Questions tagged [optical-character-recognition]

Optical character recognition (also optical character reader, OCR) is the mechanical or electronic conversion of images of typed, handwritten or printed text into machine-encoded text, whether from a scanned document, a photo of a document, a scene-photo (for example the text on signs and billboards in a landscape photo) or from subtitle text superimposed on an image (for example from a television broadcast).

Filter by
Sorted by
Tagged with
0 votes
0 answers
12 views

How can I apply ensemble voting to multiple OCR results

I have to OCR some text, it is some laser engraved characters on leather. As the well known OCR frameworks tend to make mistakes I decided to use them all then make an ensemble using there results. ...
2 votes
1 answer
25 views

Image Clustering (Unsupervised learning) on unknow class(guess less than 300)

I have 30000 unlabeled images (each image has only one character), and the content of the images is very simple, basically black lines(a language but not English) and white background. I hope to use ...
0 votes
1 answer
108 views

How to compare two texts with different order of words?

I have two texts, one ground truth and one OCR result, and I want to measure to what accuracy the result matches the ground truth. But since the text source is non-linear, both texts have a different ...
1 vote
0 answers
26 views

If I know specific pair of characters that model confuses in OCR task how can I fixe it?

I train OCR model to recognize cyrillic handwritten text. I know, for example, that it confuses very often 'Б' with '6'. How can I use this information to fine tune the model ? Just in case, my ...
0 votes
0 answers
36 views

What is the best structure (Accuracy of the text extracted) for building an OCR? ATTENTION, CRNNN, DRAM,RAM, CTC based

If I want to make a new OCR for extracting text from textbooks, specially maths and chemistry, what should be the structure for the OCR? THERE ARE LOT OF TUTORIALS around the internet but no one ...
  • 234
1 vote
1 answer
38 views

Incorrect predictions on extracted images from text [closed]

I trained a model in PyTorch on the EMNIST data set - and got about 85% accuracy on the test set. Now, I have an image of handwritten text from which I have extracted individual letters, but I'm ...
9 votes
1 answer
938 views

Can deep learning determine if two samples of handwriting are by the same person?

I have dabbled using Tesseract CNN OCR on handwriting records before and was surprised by the accuracy. I am wondering, is it possible to use it, or something else, to determine if a sample of ...
0 votes
1 answer
110 views

ML model for text detection similar to object detection?

I'm n00b to ML and am looking for a text detection model which could tell me a box of pixels has X% possibility to be a word ABC, very similar to common object detection models like these. I searched ...
  • 3
2 votes
0 answers
120 views

Avoiding OCR performance coupling to upstream Bounding Box model

I have a model pipeline where I first use an object detection deep learning model to locate text regions in images of natural scenery (i.e. outdoor images), and then send the cropped region to a deep ...
  • 21
4 votes
1 answer
2k views

Is CTC Loss function right for License Plate Recognition?

I trained some CNN model for license plate recognition using stacked LSTM and convolutional layers, but I got stuck in %88 accuracy. (This accuracy is on the whole license plate not one character). ...
  • 225
1 vote
1 answer
570 views

What NN architecture to use for documents OCR?

I recently go interested in document OCR and would like to gather some opinions on what NN to use. I wonder if there are any proven examples that I can exploit? I have heard of CNN+LSTM+CTC is good ...
1 vote
0 answers
320 views

An algorithm to read handwriting from checks

I've noticed that ATM machines have become very good at reading handwriting on checks. I would like to write a program (using some appropriate machine learning or computer vision library) that is ...
  • 510
2 votes
2 answers
2k views

KNN outperforms CNN

Disclaimer: I am a programmer by trade, not a statistician, so please cater to my ignorance when explaining things and I apologize now if I make any incorrect assumptions Please consider the ...
  • 165
1 vote
0 answers
72 views

Recognizing several digits in an image - CNN

I am attempting to build a convolution neural network that will learn to classify images that contain up to three digits. I am currently building my training labels with the following format: For ...
  • 165
2 votes
0 answers
54 views

Simple OCR over individual words from a fixed dictionary

I have a series of images, each containing a single word from a known dictionary of 2048 words. The size, font, and position of the word is known ahead of time, and I simply need to tell which word ...
1 vote
1 answer
793 views

Automatically determine whether a form filled in by hand and then scanned is valid

I'd like to automatically determine whether a form which is filled in by hand and then scanned or photographed is "valid". To be considered valid, the form has to satisfy the following two criteria: ...
3 votes
1 answer
879 views

Can CNN detect text in arbitrary position of image?

My task is that: there are some text in some position (left, right, top, bottom center, etc) of an images. The style (include size, orientation, font, etc) of text is arbitrary and the content length ...
  • 293
4 votes
0 answers
416 views

Train Neural Network For Handwritten Chinese Characters

The article here: http://novanoid.github.io/2014/09/26/training-a-neural-network-to-recognize-handwritten-digits/ discusses and implements a way to recognize handwritten digits. For images with a ...
  • 141
1 vote
0 answers
31 views

Normalizing features that represent the same thing

I'm working through the beginner exercise of classifying the MNIST dataset (recognizing hand written digits). If I train with 80% of the dataset, then test the remaining 20% of the samples, I get ~90% ...
15 votes
3 answers
2k views

State-of-the-art ensemble learning algorithm in pattern recognition tasks?

The structure of this question is as follows: at first, I provide the concept of ensemble learning, further I provide a list of pattern recognition tasks, then I give examples of ensemble learning ...
4 votes
1 answer
207 views

How many samples do I need for OCR problems?

I am thinking about collecting samples of hand written digits (0 to 9) from people. I'll try to test different algorithms for optimal character recognition- some form of neural network and random ...
  • 3,395
0 votes
3 answers
926 views

SVM Classifier with HOG Features

I am interested in having a system to detect and recognize speed limits from traffic signs. The detection part works fine, meaning that I am able to detect them inside any image. Now I would like to ...
  • 21
3 votes
0 answers
107 views

How is prior knowledge of letter/word patterns incorporated into handwriting (or speech) recognition?

Using handwriting recognition as an example, we can train various models to recognise individual characters but to actually be useful we must incorporate prior knowledge of common character sequences, ...
  • 169
2 votes
2 answers
621 views

How to remove horizontal bar in Hindi word Matlab

I wish to remove the horizontal bar (Shirorekha) from the word to get characters from the following image, for character recognition. Any ideas as to how can I do that. I tried to use Hough ...
3 votes
0 answers
104 views

How can you use HMMs and ANNs for on-line handwriting recognition?

I've asked this question on cs.stackexchange before. It has a 20-hours remaining bounty there. On-line handwriting recognition is the task of converting a series of $(x(t),y(t))$ coordinates to ...
  • 1,527