【学习】linux下安装编译tesseract-ocr

安装依赖

yum install autoconf automake libtool libjpeg-devel libpng-devel libtiff-devel zlib-devel gcc gcc-c++

安装leptonica

  • 安装
mkdir  /usr/local/leptonica

tar -xzvf leptonica-1.79.0.tar.gz

cd leptonica-1.79.0

./configure --prefix=/usr/local/leptonica  && make  && make install

# 注意,编译如果报错,请检查依赖安装
  • 配置环境
vim /etc/profile
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

安装 tesserac

  • 安装
mkdir /usr/local/tesseract

tar -xzvf tesseract-4.1.1.tar.gz
cd tesseract-4.1.1
# 必须先运行autogen.sh文件才会有configuer文件
./autogen.sh
# 编译安装到指定文件夹
./configure --prefix=/usr/local/tesseract  && make && make install
  • 配置环境变量
vim /etc/profile

# 追加字段
PATH=$PATH:/usr/local/tesseract/bin
export PATH

source /etc/profile
  • 下载OCR识别字符集(或自己上传训练好的字符集)
# 进入到tesseract安装路径下share下面的tessdata文件夹下下载字符集
cd  /usr/local/tesseract/share/tessdata

wget https://hub.fastgit.org/tesseract-ocr/tessdata/raw/master/eng.traineddata
wget https://hub.fastgit.org/tesseract-ocr/tessdata/raw/master/chi_sim.traineddata
wget https://hub.fastgit.org/tesseract-ocr/tessdata/raw/master/chi_sim_vert.traineddata
posted @ 2022-06-14 11:55  小拳头呀  阅读(709)  评论(0)    收藏  举报