Artificial Intelligence Stack Exchange
Artificial Intelligence Stack Exchange

Questions tagged [handwritten-characters]

For questions regarding handwriting recognition

8 questions
4
votes
2 answers

Does this tutorial use normalization the right way?

There is this video on pythonprogramming.net that trains a network on the MNIST handwriting dataset. At ~9:15, the author explains that the data should be normalized. The normalization is done with x_train = tf.keras.utils.normalize(x_train,…
Thomas Weller
  • 221
  • 3
  • 9
3
votes
0 answers

Handwritten digits recognition during the process of writing

I know how to train a NN for recognizing handwritten digits (e.g. using the MNIST database). I'm wondering how to accomplish the same "online", which is during the process of writing e.g. I'm writing down a digit, and during the process and while…
kuma
  • 341
  • 1
  • 9
2
votes
1 answer

How to add variation in the results of a neural networks?

I would like to create a neural network that converts text into handwriting for use with a pen plotter. Before I start on this project, I'd like to be sure that artificial intelligence is the best way to do this. A problem that I foresee with this…
cr5519
  • 23
  • 2
1
vote
2 answers

How to approach this handwritten digit recognition?

I have multiple pictures that look exactly like the one below this text. I'm trying to train CNN to read the digits for me. Problem is isolating the digits. They could be written in any shape, way, and position that person who is writing them wanted…
Igor
  • 77
  • 4
1
vote
0 answers

Can you make the first layer of a net have discernible shapes?

Coming from the YT videos of 3blue1brown which showed that the individual layers do not have discernible shapes in the case of hand written letter recognition, I wondered if you could penalize dispersed shapes while training, thus creating connected…
Chuquicamata
  • 11
  • 1
1
vote
3 answers

Can I use 4 neurons for output layer to classify hand written digit?

Hello world of ANN usually uses MNIST hand written digit data. For classes there are 10, therefore it takes 10 neurons in the output layer, each class is 0 to 9 handwritten digit images. If in the end there is only one active neuron in the output…
Muhammad Ikhwan Perwira
  • 169
  • 6
1
vote
1 answer

What are the challenges for recognising the handwritten characters?

This 2014 article saying that a Chinese team of physicists have trained a quantum computer to recognise handwritten characters. Why did they have to use a quantum computer to do that? Is it just for fun and demonstration, or is it that recognising…
kenorb
  • 10,423
  • 3
  • 43
  • 91
0
votes
1 answer

What are the disadvantages to using a distance metric in character recognition prediction

I am reading this paper, that is discussing the use of distance metrics for character recognition predicton. I can see the advantages of using a distance metrics in predictions like character recognition: You can model a set of known character's…
Slowat_Kela
  • 287
  • 2
  • 9