java图片识别文字的方法

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*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。

以上就是本文的全部内容，希望对大家的学习有所帮助，也希望大家多多支持。