Questions tagged [ocr]
Questions relating to optical character recognition (OCR) software.
153
questions
0
votes
0answers
7 views
Automatically sort/OCR images in a folder Mac, for personal use
What I'm looking for:
A image/document manager thats easy to install and maintain for personal use on a Mac/OSX.
The Problem:
Like many, I have a whole bunch of image/media files- JPG, videos, PDF in ...
2
votes
0answers
13 views
Convert diagrams to graph data
There are some publicly available PDFs and image files of diagrams showing UK rail track layout (basically flow charts), which I want to parse to something more computer-friendly (a database perhaps, ...
0
votes
0answers
17 views
Software or services to extract data from already-filled IRS 1040 tax form PDF
Looking for software or services that will take as input already-completed 1040 return PDF files (ideally with full schedules etc) and output the numerical values taken from the return.
What software ...
0
votes
1answer
38 views
.NET library for scanning documents to searchable PDF's (with barcode support)
I have a requirement to develop an application that can scan documents and produce searchable PDF's that can be previewed from a desktop application (e.g. WPF) or a web browser. Also ability to scan a ...
0
votes
0answers
8 views
What can recognise handwritten check marks and notes on a survey questionnaire?
I have some questionnaires that are manually filled. Its couple of multiple choice questions & one of the MCQ has a comment section.
People have just scratched (big & small ticks, crossing, ...
1
vote
0answers
15 views
OCR software with automatic translation
I'm looking for an application that will allow me to swiftly select a portion of my screen, (like the snipping tool does) preferably by hotkey, and then return me the text translated to English.
...
0
votes
0answers
20 views
Searching for OCR that works well with non Latin characters(mainly Hebrew and Arabic)
Is there any good Hebrew OCR API/library (preferably free but not necessary)
the text is printed so no need for hand-writing
An Example for an image I want to parse
The Program language is non-...
1
vote
2answers
34 views
Tools to read human written text from a scanned page
What would be the best/most accurate way to read human writing from a scanned document and convert it into text?
0
votes
1answer
23 views
Application to recognize text in PDF files and images(OCR) for Windows
The problem: PDF files and images from a scanned paper document contain text that cannot be copied or edited. However, manual typing is not possible due to the size of the document and the high time ...
0
votes
0answers
82 views
Software for manual PDF OCR
Is there a software where you can import or directly scan pictures and manually add searchable keywords to it?
The use case would by scanning handwritten notes and then labeling the headings, such ...
0
votes
0answers
30 views
Optical Music Recognition using neural networks
A friend is transcribing a lot of handwritten music scores into Lilypond and I
went looking for a better way. It would need 90-95% accuracy so the full process
with verification and manual corrections ...
1
vote
1answer
231 views
Python & PDF parsing: any modern, powerful, well-maintained open-source libraries out there?
I'm looking for well-maintained and well-documented powerful PDF parsing libraries for Python (mainly to extract and parse data from various types of PDFs with different/unpredictable structures, ...
0
votes
0answers
8 views
Ready-made Python library for edge detection + warp transform for OCR purpose?
I'm looking to do something like this, basically from an image, find edge of the paper, and transform it so that it becomes rectangle and more readable... similar to phone scanner apps. I intend to ...
1
vote
0answers
11 views
Is there a tool to optically extract a valid UML from the Image of a UML ? (objects, relationships, etc.)
I was searching for this too. I found mention of three tools but none seem available for public use or downloadable :
1- IMG2UML : https://www.researchgate.net/publication/...
0
votes
0answers
6 views
Machine learning in data extraction
Are there any tools that have “self leaning and auto transformation” capability whereby we can interrogate a client-provided file in it’s native format, identify key data elements, and pull pertinent ...
0
votes
0answers
4 views
Tools that can do AI based document-data-extraction
I have a requirement for an “auto transformation” capability whereby we can interrogate a client-provided file in it’s native format, identify key data elements, and pull pertinent content into a ...
