Questions tagged [ocr]

Optical character recognition, usually abbreviated to OCR, is the mechanical or electronic translation of scanned images of handwritten, typewritten or printed text into machine-encoded text.

Filter by
Sorted by
Tagged with
9
votes
1answer
2k views

How can you build a model that extracts data out from receipts?

I'm trying to build a model that is capable of identifying information on receipts and invoices. I have used google cloud vision api for text extraction from the receipt but the problem is it just ...
8
votes
1answer
3k views

How can you build a model that reads out receipts and invoices?

The objective is to build a model that is capable of identifying information on receipts and invoices that can look completely different. I've had a discussion with my brother about the right ...
6
votes
2answers
2k views

Document Layout Analysis - state-of-the-art?

What is the current state-of-the art within document layout analysis? I.e. detecting columns, separating images from text, distinguishing between page numbering and text and so on. I am looking for ...
6
votes
1answer
2k views

How to pass features extracted using CNN into RNN?

I have word images as below: Let's say it's a 256x64 image. My aim is to extract the text from the image as 73791096754314441539...
6
votes
1answer
117 views

Can I train two stacked models end-to-end on different resolutions?

Is it possible to stack two networks on top of each other that operate on different resolutions of input data? So here's my usecase: like Google, I want to recognize text in images. Unlike Google, I ...
5
votes
1answer
4k views

Pretrained handwritten OCR model

I've been looking around for pretrained models dedicated to handwritten OCR. So far I've found very little. Could you please share, if you know any? I find tesseract...
4
votes
1answer
181 views

Fake News Detection problem

I would like to work on a project for Fake News Detection especially for Indians news which are in different languages and different formats. Fake news as image with no or very less text Fake news on ...
4
votes
2answers
8k views

how can I solve label shape problem in tensorflow when using one-hot encoding?

I used tensorflow to recognize text from natural images by using convolutional neural network; there is no specific number of characters in the text. To make a successful training I should convert the ...
4
votes
1answer
155 views

what is the loss function in char recognition using Tensorflow?

I have code in Tensorflow using convolution neural network to recognize the characters in street view Text (SVT) data. Since the label type is string, what should I use instead of ...
4
votes
1answer
315 views

What is representation in optical character recognition?

I am learning OCR and reading this book The authors define 8 processes to implement OCR that follow one by one (2 after 1, 3 after 2 etc): Optical scanning Location segmentation Pre-processing ...
4
votes
2answers
2k views

What is the best approach for specified optical character recognition?

I have a quite understandable request of extracting information (invoice number, invoice data, due date, total etc.) from scanned invoices (the digital format is image, not PDF), preferably in Python. ...
3
votes
1answer
49 views

How to segment old digitized newspapers into articles

I'm working on a large corpus of french daily newspapers from the 19th century that have been digitized and where the data are in the form of raw OCR text files (one text file per day). In terms of ...
2
votes
1answer
4k views

How to improve OCR (Scanning) results?"

Below is text output obtained after ocr image to string of medical discharge summary report. ...
2
votes
1answer
610 views

Machine learning algorithm which gives multiple outputs from single input

I need some help, i am working on a problem where i have the OCR of an image of an invoice and i want to extract certain data from it like invoice number, amount, date etc which is all present within ...
2
votes
1answer
93 views

What model to use for matching two datasets

I've got 500 images of paper receipts scanned and OCR as one dataset. I also have a dataset of transactions from my credit card statement including amount and date. What model is best to match the ...
2
votes
0answers
34 views

Entity Linking for Receipts [closed]

I am building a model for reading receipts from their mobile snapshots. After the receipt is OCR'd, I plan to use a variation on LayoutLM for entity extraction. Entities are: "quantity", &...
2
votes
0answers
85 views

What is the difference between ICR and OCR?

I've just found the term "Intelligent Character Recognition" (ICR) on Wikipedia and other pages. According to Wikipedia: In computer science, intelligent character recognition (ICR) is an ...
2
votes
1answer
47 views

Does CRNN use sparse tensor value for its label?

I just read paper about cnn + rnn for text recognition. The labels of dataset is tensor of char index (e.g [0, 1, 2 ] for image with label "abc"). Since the label of each input has different length ...
2
votes
0answers
341 views

OCR in book spines

I'm experimenting with OCR on book spines, as a way of cataloguing books which are on shelves without the tedium of taking out each one and scanning a barcode. I need a way to tell if I have ...
1
vote
1answer
53 views

Evaluating information extraction from structured documents

I'm trying to find metrics to evaluate multiple algorithms for key information extraction from already OCRed invoices. For instance, such an algorithm, given an invoice, could find that: ...
1
vote
1answer
103 views

optical chemical structure recognition from images

I want to recognize name of the chemical structure from the image of chemical structure, like in the given image it is benzene structure I want to recognize that it is benzene from the image(I should ...
1
vote
1answer
724 views

Extract text from a image - OCR

This is the first time I am working with OCR. I have an image and want to extract data from the image. My image looks like this: I want to extract the parameters and the values against them. Can ...
1
vote
1answer
142 views

Extracting text from few areas on product label

I'm trying to achieve algorithm that will extract text from few areas(marked with red color) on label(similar to attached image) and QR code on a single photo taken with mobile camera so label may be ...
1
vote
1answer
124 views

How can I split an image into rectangles?

I have a labelled form to which people will add their name and a series of numbers. They will then take a picture of the form. Like so: I can get decent results by simply sending this to AWS ...
1
vote
1answer
3k views

High, constant training loss with CNN

I try to solve a multi-character handwriting problem with CNN and I encounter with the problem that both training loss (~125.0) and validation loss (~130.0) are high and don't decrease. I use the ...
1
vote
0answers
12 views

Are there any publicly available scan document database containing text together with ticked/unticked checkboxes?

