java

关注公众号 jb51net

关闭
首页 > 软件编程 > java > Java调用OCR进行图片识别

Windows下Java调用OCR进行图片识别

作者:coco_ethan

这篇文章主要为大家详细介绍了Windows下Java调用OCR进行图片识别,通过Tesseract-OCR对图片进行识别,具有一定的参考价值,感兴趣的小伙伴们可以参考一下

使用Java语言,通过Tesseract-OCR对图片进行识别。

1.Tesseract-OCR

下载windows版本并安装。

2.程序如下:

a.ImageIOHelper类

package 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<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"));
 }
 
}

b.OCR核心类

package 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");
 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<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();
 }
}

c.main

package OCR;
import java.io.File;
import java.io.IOException;
 
public class TestOcr {
 
 /**
 * @param args
 */
 public static void main(String[] args) {
 //输入图片地址
 String path = "d://test//test.bmp";  
    try {  
      String valCode = new OCR().recognizeText(new File(path), "bmp");  
      System.out.println(valCode);  
    } catch (IOException e) {  
      e.printStackTrace();  
    } catch (Exception e) {
  e.printStackTrace();
 }  
 }
 
}

以上就是本文的全部内容,希望对大家的学习有所帮助,也希望大家多多支持脚本之家。

您可能感兴趣的文章:
阅读全文