1
vote
0answers
33 views
CamScanner alternative? [Android]
Recently CamScanner has become annoying with ads and popups. So looking for an alternative document scanner on Android, hopefully with these features:
Anti-shake (what I really liked on CamScanner: ...
0
votes
2answers
34 views
Which software to use for PDF scanning that can extract information and send to an invoiceprogram?
I'm working as an intern at a company where they need accurate scanning of invoices that comes in PDF-forms. The program, or java-library, needs to be able to extract certain parts of the invoice so ...
0
votes
0answers
22 views
Open Source Libraries for OCR which gives output files as text, pdf, excel, vcf format
I am looking for an cross platform ocr library and my requirement is to parse the scanned images and extract the text in to txt,pdf,xls and vcf format files. I have used tesseract ocr to extract the ...
0
votes
0answers
8 views
OCR reader for batch of images
I have a batch of screenshots from my favourite radio station, Primoridal Radio on my android phone. These images are saved in google photos. These contain the name of the song and artist.
note: ...
0
votes
0answers
11 views
Extracting digits from an image and processing them
I work in a biology lab. Whenever we go out on the field, we start collecting data on notepads using some form of writing utensil. It's usually a large matrix I fill up with numbers. Probably the most ...
0
votes
0answers
5 views
Softwear to detect vertex of cells on grid table for java
I wonder which library or softwear is proper to detecting vertex of cells on grid table image.
Please refer to the picture below.
I want to know each position (x,y or value for distinguish each cells)....
2
votes
1answer
304 views
Free OCR command line application for Windows that can add invisible-text layer to PDF?
I have seen other similar posts, but none with these specific requests:
OCR application that can be run from the command line
Windows native application
Accepts multipage PDF inputs
Can create a PDF ...
0
votes
0answers
12 views
Open-source multilingual OCR/ICR library?
I am looking for an open-source multi-lingual OCR/ICR library. This is intended for use in low-resourced and low-connectivity environments, primarily with form-based data. Primary languages are ...
0
votes
0answers
18 views
What OCR can i use to extract text from images for multiple languages (all European languages)? Open source software is preferred
Input is in image format(.jpg and .png) and output is in text format. Preferred language for coding is python.
0
votes
0answers
11 views
Document scanning and evaluation framework
Is there any open source or proprietary solution that helps scanning documents, evaluate them and store the results in a database?
Scanning: Scan documents into an image or pdf file. The documents I ...
1
vote
0answers
28 views
Python library to remove handwritten signature
I'm looking for a recommendation for Python libraries to remove handwritten signatures from a document. My use case: document has a number of fields with typed text and one with a handwritten ...
1
vote
1answer
19 views
Looking for a OCR Library in WinForm
Is there any free/paid OCR library that able to capture the invoices data in PDF format?
Need to have a low error rate.
We need to take those data and do some further processing.
1
vote
1answer
33 views
Looking for a library that extracts text from images
The basic description for what I'm looking for is something that can extract text (written by hand) from an image and return it as a plain character stream, without any page processing.
More ...
1
vote
0answers
125 views
Free API for handwritten OCR (Optical Character Recognition)
I wanted to know if there are any free APIs available for text recognition from a handwritten document. I looked in Google Vision API, Microsoft Cognitive API but all of the above are paid. So is it ...
1
vote
1answer
27 views
Which software or API is best for extracting information from PDF and save to excel?
In my project there are lots of use of purchase order and sales order.
So, I have to enter data manually. So, is there any software and API of project that directly take PDF and give output in excel ...
0
votes
0answers
11 views
OCR with data recognition and organization
I have tons of pictures of patient exams documents of which I need to extract the patient number and exam type and write it into and excel sheet, but this process is very time consuming, is there any ...
0
votes
0answers
5 views
Software that automatically deletes all text from photos
I am looking for software, preferably for Linux (Windows if no other choice) that can automatically identify and then remove(delete) all text from photos.
0
votes
0answers
23 views
I am looking for adobe acrobat pro alternative with OCR support?
