java ORC 图片中文识别
java通过调用tesseract完成图片中文字识别
1.安装tesseract-ocr-setup-3.00.exe（3.0以上版本才增加了中文识别）
2.下载tesseract-ocr的中文包chi_sim.traineddata.gz，解压缩之后复制到tesseract-ocr的安装目录之下。如：D:/Tesseract-OCR/tessdata
3.java需要增加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 {
/**
* 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"));
}
}
OCR 类：
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://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();
}
}
测试类TestOCR ：
import java.io.File;
import java.io.IOException;
public class TestOCR {
/**
* @param args
*/
public static void main(String[] args) {
String path = "d://test//C360_2011-04-25 16-15-34.jpg";
System.out.println("ORC Test Begin......");
try {
String valCode = new OCR().recognizeText(new File(path), "jpg");
System.out.println(valCode);
} catch (IOException e) {
e.printStackTrace();
} catch (Exception e) {
e.printStackTrace();
}
System.out.println("ORC Test End......");
}
}
不过实话实说，tesseract虽然刚刚在3.0版本提供了对中文识别的支持，但是识别率实在是不尽如意，经过本人的测试即使扫描件的识别，也并不理想，使用手机拍照的图片，本人使用的是HTC G7的摄像头（500w像素）在光线良好的状态下，以名片进行测试，并不理想，在光线并不良好下，基本全是乱码。在这里我想进行调用office orc识别系统在进行测试一下。