yundaxian / loov Goto Github PK

###########################################################################
Copyright (C) <2014>  <Johann POIGNANT>

This file is part of LOOV.

LOOV is free software: you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation, either version 3 of the License, or
(at your option) any later version.

LOOV is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
GNU General Public License for more details.

You should have received a copy of the GNU General Public License
along with LOOV.  If not, see <http://www.gnu.org/licenses/>.
###########################################################################

## You must cite ICME 2012 paper in all publications which use LOOV:

Johann Poignant, Laurent Besacier, Georges Quénot, Franck Thollard 
From text detection in videos to person identification
ICME, july 2012, Australia, Melbourne. 


## Typical installation for ubuntu 12.04, you probably have to change this installation and the makefile to adapt to your distrib/version

## install pre-requires
sudo apt-get install cmake autoconf automake libtool

## Install opencv
sudo apt-get install libavcodec-extra-53 libopencv-dev libcv-dev libhighgui-dev

## Install leptonica 1.70 or earlier
wget http://www.leptonica.org/source/leptonica-1.70.tar.gz
tar -zxvf leptonica-1.70.tar.gz
cd leptonica-1.70
./configure
make
sudo make install
cd ..

## Install local version of Tesseract
#from LigOverlaidOCRinVideo folder:
wget "http://tesseract-ocr.googlecode.com/files/tesseract-3.00.tar.gz"
tar -xf "tesseract-3.00.tar.gz"
cd "tesseract-3.00"
./configure
make -j3
sudo make install
sudo cp -d */.libs/*.a /usr/local/lib/
cd ..

## Copy model language (lang.traineddata) in the folder /usr/local/share/tessdata from http://code.google.com/p/tesseract-ocr/downloads/list

# combination tools 
install srilm from http://www.speech.sri.com/projects/srilm/
comb_output_LOOV.py is a python script that used lattice-tool and nbest-lattice binary to combine multiple transcription from LOOV output

## Compile LOOV
mkdir build
cd build
cmake ..
make

./LOOV -v path_to_video