centos下 安装tesseract4.0详细步骤 及Syntax error near unexpected token `LEPTONICA,'解决

#安装系统依赖

yum install -y automake autoconf libtool gcc gcc-c++ 
yum install -y libpng-devel libjpeg-devel libtiff-devel
yum -y install  python-devel
yum -y install openssl-devel   
yum -y install opencv 
yum -y install  java-1.8.0-openjdk   java-1.8.0-openjdk-devel  
yum install -y libffi libffi-devel

#安装leptonica-1.74.4
http://www.leptonica.org/download.html
wget http://linux-1251121573.cosgz.myqcloud.com/soft/tesseract/leptonica-1.74.4.tar.gz
tar xvzf leptonica-1.74.4.tar.gz
cd leptonica-1.74.4/ 
./configure 
make && make install
cd ..

# 安装auto*之类的依赖，目的是为了autogen.sh调用autoreconf生成configure文件

wget http://linux-1251121573.cosgz.myqcloud.com/soft/tesseract/autoconf-2.69.tar.gz
tar -zxvf autoconf-2.69.tar.gz 
cd autoconf-2.69
./configure
make && make install
cd ..

wget http://linux-1251121573.cosgz.myqcloud.com/soft/tesseract/automake-1.14.tar.gz
tar -zxvf automake-1.14.tar.gz 
cd automake-1.14
./bootstrap.sh
./configure
make && make install
cd ..

wget http://linux-1251121573.cosgz.myqcloud.com/soft/tesseract/autoconf-archive-2018.03.13.tar
xz -d autoconf-archive-2018.03.13.tar.xz
tar xvf autoconf-archive-2018.03.13.tar 
cd autoconf-archive-2018.03.13
./configure
make && make install
cd ..

# 安装glib之类的依赖
wget http://linux-1251121573.cosgz.myqcloud.com/soft/tesseract/pcre-8.40.tar.gz
tar -zvxf pcre-8.40.tar.gz 
cd pcre-8.40
./configure 
make
make install
cd ..

wget http://linux-1251121573.cosgz.myqcloud.com/soft/tesseract/glib-2.56.1.tar
tar xvf glib-2.56.1.tar
cd glib-2.56.1
./configure --enable-libmount=no
make
make install
cd ..

wget http://linux-1251121573.cosgz.myqcloud.com/soft/tesseract/pkg-config-0.29.2.tar.gz
tar -zvxf pkg-config-0.29.2.tar.gz
cd pkg-config-0.29.2
./configure --with-internal-glib
make
make install
cd ..

 

# 安装pkg-config              --- 很多博客没有这一步骤，会报错：Syntax error near unexpected token `LEPTONICA,'，参考https://github.com/tesseract-ocr/tesseract/issues/941

wget  https://pkg-config.freedesktop.org/releases/pkg-config-0.29.tar.gz

tar -zxvf pkg-config-0.29.tar.gz

cd 进入解压文件夹

./configure --with-internal-glib

 make

make install
 

 

# 安装tesseract-ocr4.0

wget http://linux-1251121573.cosgz.myqcloud.com/soft/tesseract/4.0.0-beta.1.tar.gz
tar zxvf 4.0.0-beta.1.tar.gz 
cd tesseract-4.0.0-beta.1
autoreconf -I /usr/local/share/aclocal 
./autogen.sh 
./configure --prefix=$HOME/local/
make
make install

 

vi /etc/profile

添加：

PKG_CONFIG_PATH=$PKG_CONFIG_PATH:/usr/local/leptonica/lib/pkgconfig
export PKG_CONFIG_PATH
CPLUS_INCLUDE_PATH=$CPLUS_INCLUDE_PATH:/usr/local/leptonica/include/leptonica
export CPLUS_INCLUDE_PATH
C_INCLUDE_PATH=$C_INCLUDE_PATH:/usr/local/leptonica/include/leptonica
export C_INCLUDE_PATH
LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/usr/local/leptonica/lib
export LD_LIBRARY_PATH
LIBRARY_PATH=$LIBRARY_PATH:/usr/local/leptonica/lib
export LIBRARY_PATH
LIBLEPT_HEADERSDIR=/usr/local/leptonica/include/leptonica
export LIBLEPT_HEADERSDIR
PATH=$PATH:/usr/local/tesseract/bin
export PATH

运行命令：source /etc/profile

 

# 运行 tesseract提示找不到命令，把/root/local/bin/tesseract文件复制到/usr/bin/目录即可

 

 

下载训练模型并移动到文件夹中：

wget http://linux-1251121573.cosgz.myqcloud.com/soft/tesseract/chi_sim.traineddata
wget http://linux-1251121573.cosgz.myqcloud.com/soft/tesseract/eng.traineddata

mv chi_sim.traineddata eng.traineddata /usr/local/share/tessdata

 

vi ~/.bash_profile

添加：

export TESSDATA_PREFIX=/usr/local/share/tessdata/   

运行命令：source ~/.bash_profile