C语言学习网

使用java怎么识别图片中的文字

发表于:2022-10-04 作者:安全数据网编辑
编辑最后更新 2022年10月04日,本篇文章给大家分享的是有关使用java怎么识别图片中的文字,小编觉得挺实用的,因此分享给大家学习,希望大家阅读完这篇文章后可以有所收获,话不多说,跟着小编一起来看看吧。java中使用tesseract

本篇文章给大家分享的是有关使用java怎么识别图片中的文字,小编觉得挺实用的,因此分享给大家学习,希望大家阅读完这篇文章后可以有所收获,话不多说,跟着小编一起来看看吧。

java中使用tesseract-ocr3.01的步骤如下:

1.下载安装tesseract-ocr-setup-3.01-1.exe(3.0以上版本才增加了中文识别)

2.在安装向导中可以选择需要下载的语言包。

3.到网上搜索下载java图形处理所需的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 {    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"));  }  }

OCR 类:

package com.hhp.util;  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 (x86)//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();  } }

测试类TestOCR :

import java.io.File; import java.io.IOException;  import com.hhp.util.OCR;  public class OcrTest {   public static void main(String[] args) {   String path = "C://temp//OCRcode//4.png";    System.out.println("ORC Test Begin......");   try {     String valCode = new OCR().recognizeText(new File(path), "png");     System.out.println(valCode);    } catch (IOException e) {     e.printStackTrace();    } catch (Exception e) {    e.printStackTrace();   }     System.out.println("ORC Test End......");  }  }

Java有哪些集合类

Java中的集合主要分为四类:1、List列表:有序的,可重复的;2、Queue队列:有序,可重复的;3、Set集合:不可重复;4、Map映射:无序,键唯一,值不唯一。

以上就是使用java怎么识别图片中的文字,小编相信有部分知识点可能是我们日常工作会见到或用到的。希望你能通过这篇文章学到更多知识。更多详情敬请关注行业资讯频道。

0