ocr 中文 java_Java中文图像识别tesseract-ocr

tesseract-ocr引擎最初是由惠普开发的，后来开源了然后交给谷歌打理进行优化工作了。3.0版本开始支持中文OCR，对于中文图像的识别。尽管效果并不如人意，但是只要图像够清晰，还是能够凑合着用的。

PS：com.input.ocr下的java类文件是copy网友所写的，感觉只是把它当成工具起辅助作用，就没有深入研究了，大概看了一下作为主体的两个类主要是一些流的操作。

在java中调用tesseract-ocr进行图像识别的三段代码，最后一段mian方法是测试用的。提供完整的OCR Java Web项目下载，在文章末尾。

---------------------------------------------------------------------

package com.input.ocr;

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 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"));

}

}

package com.input.ocr;

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");

//配置你安装的OCR的路径

private String tessPath = "C:\\Program Files\\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();

}

}

package com.input.ocr;

import java.io.File;

import java.io.IOException;

public class TestOCR {

/**

* @param args

*/

public static void main(String[] args) {

String path = "D:\\image.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();

}

}

} 基于tesseract-ocr JavaWeb项目-下载地址：http://pan.baidu.com/s/1sj1zNGx