL]), with the preview of the files on the left and the imported fields on the right, giving the possibility to modify and correct them, click on next and go to process next file.

Once the process is complete, save everything to the database.

In the dashboard the Admin will have the possibility to:

1. Search, consult, modify and categorize (with labels) the information imported during the ocr recognition process;

2. Select some fields such as Name, Surname, Email and export them in csv, xlsx or pdf file.

SuperAdmin side:

In addition to the Admin capabilities, the SuperAdmin user can:

1. Create / delete Admin users;

2. Check the overall report of all imported data;

3. Check the report of imported data for a given Admin user;

We should then create a module to be installed separately (for both the Admin and SuperAdmin roles) to send single or mass emails to those people whose imported the data.

A resume will surely contain an email field.

Then the "Mail Module" will allow you to select (checkbox) the relevant rows and then click on a button for massive email, where a popup will open with the text to be written.

The "Mail Module" will contain a section called "Settings" where it will be possible to:

1. Configure the email that will be used, then email, password, smtp address, port, ssl / tls encryption

2. Email signature.

Searching the web I found a library called "tesseract-ocr"

[login to view URL]

A wrapper to use it with PHP

[login to view URL]

or directly in Python

[login to view URL]

or on Node.js

[login to view URL]

The latter clearly offers the possibility of using frontend frameworks such as Vue.js or Angular.js

With Vue: [login to view URL]

With Angular: [login to view URL]

With React: [login to view URL]

Typescript: [login to view URL]

Below there is a tutorial on how to create a ocr microservice with Tesseract, PDFBox and Docker

[login to view URL]

Better solutions are welcome!

Attention:

This is a project that will require future changes and updates, it is not a one-time-job, but it is an investment in a product that will be resold to many (hopefully) customers and which will therefore require (paid) intervention by of a developer for the initial configuration.

Who wants to get on the train?

Tickets are on sale ... :)

Evner: OCR, Data Extraction, React.js, MongoDB, Machine Learning (ML)

Se mere: iphone looking developer, looking developer team, looking developer iphone app developer, ifferent stages sdlc develop software bank atm machine, develop software small retail shop, looking call center representative agent supervisor software, looking developer kentico cms, kosice develop software, develop software users guide, object oriented data model helps develop software system, companies develop software home based developer, develop software convert voice text, looking developer capable building group buying website, looking for a developer to to further develop an existing mobile app west beach, looking for member to member matrix software developer, usa software companies looking for cleints in india to develop software product, how ocr works for extracting text from the images, describe what you are looking for in your next job software developer

Om arbejdsgiveren:
( 5 bedømmelser ) Napoli, Italy

Projekt ID: #30543607

Tildelt til:

vbidprojects21

OnPremise Software Delivery with following modules - - User Module with below features - Manual mode - Semi auto - Automatic - Batch processing support - Multi-language - Dashboard - Email module Flere

$2250 USD in 80 dage
(0 bedømmelser)
0.0

35 freelancere byder i gennemsnit $2403 timen for dette job

(14 bedømmelser)
6.5
kevinlee1238

Hello, sir I am a professional OCR developer. I know the tesseract, google vsion for ocr well I developed several products for image processing [login to view URL] [login to view URL] Flere

$2000 USD in 30 dage
(10 bedømmelser)
5.6
(7 bedømmelser)
5.7
nemanjadevelope2

https://www.freelancer.com/u/nemanjadevelope2 Hello, I am very good at computer vision like OCR. Please check my profile. I have done projects about OCR. Please open chat so let's discuss more. Thank you. Nemanja.

