The blog post and source code refer to an older algorithm than the one in the demo. Currently it is using a convolutional network for prediction not dissimilar to [1] or [2]. I'm writing a paper about it, if there is interest I'll put it online :) .
Thank you for the feedback on incorrectly identified characters! The algorithm is not quite perfect - 70% accuracy on a randomly chosen test set.
Also, it incorrectly identified two characters on the demo for me: http://a.pomf.se/pykdwz.png
Source: https://github.com/alexisVallet/anime-character-detection it seems