tesseract-ocr 识别中文扫描图片

原文链接：http://www.cnblogs.com/alex-blog/articles/2714984.html

 

项目主页地址：http://code.google.com/p/tesseract-ocr/

相关资源下载地址：http://code.google.com/p/tesseract-ocr/downloads/list

需要下载的资源有：

1、tesseract-ocr-setup-3.01-1.exe

因我本地为windows系统，所以用这个

2、chi_sim.traineddata.gz

中文识别时需要的。

安装tesseract-ocr

自定义安装语言包

在Tesseract-OCR安装目录下找到 tessdata目录，其是用来存放语言包，可把 chi_sim.traineddata.gz 解压缩之后的chi_sim.traineddata文件复制到该目录下即可。

本文使用参考blog中的例子

如下：

package org.img;
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 {
    /**
     * 图片文件转换为tif格式
     * @param imageFile 文件路径
     * @param imageFormat 文件扩展名
     * @return
     */
    public static File createImage(File imageFile, String imageFormat) {
        File tempFile = null;
        try {
            Iterator<ImageReader> 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<ImageWriter> 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"));
    }

}

package org.img;
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//Tesseract-OCR"; //

注意这个路径，为安装的tesseract-OCR的路径

    //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<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("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();
    }
}

package org.img;
import java.io.File;
import java.io.IOException;


public class TestOCR {

    /**
     * @param args
     */
    public static void main(String[] args) {
        String path = "D:\temp\img\untitled8.png";   
        try {   
            String valCode = new OCR().recognizeText(new File(path), "png");  
            //6905_1294109277pAj9.jpg
            System.out.println(valCode);   
        } catch (IOException e) {   
            e.printStackTrace();   
        } catch (Exception e) {
            e.printStackTrace();
        }    
    }

}

对于报错，请检查tessPath 这个参数是否设置正确

本文参考以下两位的blog：

http://blog.csdn.net/foamflower/article/details/6110211

http://blog.csdn.net/zhoushuyan/article/details/5948289