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
1 vote
1 answer
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 ...
user avatar
  • 113
2 votes
1 answer
53 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 ...
user avatar
1 vote
1 answer
203 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 ...
user avatar
  • 111
2 votes
0 answers
388 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 ...
user avatar
1 vote
0 answers
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 ...
user avatar
1 vote
0 answers
122 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. ...
user avatar
  • 8,036
2 votes
1 answer
666 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 ...
user avatar
1 vote
1 answer
180 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 ...
user avatar
8 votes
1 answer
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 ...
user avatar
  • 181
1 vote
1 answer
4k 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 ...
user avatar
  • 7,947
6 votes
1 answer
143 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 ...
user avatar
2 votes
1 answer
95 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 ...
user avatar
  • 121
1 vote
0 answers
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 ...
user avatar
  • 63
4 votes
2 answers
9k 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 ...
user avatar
  • 85
4 votes
1 answer
176 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 ...
user avatar
  • 85
2 votes
1 answer
4k views

How to improve OCR (Scanning) results?"

Below is text output obtained after ocr image to string of medical discharge summary report. ...
user avatar
  • 91
6 votes
1 answer
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...
user avatar
  • 207
4 votes
1 answer
334 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 ...
user avatar
  • 41
6 votes
2 answers
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 ...
user avatar
  • 211
4 votes
2 answers
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. ...
user avatar
  • 7,947

1
2