CentOS系统下安装tesseract-ocr5.x版本
1.安装依赖包
yum update -y
yum install autoconf automake libtool libjpeg-devel libpng-devel libtiff-devel zlib-devel
yum install automake libtool bzip2 -y
2. GCC版本升级
查看系统默认的GCC版本:
gcc --version
gcc (GCC) 4.8.5 20150623 (Red Hat 4.8.5-44)
g++ --version
g++ (GCC) 4.8.5 20150623 (Red Hat 4.8.5-44)
which gcc
/bin/gcc
which g++
/bin/g++
tesseract-ocr5.x需要的GCC版本为10以上,需要升级GCC版本:
wget http://ftp.gnu.org/gnu/gcc/gcc-11.3.0/gcc-11.3.0.tar.gz
tar xf gcc-11.3.0.tar.gz
cd gcc-11.3.0
./contrib/download_prerequisites
mkdir build
cd build/
../configure --prefix=/usr/local/gcc-11.3.0 \
--enable-bootstrap \
--enable-checking=release \
--enable-languages=c,c++ \
--disable-multilib
make -j$(nproc) && make install
gcc --version
gcc (GCC) 11.3.0
vim /etc/profile
export PATH=/usr/local/bin:$PATH
上面的过程执行完,如果你在linux命令行中输入gcc -version
,你会发现显示的还是原来的版本,这是因为gcc还没有更新,执行的还是原来的gcc命令。原来的gcc命令位于目录/bin/gcc
等目录下面,为了不覆盖原来的命令。将原来的相关内容进行备份处理,执行如下命令:
mv /bin/gcc /bin/gcc485
mv /bin/g++ /bin/g++485
mv /bin/c++ /bin/c++485
mv /bin/c /bin/c++485
mv /bin/cc /bin/cc485
mv /usr/lib64/libstdc++.so.6 /usr/lib64/libstdc++.so.6.bak
安装的gcc新版本位于/usr/local/bin目录下面,需要为新版本gcc创建软链接:
ln -s /usr/local/bin/gcc /bin/gcc
ln -s /usr/local/gcc-11.3.0/bin/g++ /bin/g++
ln -s /usr/local/gcc-11.3.0/bin/c++ /bin/c++
ln -s /usr/local/gcc-11.3.0/bin/cc /bin/cc
ln -s /usr/local/gcc-11.3.0/lib64/libstdc++.so.6.0.29 /usr/lib64/libstdc++.so.6
gcc --version
gcc (GCC) 11.3.0
g++ --version
g++ (GCC) 11.3.0
3. 安装leptonica
wget http://www.leptonica.org/source/leptonica-1.82.0.tar.gz
tar xf leptonica-1.82.0.tar.gz
cd leptonica-1.82.0
./configure --prefix=/usr/local/leptonica --with-libtiff
make && make install
vim /etc/profile
# leptonica环境变量
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=$LIBRARY_PATH:/usr/local/leptonica/lib
export LIBRARY_PATH
LIBLEPT_HEADERSDIR=/usr/local/leptonica/include/leptonica
export LIBLEPT_HEADERSDIR
source /etc/profile
4. 安装tesseract5.4
git clone https://github.com/tesseract-ocr/tesseract.git
cd tesseract
git checkout 5.4.1
./autogen.sh
./configure --prefix=/usr/local/tesseract
make && make install
vim /etc/profile
# tesseract
PATH=$PATH:/usr/local/tesseract/bin
source /etc/profile
tesseract --version
tesseract 5.4.1
leptonica-1.82.0
libjpeg 6b (libjpeg-turbo 1.2.90) : libpng 1.5.13 : zlib 1.2.7
Found AVX512BW
Found AVX512F
Found AVX2
Found AVX
Found FMA
Found SSE4.1
Found OpenMP 201511