孟加拉语（孟加拉）语言OCR预处理器

Drirupa (দৃরূপা) **Bangla(Bengali)** Language pre-processor to process scan image and prepare for **OCR** conversion. In the Bangla(Bengali) language written and printed system, alphabets are consecutively connected with a line called "matra" in most of the word. So, Operation of an Optical Character Recognition (OCR) on Bangla(Bangali) language is different from other languages. To make the **Bangla (Bengali)** OCR preprocessor we divide our system into four(4) parts. Those are: Image Detection (Conversion of scan image to black and white) Line Detection Word Detection Alphabet Detection | | | |:----------------------------------------------

drirupa-0.2
.deps
autom4te.cache
script
alphabetProcess
lineProcess
preProcess
wordProcess
ChangeLog
configure.ac
configure.scan
config.status
config.log
missing
install-sh
Makefile.in
COPYING
INSTALL
NEWS
README
configure
AUTHORS
autoscan.log
aclocal.m4