I would like to train an optical mark recognition model (OMR) to detect and classify the ticked/unticked state of checkboxes in documents. Does anyone know where I can have access to a publicly ...
1
vote
0answers
29 views

How Does EAST detector implementation with VGG16 look? How many outputs does it have?

I was reading the Efficient and Accurate Scene Text Detector paper and saw the author reference VGG-16 as a possible stem "feature extractor" network. In the paper they say: In our ...
1
vote
0answers
646 views

What is the best approach to extract keys/values from documents?

I am thinking of training a model to automatically extract information from more or less structured documents like invoices. Here are the main challenges regarding this task: In fact, even though ...
1
vote
0answers
52 views

Create a model that can extract only specific data out of receipts or invoices?

I'm trying to build a model that is capable of identifying only some of the information on receipts and invoices. All the documents having different structure in image format. Sample Data : Click here ...
1
vote
0answers
25 views

Is there any research on zonal OCR / field level ORC / template OCR?

I've recently found the term "Zonal OCR": (source 1, 2, 3, 4). It seems to be essentially OCR, but restricted to relevant parts of the document. The interesting task about which I want to ...
1
vote
0answers
28 views

Possible?: Split pdf file on pages where object detection algorithm finds custom object

I have scanned documents in large pdf files consisting of many individual documents. Each document begins with a exhibit number sticker, much like this one: example. The files are scanned in greyscale....
1
vote
0answers
32 views

Extracting document templates from similar documents

Using very basic techniques (zone segmentation + OPTICS) I was able to organize a set of around 10^4 business documents (invoices, receipts) into hierarchy of clusters of documents of similar layout. ...
1
vote
0answers
403 views

how to resize image without changing DPI in opencv for detecting text and feeding into OCR?

i resized the image using open cv and it changed the dpi of the image from 300 dpi to 90 dpi . What is the correct way to resize image without changing its dpi in open cv . if we feed the resized ...
1
vote
0answers
3k views

how to resolve this error in Tesseract : (2, 'Usage: pytesseract [-l lang] input_file') [closed]

pytesseract.pytesseract.tesseract_cmd = r'/usr/local/bin/pytesseract' img = Image.open("/content/drive/My Drive/abc.jpg") print(pytesseract.image_to_string(img)) ...
1
vote
0answers
9 views

detect diagram region in research papers

How can I detect diagram region and extract it from a research paper
1
vote
1answer
89 views

Classifying Letters using CNN - Help

so some context, I'm trying to develop an OCR (for fun) and for that reason I decided to first find text within a page, parse it in to letters within the text and from there try and classify the ...
1
vote
0answers
32 views

Best OCR approach on documents with different formats to find one specific information

Unfortunately, because of confidential data, I can't give a more specific explanation. The Problem So I've got a few documents that in general contain the same information but have different formats....
1
vote
0answers
504 views

Character segmentation using deep learning

I'm developing a character segmentation algorithm for license plate OCR. My algorithm includes two steps: segmentation and recognition. There is almost no problem for recognition thanks to CNN. My ...
1
vote
1answer
1k views

Reading meters with tensorflow

I'm new to ML world and been reading about ML and TensorFlow. My goal is to read the following example in real time with Android phone: So I tried firebase ML OCR and it works really good, it reads ...
1
vote
0answers
40 views

How to approach training a machine to read a form

After many rewrites I'm still not entirely thrilled with how I've presented this.... please delete if inappropriate. Background As part of my job, we record observations on underwater paper and then ...
1
vote
0answers
115 views

OCR on striked-out text

I have the following image with me: I want to identify the text, which is the amount mentioned at the bottom of the table. However, the bottom edge of the table goes through the text in this case. ...
1
vote
0answers
78 views

How to segment a scanned Page so that it can be fed into an OCR [closed]

I have an OCR that can read a given character. Now I want to build something that can take a scanned document and convert it into text. The problem is how do I segment each character? I know this can ...
0
votes
2answers
38 views

how can i detect medicine name and info(use and contents) by using medicine wrappers

I got one project idea creating a Cross-platform react-native app the project title is creating an app that can detect medicine name and other info from the medicine wrapper I'm thinking of using ...
0
votes
2answers
148 views

How to detect medicine name from the medicine wrapper

I have got medicine wrapper ( Packaging ) of different medicines. I want to detect medicine name out of it. I'm using Google Cloud Vision to extract all the text from the medicine wrapper. Text ...
0
votes
1answer
59 views

License Plate OCR

Are there any pretrained models or annotated data available for license plate detection? I've seen some sets but most of them are little in size. I'm more interested in prod-like quality. Are there ...
0
votes
1answer
547 views

How to create a model to recognize matching label and ROI with OCR

I am trying to make a model in python using Tensorflow to process the Tesseract OCR to detecting and extracting particular ROI from Image. I want to recognize the particular fields and values from ...
0
votes
1answer
47 views

training neural nets for OCR

we are trying to build an in house OCR system to extract alphanumeric strings from images (kindly note, most of our clients cant afford to send their data onto the cloud so it rules out any API from ...
0
votes
1answer
25 views

LSTM layer (keras) is causing all layers after it to constantly predict the same thing no matter the input

I have a model for OCR, which after 2-3 epochs gives the same output. When I predicted the values and looked at the output for each layer I realized that all layers after the 1st layer in the LSTM ...
0
votes
0answers
12 views

No gradients provided for any variable, when using Lambda to round model output

I have a problem where I need to predict some integers from an image. The problem is that this includes some negative integers too. I have done some reasearch and came accross Poisson which does count ...