欢迎您访问程序员文章站本站旨在为大家提供分享程序员计算机编程知识!
您现在的位置是: 首页

tesseract-ocr图片识别开源工具

程序员文章站 2022-05-23 14:50:48
...
今天看同事的ppt,提到了图片识别,又tesseract-ocr,觉得不错,试一下,如果效果好可以用来做验证码的识别
http://code.google.com/p/tesseract-ocr/
tesseract是一款开源工具,我安装了Windows版试水先
1、首先登录首页在‘下载’页面下载
tesseract-ocr-setup-xx.xx.exe     
chi_sim.traineddata.gz   中文语言包

2、双击即可安装tesserract-ocr,
3、安装中文语言包,将语言包 chi_sim.traineddata.gz   解压到 Tesseract-OCR下
4、写测试代码:
package com.taobao.voc.tesseract;

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 = "D://java_tools//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<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 com.taobao.voc.tesseract;

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"));
    }

}

测试代码
package com.taobao.voc.tesseract;
import java.io.File;
import java.io.IOException;

public class TestOCR {

    /**
     * @param args
     */
    public static void main(String[] args) {
        String path = "d://test4.jpg";
        try {
            String valCode = new OCR().recognizeText(new File(path), "jpg");
            System.out.println(valCode);
        } catch (IOException e) {
            e.printStackTrace();
        } catch (Exception e) {
            e.printStackTrace();
        }
    }

}

String path = "d://test4.jpg"; 修改为需要测试的图片,最好全中文,如果因为请更换语言包,OCR类中cmd.add("chi_sim");
相关标签: java