×
Menu
Index

3.2.12.1. Language Detection

 
Language Detection tries to automatically determine the language of the document.
 
The results are stored in the system fields:
 
At document level:
 
sys_lang_code1      -> first language code detected for first page.
sys_lang_name1     -> first language name detected (in English) for first page.
sys_lang_con1     -> confidence of the result for first page.
 
Also sys_lang_code2 & sys_lang_code3 fields are added with the second and third languages detected.
 
At page level it is added on the same fields:
 
sys_lang_code[1..3]      -> first language code detected.
sys_lang_name1[1..3]     -> first language name detected (in English).
sys_lang_con1[1..3]     -> confidence of the result.
 
IMPORTANT NOTE: The language charset should be activated on the OCR engine in order to be detected.