$3000 USD in 7 dage
(7 bedømmelser)
5.1
seniorarm99

Hi, How are you, I have read your description carefully and understood your requirements. As you can see on my portfolio, I am a senior software developer who expertise desktop app development, ML and algorithimic prob Flere

$2250 USD in 7 dage
(1 bedømmelse)
4.7
(2 bedømmelser)
4.5
AzzkaNoor

Good day. Hope this proposal finds you in the best of your health. It is my humble offer to present my services to you for this project related to software that will be capable of extracting text from pdf files / image Flere

$3000 USD in 25 dage
(2 bedømmelser)
4.7
Igorter

Hi, I am interested in your project as a Machine Learning, OCR Expert. I am good at tessseract ocr and deep learning based OCR, I have built some OCR engine for Invoice and Medical Report. In my experiences, OCR works Flere

$3000 USD in 7 dage
(8 bedømmelser)
4.7
kordiukovkyrylo

✨ Hi, Good day! ✨ I have great interest in the project as I have all qualities you need. I have a great relevant experience, which is very similar to your project so I am very confident I would be an excellent addition Flere

$2500 USD in 21 dage
(3 bedømmelser)
4.0
Annmarie1995

Hi!, I am a professional data scientist with 5 years of experience. I hold an MBA and first Degree in statistics which provides me with the necessary background to handle your project. I've carefully checked your requ Flere

$2500 USD på 1 dag
(6 bedømmelser)
3.9
sevastyanovilya2

Hello, I read your proposal very carefully and thank you for your all kind url. May I help you? I think ur project requires new thechs, maybe I don't know all, but love to do it because I can expand my skills. I like j Flere

$2000 USD in 7 dage
(1 bedømmelse)
3.7
jap2013

Hi, Greeting of the day. I have gone through your ocr project. There are many ML and image processing based libraries available for OCR. Tesseract is a classical tool and also many new deep learning based open-source Flere

$2550 USD in 15 dage
(3 bedømmelser)
3.8
d1master

Dear Hiring Manager, I have experience in image processing with python such as cropping, merging, OCR. In the last project I've implemented that comparing system with .docx and converted .pdf files with OCR. For compa Flere

$3000 USD in 25 dage
(2 bedømmelser)
3.7
davronbekvssatto

Hi I am Senior Full stack engineer with skills including React.js, MongoDB, Machine Learning (ML), Data Extraction and OCR etc. Very Thanks for your positing "Looking for a developer who is familiar with OCR technolog Flere

$2500 USD in 7 dage
(4 bedømmelser)
2.8
markverenich103

★★★★★ You will succeed!!! ★★★★★ I really want to be contributed to letting your vision come true and have such great ability and proficiency. I have +6 years of experiences in ReactJS, Next and Material-UI are my best Flere

$2250 USD in 7 dage
(2 bedømmelser)
2.7
Dovasy

Hi how are you doing I have checked your project's description in detail I think I can complete your OCR projectr perfectly because I have rich experience in this kinda Machine learning project development for 10+ yea Flere

$2500 USD in 25 dage
(1 bedømmelse)
2.5
popovicjovan185

Hi, there. Hope you are doing well. I will develop a software that extracting text from pdf files and saving the output in a database. I have been working as a senior full stack developer for over 5 years and have a to Flere

$1500 USD in 7 dage
(2 bedømmelser)
2.6
liberato7

Hi, I read your requirement carefully. I am a professional MERN(MongoDB, Express, ReactJS, NodeJS ) Stack developer. As I have skills like JavaScript, Website Design, Graphic Design, HTML,PHP, ReactJS, NodeJS, MySQL an Flere

$1500 USD in 7 dage
(2 bedømmelser)
2.3
ahmedecw123

hi how are you ? I have an experience with OCR more than five years, but i use C# and ASP.NET. i will do all requirements you need. good day for you

$1500 USD in 7 dage
(4 bedømmelser)
2.0
kiryasidorov200

Hello. Thanks for your job posting. I just checked your project carefully. So it is very motivated and interesting for me. It is an ideal match for my skill and experience. I have rich experience in PHP, Laravel, React Flere

$2500 USD in 30 dage
(1 bedømmelse)
1.4