3

I am trying to read the handwritten documents. For which I am going to segment the characters and then OCR/ICR the characters thus segmented.

I want results like this! Although this is a very trivial case. The handwriting may be cursive, the single stroke can be used to segment characters but it doesn't always work.

enter image description here

Cœur
  • 37,241
  • 25
  • 195
  • 267
amor.fati95
  • 119
  • 1
  • 11

1 Answers1

2

After a lot of reading and researching, realized that I was tackling the problem in a wrong way. For Handwriting recognition it's tough to segment characters and then recognize them.

As the paradox goes

A letter can't be segmented before having recognized and can't be recognized before having segmented.

So the correct way is to treat the problem as "Supervised Sequence Labelling". What distinguishes such problems from the traditional framework of supervised pattern classication is that the individual data points cannot be assumed to be independent. Instead, both the inputs and the labels form strongly correlated sequences.

I would suggest the paper here using Multi Dimensional RNN and CTC.

amor.fati95
  • 119
  • 1
  • 11