Language identification of on-line documents using word shapes

We have extended existing methods to identify the language of an on-line document after the characters have been coded using 10 character classes based on visual characteristics, In particular, we exploit word bigrams and trigrams in both a linear combination of score values and an expert systems approach. Knowledge about each language is acquired from a large number of on-line texts. Using a small set of rules, the expert system outperforms the linear combination in accuracy and shows more stability when parameter settings are varied.