tesseract ocr3 02字符识别过程操作步骤

分享一下我老师大神的人工智能教程!零基础,通俗易懂!http://blog.csdn.net/jiangjunshow

也欢迎大家转载本篇文章。分享知识,造福人民,实现我们中华民族伟大复兴!

               

1、  从http://code.google.com/p/tesseract-ocr/downloads/list下载tesseract-ocr-3.02-vs2008tesseract-ocr-3.02.chi_sim.tartesseract-ocr-3.02.02.tartesseract-ocr-3.02.02-doc-html.tarleptonica-1.68-win32-lib-include-dirs相关文件;

2、  将所有文件存放在E:\OCR\tesseract_ocr3.02文件夹下并解压缩;

3、  打开tesseract-ocr-3.02-vs2008文件夹下的tesseract.sln工程;

4、  将tesseract-ocr-3.02.02文件夹下的对应文件如apiccmain等复制到E:\OCR\tesseract_ocr3.02\tesseract-ocr-3.02-vs2008\tesseract-ocr文件夹下,把leptonica-1.68-win32-lib-include-dirs文件夹下的include文件夹复制到E:\OCR\tesseract_ocr3.02\tesseract-ocr-3.02-vs2008文件夹下,将tesseract_ocr3.02\tesseract-ocr-3.02.02\tesseract-ocr\vs2008\port文件夹下的文件复制到E:\OCR\tesseract_ocr3.02\tesseract-ocr-3.02-vs2008\tesseract-ocr\vs2008\port文件夹下,将leptonica-1.68-win32-lib-include-dirs文件夹下lib文件夹复制到tesseract_ocr3.02\tesseract-ocr-3.02-vs2008文件夹下;

5、  将ccmain文件夹下的equationdetect.cpp文件中的static const STRING kCharsToEx[] = {"'", "`","\"", "\\", ",", ".", "〈", "〉", "《", "》", "」", "「", ""};修改成static const STRING kCharsToEx[] = {"'", "`","\"", "\\", ",",".","<", ">",   "<<",">>",  ""};(注:不改动编译时始终出错,其它方法暂未发现,3.01版本中没有此文件,编译3.01不用对源文件作任何修改)

6、 重新编译整个Solution;

7、 创建一个控制台空工程,配置环境仿照tesseract工程,并在执行文件夹下创建一个tessdata文件夹,里面存放chi_sim.traineddata数据文件,示例代码如下:

 

#include "allheaders.h"#include "baseapi.h"#include "basedir.h"#include "strngs.h"#include "tesseractmain.h"#include "tprintf.h"int main(int argc, char **argv){  tesseract::TessBaseAPI api;  STRING tessdata_dir;  truncate_path(argv[0], &tessdata_dir);  int rc = api.Init(tessdata_dir.string(), NULL);  if (rc)   {    fprintf(stderr, ("Could not initialize tesseract.\n"));    exit(1);  }  api.End();  // Make the order of args a bit more forgiving than it used to be.  const char* lang = "chi_sim";//eng  const char* image = "E:\\OCR\\tesseract_ocr3.02\\tesseract-ocr-3.02-vs2008\\tesseract-ocr\\vs2008\\Debug\\ABC.tif";//NULL;  const char* output = "E:\\OCR\\tesseract_ocr3.02\\tesseract-ocr-3.02-vs2008\\tesseract-ocr\\vs2008\\Debug\\xxxxx";//NULL;    tesseract::PageSegMode pagesegmode = tesseract::PSM_AUTO;  int arg = 1;  api.SetOutputName(output);  rc = api.Init(tessdata_dir.string(), lang, tesseract::OEM_DEFAULT,                &(argv[arg]), argc - arg, NULL, NULL, false);  if (rc)  {    fprintf(stderr, ("Could not initialize tesseract.\n"));    exit(1);  }  if (api.GetPageSegMode() == tesseract::PSM_SINGLE_BLOCK)  {    api.SetPageSegMode(pagesegmode);  }  tprintf("Tesseract Open Source OCR Engine v%s with Leptonica\n", tesseract::TessBaseAPI::Version());  FILE* fin = fopen(image, "rb");  if (fin == NULL)   {    fprintf(stderr, ("Cannot open input file: %s\n"), image);    exit(2);  }  fclose(fin);  PIX   *pixs;  if ((pixs = pixRead(image)) == NULL)  {    fprintf(stderr, ("Unsupported image type.\n"));    exit(3);  }  pixDestroy(&pixs);  STRING text_out;  if (!api.ProcessPages(image, NULL, 0, &text_out))   {    fprintf(stderr, ("Error during processing.\n"));  }  bool output_hocr = false;  api.GetBoolVariable("tessedit_create_hocr", &output_hocr);  bool output_box = false;  api.GetBoolVariable("tessedit_create_boxfile", &output_box);  STRING outfile = output;  outfile += output_hocr ? ".html" : output_box ? ".box" : ".txt";  FILE* fout = fopen(outfile.string(), "wb");  if (fout == NULL)   {    fprintf(stderr, ("Cannot create output file %s\n"), outfile.string());    exit(1);  }  fwrite(text_out.string(), 1, text_out.length(), fout);  fclose(fout);  return 0;                      // Normal exit}

 

以上代码编译运行成功,直接输入整幅图像进行字符识别,效果一般。

           

给我老师的人工智能教程打call!http://blog.csdn.net/jiangjunshow

这里写图片描述

你可能感兴趣的:(tesseract ocr3 02字符识别过程操作步骤)