Classifying Japanese characters from the Edo period

If I understand correctly, the guy downloaded a data set, train it and get happy because it performs over 95% on the training set from the data set.<p>This is not interesting at all because the hard part is to actually segment and classify characters in a real text, and in real life they don’t conveniently come as 28x28 images. As someone with a few hours of training in reading that kind of texts the difficulties are:<p>- taking appart characters (hentaigana) that looks very close<p>- segmenting characters because size and length vary a lot<p>- differentiating between kana and kanji because the former are deritaves of the latter and they sometime look quite alike<p>So the experimenter should have started his post telling he didn’t know any Japanese instead of closing it as such (even if one can notice when he just use modern kana as classes).

The training set contains errors. The に row is especially messy: it&#x27;s full of 小, ふ, and み.

I want to do the same for Chinese.<p>I have a collection of 1500 fonts, and finally exported all the PNGs for 75,000 characters. Now I need to pad, crop, and scale to make 28x28 (or 32x32, or 64x64, or another resolution).<p>Then I want to do the Machine Learning (Classify) step.<p>The article doesn&#x27;t go into any detail about how to install Classify, how to import the training and testing data, and how to then actually run it. I watched the videos from CS231n because of my boss, but again, I&#x27;m still not really sure what to do practically.<p>If I have lots of folders of images, what should I do to build an OCR program?

Anyone know the work he refers to as the inspiration for this article?