识别率很高的java文字识别技术

java文字识别程序的关键是寻找一个可以调用的OCR引擎。tesseract-ocr就是一个这样的OCR引擎，在1985年到1995年由HP实验室开发，现在在Google。tesseract-ocr 3.0发布，支持中文。不过tesseract-ocr 3.0不是图形化界面的客户端，别人写的FreeOCR图形化客户端还不支持导入新的 3.0 traineddata。但这标志着，现在有自由的中文OCR软件了。

java中使用tesseract-ocr3.01的步骤如下：

1.下载安装tesseract-ocr-setup-3.01-1.exe（3.0以上版本才增加了中文识别）

2.在安装向导中可以选择需要下载的语言包。

3.到网上搜索下载java图形处理所需的2个包：jai_imageio-1.1-alpha.jar，swingx-1.6.1.jar

4.java程序清单：

ImageIOHelper 类：

 import java.awt.image.BufferedImage;
 import java.io.File;
 import java.io.IOException;
 import java.util.Iterator;
 import java.util.Locale;

 import javax.imageio.IIOImage;
 import javax.imageio.ImageIO;
 import javax.imageio.ImageReader;
 import javax.imageio.ImageWriteParam;
 import javax.imageio.ImageWriter;
 import javax.imageio.metadata.IIOMetadata;
 import javax.imageio.stream.ImageInputStream;
 import javax.imageio.stream.ImageOutputStream;

 import com.sun.media.imageio.plugins.tiff.TIFFImageWriteParam;

 public class ImageIOHelper { 

  public static File createImage(File imageFile, String imageFormat) {
   File tempFile = null;
   try {
    Iterator readers = ImageIO.getImageReadersByFormatName(imageFormat);
    ImageReader reader = readers.next(); 

    ImageInputStream iis = ImageIO.createImageInputStream(imageFile);
    reader.setInput(iis);
    //Read the stream metadata
    IIOMetadata streamMetadata = reader.getStreamMetadata(); 

    //Set up the writeParam
    TIFFImageWriteParam tiffWriteParam = new TIFFImageWriteParam(Locale.CHINESE);
    tiffWriteParam.setCompressionMode(ImageWriteParam.MODE_DISABLED); 

    //Get tif writer and set output to file
    Iterator writers = ImageIO.getImageWritersByFormatName("tiff");
    ImageWriter writer = writers.next(); 

    BufferedImage bi = reader.read(0);
    IIOImage image = new IIOImage(bi,null,reader.getImageMetadata(0));
    tempFile = tempImageFile(imageFile);
    ImageOutputStream ios = ImageIO.createImageOutputStream(tempFile);
    writer.setOutput(ios);
    writer.write(streamMetadata, image, tiffWriteParam);
    ios.close(); 

    writer.dispose();
    reader.dispose(); 

   } catch (IOException e) {
    e.printStackTrace();
   }
   return tempFile;
  } 

  private static File tempImageFile(File imageFile) {
   String path = imageFile.getPath();
   StringBuffer strB = new StringBuffer(path);
   strB.insert(path.lastIndexOf('.'),0);
   return new File(strB.toString().replaceFirst("(?<=//.)(//w+)$", "tif"));
  } 

 } 

OCR 类：

 package com.hhp.util;

 import java.io.BufferedReader;
 import java.io.File;
 import java.io.FileInputStream;
 import java.io.InputStreamReader;
 import java.util.ArrayList;
 import java.util.List;
 import org.jdesktop.swingx.util.OS; 

 public class OCR {
  private final String LANG_OPTION = "-l"; //英文字母小写l，并非数字1
  private final String EOL = System.getProperty("line.separator");
  private String tessPath = "C://Program Files (x86)//Tesseract-OCR";
  //private String tessPath = new File("tesseract").getAbsolutePath(); 

  public String recognizeText(File imageFile,String imageFormat)throws Exception{
   File tempImage = ImageIOHelper.createImage(imageFile,imageFormat);
   File outputFile = new File(imageFile.getParentFile(),"output");
   StringBuffer strB = new StringBuffer();
   List cmd = new ArrayList();
   if(OS.isWindowsXP()){
    cmd.add(tessPath+"//tesseract");
   }else if(OS.isLinux()){
    cmd.add("tesseract");
   }else{
    cmd.add(tessPath+"//tesseract");
   }
   cmd.add("");
   cmd.add(outputFile.getName());
   cmd.add(LANG_OPTION);
   cmd.add("chi_sim");
   //cmd.add("eng"); 

   ProcessBuilder pb = new ProcessBuilder();
   pb.directory(imageFile.getParentFile()); 

   cmd.set(1, tempImage.getName());
   pb.command(cmd);
   pb.redirectErrorStream(true); 

   Process process = pb.start();
   //tesseract.exe 1.jpg 1 -l chi_sim
   int w = process.waitFor(); 

   //删除临时正在工作文件
   tempImage.delete(); 

   if(w==0){
    BufferedReader in = new BufferedReader(new InputStreamReader(new FileInputStream(outputFile.getAbsolutePath()+".txt"),"UTF-8")); 

    String str;
    while((str = in.readLine())!=null){
     strB.append(str).append(EOL);
    }
    in.close();
   }else{
    String msg;
    switch(w){
     case 1:
      msg = "Errors accessing files.There may be spaces in your image's filename.";
      break;
     case 29:
      msg = "Cannot recongnize the image or its selected region.";
      break;
     case 31:
      msg = "Unsupported image format.";
      break;
     default:
      msg = "Errors occurred.";
    }
    tempImage.delete();
    throw new RuntimeException(msg);
   }
   new File(outputFile.getAbsolutePath()+".txt").delete();
   return strB.toString();
  }
 }

测试类TestOCR ：

 import java.io.File;
 import java.io.IOException;

 import com.hhp.util.OCR;

 public class OcrTest {

  public static void main(String[] args) {
   String path = "C://temp//OCRcode//4.png";
   System.out.println("ORC Test Begin......");
   try {
    String valCode = new OCR().recognizeText(new File(path), "png");
    System.out.println(valCode);
   } catch (IOException e) {
    e.printStackTrace();
   } catch (Exception e) {
    e.printStackTrace();
   }
   System.out.println("ORC Test End......");
  } 

 }

经过测试，tesseract-ocr 3.01的文字识别率很高，对于网站中常见的验证码识别率也很高。

---

微信扫码，欢迎关注微信公众账号，更多精彩~

手机扫码加入QQ群，欢迎你~