The following extended attributes are written:
-
whether the character is the first character in a word,
-
whether the word is found in the dictionary,
-
whether the word is recognized with either a standard or user-defined language, and that it is not a number or an identifier,
-
whether the word is a number,
-
whether the word is an identifier,
-
probability that a character is written with a Serif font,
-
penalty for discordance of characters in a word,
-
the mean width of stroke in the RLE representation of a word image.