I am trying to learn more about text-independent writer identification and was hoping for some advice.

I have a folder with 100k images, each of them with a different handwritten sentence. All of the images have sentences of different lengths. They range from about 30 to 80 English characters. The file names start at 1.png and go up to 100k.png. That's it, as far as input data. 95% of the sentences are written by different writers. 5% are written by the same writers. Some writers might have written 2 sentences, while others 300+.

Does anyone know of an identification method that would be able to determine what images were written by the same writer?

I know that most methods require each writer to have provided a full page of sample writing for training, but, of course, I do not have that.

  • $\begingroup$ I have edited your post to clarify it. Make sure that I did not change the meaning of your sentences. $\endgroup$
    – nbro
    Commented Jul 13, 2020 at 20:02
  • $\begingroup$ Is the data labeled, i.e. do you know which sentence has been produced by which writer? If so, I'd start out training a Recurrent Neural Network, which is specialized on working with sequence data. $\endgroup$
    – Daniel B.
    Commented Jul 15, 2020 at 21:09


You must log in to answer this question.