我的tesseract学习记录

Posted Crysaty

tags:

篇首语:本文由小常识网(cha138.com)小编为大家整理,主要介绍了我的tesseract学习记录相关的知识,希望对你有一定的参考价值。

前言:花了约三周看文档(打酱油),又花了两周搭环境,终于把tesseract用起来了,对简体中文的识别率还不错,在95%以上。现在简要记录一下安装、识别过程。

一、系统环境

  系统:centos6.5

  编译环境:g++

  依赖软件:leptonica、opencv2.4.9、tesseract3.02

二、安装过程

(1) leptonica

  sudo yum -y install autoconf automake libtool
  sudo yum -y install autoconf-archive
  sudo yum -y install pkgconfig
  sudo yum -y install libpng12-dev
  sudo yum -y install libjpeg8-dev
  sudo yum -y install libtiff5-dev
  sudo yum -y install zlib1g-dev

  wget http://www.leptonica.org/source/leptonica-1.68.tar.gz
  tar xvzf leptonica-1.68.tar.gz
  cd leptonica-1.68/
  ./configure
  make && make install

  
  该步骤在普华操作系统中,make时报了一个错误
  pngio.c:119: error: ‘Z_DEFAULT_COMPRESSION’ undeclared here (not in a function)
  解决办法如下:

     去wiki上搜了一把发现是 pngio.c这个文件有个BUG,在MAC下无法找到zlib1g包修改Leptionica/src/pngio.c在  #include "png.h"后插入一下代码即可。

  C代码  收藏代码
  1. #ifdef HAVE_LIBZ  
  2. #include "zlib.h"  
  3. #endif  
 参考的这里

(2) tesseract3.02

  tesseract的安装参考这里

  同时参考官网这里

  wget https://github.com/tesseract-ocr/tesseract/archive/3.02.02.zip
  unzip 3.
02.02.zip
  cd tesseract-3.02.02/
  ./autogen.sh
  ./configure --enable-debug LDFLAGS="-L/usr/local/lib" CFLAGS="-I/usr/local/include"
  make   make install
  $ echo "/usr/local//lib" >> /etc/ld.so.conf(普华操作系统)
  ldconfig

  语言文件:

  export TESSDATA_PREFIX=/some/path/to/tessdata

    to point to your tessdata directory (example: if your tessdata path is \'/usr/local/share/tessdata\' you have to use \'export TESSDATA_PREFIX=\'/usr/local/share/\').

    环境变量TESSDATA_PREFIX的路径需要设置成为tessdata文件夹的父目录。

(3) opencv2.4.9

  安装cmake(用最新版本)

  cmake版本传送cmake3.4.0二进制版本 

  配置过程:

  $ tar -xvf cmake-3.4.0-rc3-Linux-x86_64.tar.gz

  $ echo \'export PATH=$PATH:/usr/local/cmake-3.4.0-rc3-Linux-x86_64/bin\' >> /etc/profile

  $ source  /etc/profile

  参考:http://www.cnblogs.com/Crysaty/p/6247505.html

 

  重要:先安装gtk+2.x,在编译安装opencv.详细原因和安装方法参考这里

  安装方法也可以参考这里

 

  1. $ sudo yum -y install gtk2-devel tbb-devel libpng-devel
  2. $ wget http://sourceforge.net/projects/opencvlibrary/files/opencv-unix/2.4.9/opencv-2.4.9.zip   
  3. $ unzip opencv-2.4.9.zip   
  4. $ cd opencv-2.4.9  
  5. $ mkdir build   
  6. $ cd build   
  7. $ cmake  -D  CMAKE_BUILD_TYPE=RELEASE  -D  CMAKE_INSTALL_PREFIX=/usr/local  ..
  8. $ make  -j2
  9. $ make install  
  10. $ echo "/usr/local/opencv-2.4.9/build/lib" >> /etc/ld.so.conf(普华操作系统)
  11.  ldconfig(普华操作系统)

  如果下载opencv2.4.10,则是:wget http://sourceforge.net/projects/opencvlibrary/files/opencv-unix/2.4.10/opencv-2.4.10.zip   

三、API接口应用过程

(1) 编译过程

  1、设置PKG_CONFIG_PATH environment variable ,加入`tesseract.pc\'

     $echo \'export PKG_CONFIG_PATH=$PKG_CONFIG_PATH:/usr/local/lib/pkgconfig\' >> ~/.bashrc

     $source ~/.bashrc

  2、提示opencv缺libcufft,libnpps,libnppi,libnppc,libcudart等几个库,可以参考这里

    这些库在cuda/lib64中,建立软连接

    [root@localhost lib64]#ln -s /usr/local/cuda-6.5/lib64/libcufft.so.6.5 /usr/local/lib/libcufft.so

    [root@localhost lib64]#ln -s /usr/local/cuda-6.5/lib64/libnpps.so.6.5 /usr/local/lib/libnpps.so
    [root@localhost lib64]# ln -s /usr/local/cuda-6.5/lib64/libnppi.so.6.5 /usr/local/lib/libnppi.so
    [root@localhost lib64]# ln -s /usr/local/cuda-6.5/lib64/libnppc.so.6.5 /usr/local/lib/libnppc.so
    [root@localhost lib64]# ln -s /usr/local/cuda-6.5/lib64/libcudart.so.6.5 /usr/local/lib/libcudart.so

 

    在运行时,报错:

    error while loading shared libraries: libcufft.so.6.5: cannot open shared object file: No such file or directory

    error while loading shared libraries: libnpps.so.6.5: cannot open shared object file: No such file or directory

    error while loading shared libraries: libnppi.so.6.5: cannot open shared object file: No such file or directory

    error while loading shared libraries: libnppc.so.6.5: cannot open shared object file: No such file or directory

    error while loading shared libraries: libcudart.so.6.5: cannot open shared object file: No such file or directory

    

      解决方法,参考这里

    When I run testing routine, facing error: error while loading shared libraries: libcudart.so.6.5: cannot open shared object file: No such file or directory.

    Solution for this, copy respect library to /usr/local/lib:

    sudo cp /usr/local/cuda-6.5/lib64/libcudart.so.6.5 /usr/local/lib/libcudart.so.6.5 && sudo ldconfig

    sudo cp /usr/local/cuda-6.5/lib64/libcublas.so.6.5 /usr/local/lib/libcublas.so.6.5 && sudo ldconfig

    sudo cp /usr/local/cuda-6.5/lib64/libcurand.so.6.5 /usr/local/lib/libcurand.so.6.5 && sudo ldconfig

    

    最后的结果是能够成功进行识别,但是准确率较windows下有所下降,唯一的区别是,linux用的opencv是2.4.9,而windows中使用的2.4.10.

    

以上是关于我的tesseract学习记录的主要内容,如果未能解决你的问题,请参考以下文章

学习 PyQt5。在我的代码片段中找不到错误 [关闭]

python小白学习记录 多线程爬取ts片段

孤荷凌寒自学python第八十四天搭建jTessBoxEditor来训练tesseract模块

Tesseract 3.02 OCR文字识别调查记录

孤荷凌寒自学python第八十三天初次接触ocr配置tesseract环境

golang代码片段(摘抄)