PDF or Image shape recognition

Closed Posted 4 years ago Paid on delivery
Closed Paid on delivery

I have an application that is currently storing PDF documents. I am currently able to scrape the text from the document. However on the documents that my industry deal with, we have symbols i.e. square with a circle inside and will have two or more lines of text in the symbol. When scaping the document text it extracts the text from the symbols, but considers them as two separate words. What I require is someone to do is write some code that can do shape recognition and then, once the same is matched extract the text from within the symbol region.

If this is not possible using PDF then I would consider exporting the PDF's to image format and using image processing and recognition to find this. However I would need to be able to relate the symbol region position back to the position on the PDF so I can extract the text.

I am currently using PDFXchange PDF API, and if this is able to be used for the symbol recognition that great, if not I am open to any solution.

Important: Please note that I will only consider candidates that write a response specific to this project brief. And a thought on the way this project can be achieved. Any generic responses to this job will result in the candidate not being considered.

VB.NET PDF Face Recognition Image Processing

Project ID: #22439790

About the project

20 proposals Remote project Active 4 years ago

20 freelancers are bidding on average $568 for this job

khanicha

This can't be solved using any PDF library. You should convert this to an image and use tesseract libs for object recognition and extract the ROI, Region of Interest. Then using the same lib you could the OCR function More

$500 USD in 3 days
(19 Reviews)
7.7
AwaisChaudhry

Hi,. I have gone through the brief details mentioned on the job. I have done multiple jobs with Face Recognition, Image Processing, PDF, VB.NET which are the skills required to get this job done. Lets start the chat so More

$750 USD in 7 days
(2 Reviews)
4.9
dinhfreedom

Dear sir. I know you would like to develop software to recognition several industrial symbol objects and texts inside it correctly and efficiently. Your project attracted my attention at first glance, because I've exte More

$500 USD in 7 days
(6 Reviews)
4.3
sonarkaushik

Sir,      I am well versed in these kind of jobs and can do your project as per requirement. **I am ready to start Waiting to hear from you. Regards

$488 USD in 3 days
(4 Reviews)
4.3
jap2013

Hi, I have read your text extraction and shape recognition project. the project need two things. first we need to recognise all the shape objects from the pdf image and know their position. next we need to do the OCR More

$777 USD in 5 days
(2 Reviews)
4.1
Dream20172017

Hi, there ! I have read your project description carefully. I am really confident about your project as a Computer Vision expert. I have been working in computer vision for 10+ years. So I can finish your project profe More

$250 USD in 7 days
(2 Reviews)
3.1
prefectworld

I have extensive experience in the domains of Natural Language Processing, Image Recognition & Artificial Intelligence,Recommender Systems,Machine learning,Data Minning, Deep Learning, Computer Vision, AI text analysis More

$499 USD in 2 days
(0 Reviews)
0.0
nahean05

Hello I have experience in pdf shape recognition and pdf to any other formats and having the ability to give back to you excellent results.   I will send you trial work (free) to make it clear I'm 100% capable to do More

$277 USD in 7 days
(0 Reviews)
0.0
gisdeveloper2010

I am an expert at developing the facial recognition system. I have rich experiences of facial detection, facial recognition and OCR. And I am good at Image processing. I am good at Tensorflow, Keras, PyTorch and openCV More

$750 USD in 7 days
(0 Reviews)
0.0
VisionRocks

Hello, I am 4 years PhD student in the field of computer vision and machine learning. I have 8 years experience in image processing. If PDF API can extract text inside square correcty, proper template matching algorith More

$2200 USD in 3 days
(0 Reviews)
0.0
oikos85

Hi, I’m really interested in your project , I’ve worked on similar projects, converting pdf to word or word to pdf , pdf to excel etc. .I can do the work perfectly and as soon as possible. Friendly

$250 USD in 7 days
(0 Reviews)
0.0
lesteraguilar

Pro PDF/Face Recognition/VB.NET/Image Processing Expert! Hi client. Once saw a your project, it was very attracted my mind because I am very interested in your project and also, have rich experiences and high skills o More

$750 USD in 7 days
(0 Reviews)
0.0
genius1226

Dear sir. Your project attracted my attention at first glance, because I've extensive experience in Shape Recognition Programming. I'm really confident about your project, and very eager to join your project. If we hav More

$300 USD in 7 days
(0 Reviews)
0.0
wewe80

dear sir i have similar project in the past using vb.net for ocr using tessseract. for 100% object scanning is difficult, but i can teach the tesseract customizing for your document (i need a lot of sample from your More

$444 USD in 14 days
(0 Reviews)
0.0
MedaniAhmed

Hi there.. I have just seen your posted project... In my thinking.. This could he handled with a moving classifier like using an ANN with cropped symbols then let algorithm scan the image and perform classification More

$250 USD in 20 days
(0 Reviews)
0.0
BenHaughian

I have used both of your examples and created a tool that can extract the text. if you give me a few more examples i can fine tune the parameters. i can get this done by tomorrow. message me so i can show you. Thank Y More

$277 USD in 2 days
(1 Review)
0.0