I'm looking for a free software that has a similar OCR feature to that of adobe acrobat pro, so that I can convert a PDF with embedded fonts into a searchable PDF.
0
votes
0answers
82 views
Extracting user details from Driver's Licenses Image file as key,value pairs
User will upload front side image of US drivers license(png,jpg,pdf) on java web application. I have to extract the driver license number,date of birth, expiry date of license, issue date of license ...
1
vote
0answers
13 views
Should I use the Google Vision API or an OCR package from npm?
I'm just wondering what the best option is for my project:
A mobile app that rates how healthy a user's food is. It works by looking at the image the user took for text detection. I'm fairly new to ...
0
votes
4answers
183 views
Fastest way to batch/mass convert PDFs to searchable text? (thousands)
I was wondering if anyone has any software recommendations to mass OCR about 1000 PDF files. It could be; converting to text, to word Doc or making the PDF searchable. I just need an efficient way to ...
0
votes
1answer
25 views
Is there such a thing as OCR for detecting form fields?
Trying to automate a system here, either through off-the-shelf or roll-your-own solutions: how to take a PDF form (e.g. membership, taxes, etc.) and detect fields? Preferably along withe the label(s), ...
0
votes
0answers
9 views
Software to raise the definition of text in a bitmap image
I have a screenshot taken from facebook and if it prints blurred because the DPI resolution of the monitor is very low compared to the printer resolution.
I'm looking for a software which can upscale ...
0
votes
0answers
13 views
Looking for a software to rename pdf's using OCR content
I scan all my files into a scanner folder,
they get the name "Scan001;Scan002;Scan003" ...you get the idea.
Then after couple months i have to stop for a day or something, go one by one and check ...
0
votes
0answers
31 views
OCR Software with Filename
I have a project in which we need to scan a lot of documents. Currently, I´m using Kodak Alaris Capture Pro, but it´s quite expensive
Basically, the OCR software identifying the ID Number from each ...
2
votes
0answers
39 views
Linux OCR for handwritten, colored backgrounds, math, columns, tables
In my application I want to build one optical character recognition system which can extract characters from image and input it into text file ?
Till now I have used pytesseract and OpenCV for this ...
0
votes
1answer
49 views
I need tools to build boat license plate Recognition [ image processing ]
My Requirement Need to bulid License Plate Recognition from Boat
Like my Src Video : https://www.youtube.com/watch?v=DzpZ-kNFMtw
can you help me... please
2
votes
0answers
30 views
OCR Deep Learning Software
I have a question about a possible software solution for a problem. I work in a very busy psychiatric private practice that handles large amounts of paperwork. We would like to create a more efficient ...
2
votes
1answer
43 views
Text Recognition API
I am working on dictionary App for Android and iOS. Where I want to have feature like place the camera on word and app will recognize the word and will show the meaning of that word.
For example or ...
0
votes
1answer
69 views
Mobile Zonal OCR document scanner in offline
I am looking for a mobile sdk which can be capture and process a document using zonal OCR, would return a value which is part of a predefined area in an document in offline.
I have gone through some ...
0
votes
2answers
71 views
Software or method to batch invert b/w images
I have directories of 100-500 small black & white image files (jpg) that I need to batch invert, from white text on black to black text on white. They will then be input to tesseract-ocr.
I am ...
1
vote
0answers
25 views
Camera OCR as input method for Android
Perhaps as an alternate keyboard, or some kind of floating button, expose a quick & ready method to begin inputting text into current active cursor from an OCR scan from the camera. There would ...
3
votes
3answers
1k views
Software to batch OCR multiple image files to multiple text files using Tesseract?
I am currently using tesseract to OCR some jpeg files to txt files (Ubuntu 16.04). Typically this is ~500 files in one directory.
I know I can do this by making a text file with all the file names (...
2
votes
0answers
56 views
Is there an OCR solution for monospace text that preserves indentation and number or spaces (such as in source code)?
I have a pile of printed out source code and need to convert it into ascii-files. I believe, I should be able to do this with OCR, however, as far as I can see, they don't preserve neither amount of ...
