java实现图片文字识别ocr

最近在开发的时候需要识别图片中的一些文字，网上找了相关资料之后，发现google有一个离线的工具，以下为java使用的demo

在此之前，使用这个工具需要在本地安装ocr工具：

下面一个是一定要安装的离线包，建议默认安装

上面一个是中文的语言包，如果网络可以fq的童鞋可以在安装的时候就选择语言包在线安装，有多种语言可供选择，默认只有英文的

exe安装好之后，把上面一个文件拷到安装目录下tessdata文件夹下

如c:\program files (x86)\tesseract-ocr\tessdata下

然后下面两个是可选包，如果图片不做临时文件处理的话，可以不需要带的

首先是一个临时文件生成用的类以防源文件损坏，参考某位博友的例子@gunner

package org.ink.image.textrz;

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 {
  private locale locale=locale.chinese;
  /**
   * user set locale construct
   * @param locale
   */
  public imageiohelper(locale locale){
    this.locale=locale;
  }
  
  /**
   * default construct using default locale locale.chinese
   */
  public imageiohelper(){
    
  }
  /**
   * create tempfile of image in order to prevent damaging original file
   * @param imagefile
   * @param imageformat like png,jps .etc
   * @return tempfile of image
   * @throws ioexception
   */
  public file createimage(file imagefile, string imageformat) throws ioexception {  
    iterator<imagereader> readers = imageio.getimagereadersbyformatname(imageformat);  
    imagereader reader = readers.next();  
    imageinputstream iis = imageio.createimageinputstream(imagefile);  
    reader.setinput(iis);  
    iiometadata streammetadata = reader.getstreammetadata();  
    tiffimagewriteparam tiffwriteparam = new tiffimagewriteparam(locale.chinese);  
    tiffwriteparam.setcompressionmode(imagewriteparam.mode_disabled);  
    iterator<imagewriter> writers = imageio.getimagewritersbyformatname("tiff");  
    imagewriter writer = writers.next();  
    bufferedimage bi = reader.read(0);  
    iioimage image = new iioimage(bi,null,reader.getimagemetadata(0));  
    file tempfile = tempimagefile(imagefile);  
    imageoutputstream ios = imageio.createimageoutputstream(tempfile);  
    writer.setoutput(ios);  
    writer.write(streammetadata, image, tiffwriteparam);  
    ios.close();
    iis.close();
    writer.dispose();  
    reader.dispose();  
    return tempfile;  
  }  
  /**
   * add suffix to tempfile
   * @param imagefile
   * @return
   * @throws ioexception 
   */
  private file tempimagefile(file imagefile) throws ioexception {  
    string path = imagefile.getpath();  
    stringbuffer strb = new stringbuffer(path);  
    strb.insert(path.lastindexof('.'),"_text_recognize_temp");
    string s=strb.tostring().replacefirst("(?<=//.)(//w+)$", "tif");
    runtime.getruntime().exec("attrib "+"\""+s+"\""+" +h"); //设置文件隐藏
    return new file(strb.tostring()); 
  }  
  
} 

下面是真正识别的内容：

package org.ink.image.textrz;

import java.io.bufferedreader;  
import java.io.file;  
import java.io.fileinputstream;
import java.io.ioexception;
import java.io.inputstreamreader;  
import java.util.arraylist;  
import java.util.list;
import java.util.locale;

import org.jdesktop.swingx.util.os;  

/**
 * text recognize utils
 * @author ink.flower
 *
 */
public class ocrutil { 
  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";//ocr默认安装路径
  private string transname="chi_sim";//默认中文语言包，识别中文
  
  /**
   * construct method of ocr ,set tesseract-ocr install path
   * @param tesspath tesseract-ocr install path
   * @param transfilename traningfile name like eng.traineddata
   */
  public ocrutil(string tesspath,string transfilename){
    this.tesspath=tesspath;
    this.transname=transfilename;
  }
  /**
   * construct method of ocr,default path is "c://program files (x86)//tesseract-ocr"
   */
  public ocrutil(){   }
  
  public string gettesspath() {
    return tesspath;
  }
  public void settesspath(string tesspath) {
    this.tesspath = tesspath;
  }
  public string gettransname() {
    return transname;
  }
  public void settransname(string transname) {
    this.transname = transname;
  }
  public string getlang_option() {
    return lang_option;
  }
  public string geteol() {
    return eol;
  }
  
  /**
   * recognize text in image
   * @param imagefile
   * @param imageformat
   * @return text recognized in image
   * @throws exception
   */
  public string recognizetext(file imagefile,string imageformat)throws exception{  
    file tempimage = new imageiohelper().createimage(imagefile,imageformat);  
    return ocrimages(tempimage, imagefile);  
  }  
  
  /**
   * recognize text in image
   * @param imagefile
   * @param imageformat
   * @param locale
   * @return text recognized in image
   * @throws exception
   */
  public string recognizetext(file imagefile,string imageformat,locale locale)throws exception{  
    file tempimage = new imageiohelper(locale).createimage(imagefile,imageformat);
    return ocrimages(tempimage, imagefile);
      
  }
  /**
   * 
   * @param tempimage
   * @param imagefile
   * @return
   * @throws ioexception
   * @throws interruptedexception
   */
  private string ocrimages(file tempimage,file imagefile) throws ioexception, interruptedexception{
    file outputfile = new file(imagefile.getparentfile(),"output");
    runtime.getruntime().exec("attrib "+"\""+outputfile.getabsolutepath()+"\""+" +h"); //设置文件隐藏
    stringbuffer strb = new stringbuffer();  
    list<string> cmd = new arraylist<string>();  
    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(transname);  
    processbuilder pb = new processbuilder();  
    pb.directory(imagefile.getparentfile());  
    cmd.set(1, tempimage.getname());  
    pb.command(cmd);  
    pb.redirecterrorstream(true);  
    process process = pb.start();  
    int w = process.waitfor();  
    tempimage.delete();//删除临时正在工作文件     
    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(); 
  }
}  

在实验中发现，如果对有多个文字的大图进行直接识别的话，效果可能比较差，所以可以参考另一篇切图的博文，将图片取一块之后再识别

  ←我是链接

这样成功率会提高很多。

以上为离线识别版本，效率因图而已，具体使用的时候可以总结分析，希望对大家的学习有所帮助，也希望大家多多支持。