Text extraction (Java+Tesseract_OCR)

development environment

System: windows 11
jdk: 1.8
Framework: spring boot 2.1 4 + maven
Tool: idea

Tesseract installation

install

Double click to select the language and click OK
Direct next
Daily consent agreement
Choose who to install it for (depending on your needs, mine is a personal computer)
Next, select the language pack
The last two boxes are not recommended for downloading language packs (very slow, unless there is a ladder, there will be a tutorial to expand the language pack below)
Select installation directory
next, wait for the installation to complete
(there is one option to add the registry. I forgot the screenshot. By default, next is done.)
Installation complete (end)

Configure environment variables

This step is very simple for everyone

Computer settings (advanced environment variables)
windows11

windows 10(windows server makes do)
Click environment variables
PATH found in system variable
(user variables are also acceptable. If you can't use them, don't look for me)
Click new and select the path
That's about it. Just click OK

Check that the installation is successful

Here comes the omnipotent cmd

win+R input cmd
Enter tesseract -v in the small black box
See, the version we installed

Extended language pack

The link above can be downloaded from github( Portal)
csdn I uploaded: https://download.csdn.net/download/qq_35885175/68245426
This thing is in simplified Chinese

go:
Put the downloaded file into the installation directory and it is finished

Test whether the extension is successful
Small black box (cmd) input: Tesseract -- List Langs

Done

Java code (a side dish)

1.POM file

 <dependency>
            <groupId>net.sourceforge.tess4j</groupId>
            <artifactId>tess4j</artifactId>
            <version>5.0.0</version>
 </dependency>

If the download is unsuccessful, switch several version s
jar package link: https://download.csdn.net/download/qq_35885175/68256292
Or download this I uploaded and throw it directly to the warehouse according to the directory

2.ImageIOHelper code

package com.lk.integutils.utils;

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.github.jaiimageio.plugins.tiff.TIFFImageWriteParam;

public class ImageIOHelper {

    //Set language
    private Locale locale=Locale.CHINESE;

    //Method of custom language construction
    public ImageIOHelper(Locale locale){
        this.locale=locale;
    }
    //Default constructor locale CHINESE

    public ImageIOHelper(){
    }


    /**
     * Create a temporary picture file to prevent damage to the original file
     * @param imageFile
     * @param imageFormat like png,jps .etc
     * @return TempFile of Image
     */
    public File createImage(File imageFile, String imageFormat) throws IOException {

        //Read picture file
        Iterator<ImageReader> readers = ImageIO.getImageReadersByFormatName(imageFormat);
        ImageReader reader = readers.next();
        //Get file stream
        ImageInputStream iis = ImageIO.createImageInputStream(imageFile);
        reader.setInput(iis);
        IIOMetadata streamMetadata = reader.getStreamMetadata();

        //Set writeParam
        TIFFImageWriteParam tiffWriteParam = new TIFFImageWriteParam(Locale.CHINESE);
        tiffWriteParam.setCompressionMode(ImageWriteParam.MODE_DISABLED);
        //Set compressibility

        //Get tiffWriter and set output
        Iterator<ImageWriter> writers = ImageIO.getImageWritersByFormatName("tiff");
        ImageWriter writer = writers.next();


        BufferedImage bi = reader.read(0);
        IIOImage image = new IIOImage(bi,null,reader.getImageMetadata(0));
        File tempFile = tempImageFile(imageFile);
        ImageOutputStream ios = ImageIO.createImageOutputStream(tempFile);

        writer.setOutput(ios);
        writer.write(streamMetadata, image, tiffWriteParam);

        ios.close();
        iis.close();
        writer.dispose();
        reader.dispose();

        return tempFile;
    }

    /**
     * Add suffix to tempfile
     * @param imageFile
     * @throws IOException
     */
    private File tempImageFile(File imageFile) throws IOException {
        String path = imageFile.getPath();
        StringBuffer strB = new StringBuffer(path);
        strB.insert(path.lastIndexOf('.'),"_text_recognize_temp");
        String s=strB.toString().replaceFirst("(?<=//.)(//w+)$", "tif");
        //Set file hiding
        Runtime.getRuntime().exec("attrib "+"\""+s+"\""+" +H");
        return new File(strB.toString());
    }

}

3. OCRUtil code

package com.lk.integutils.utils;

import java.io.*;
import java.util.ArrayList;
import java.util.List;
import java.util.Locale;

import org.jdesktop.swingx.util.OS;

public class OCRUtil  {
    private final String LANG_OPTION = "-l";
    //English letter small l, not Arabic numeral 1

    private final String EOL = System.getProperty("line.separator");

    /**
     * ocr Installation path for
     */
    private String tessPath =  "D:\\Utils\\Tesseract-OCR";



    public OCRUtil(String tessPath,String transFileName){
        this.tessPath=tessPath;
    }

    //The default path of OCRUtil is "C: / / program files (x86) / / Tesseract OCR"

    public OCRUtil(){     }

    public String getTessPath() {
        return tessPath;
    }
    public void setTessPath(String tessPath) {
        this.tessPath = tessPath;
    }
    public String getLANG_OPTION() {
        return LANG_OPTION;
    }
    public String getEOL() {
        return EOL;
    }


    /**
     * @return Recognized text
     */
    public String recognizeText(File imageFile,String imageFormat)throws Exception{
        File tempImage = new ImageIOHelper().createImage(imageFile,imageFormat);
        return ocrImages(tempImage, imageFile);
    }

    /**
     *  You can customize the language
     */
    public String recognizeText(File imageFile,String imageFormat,Locale locale)throws Exception{
        File tempImage = new ImageIOHelper(locale).createImage(imageFile,imageFormat);
        return ocrImages(tempImage, imageFile);
    }

    /**
     * @param
     * @param
     * @return Identified content
     * @throws IOException
     * @throws InterruptedException
     */
    private String ocrImages(File tempImage,File imageFile) throws IOException, InterruptedException{

        //Set the saved file directory and file name of the output file
        File outputFile = new File(imageFile.getParentFile(),"test");
        StringBuffer strB = new StringBuffer();


        //Set command line content
        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);
        //Chinese bag
        cmd.add("chi_sim");
        //Common mathematical formula package
        cmd.add("equ");
        //English package
        cmd.add("eng");


        //Create operating system process
        ProcessBuilder pb = new ProcessBuilder();
        //Set the working directory for this process builder
        pb.directory(imageFile.getParentFile());
        cmd.set(1, tempImage.getName());
        //Set cmd command to execute
        pb.command(cmd);
        //Set that the error output generated by subsequent sub processes will be merged with the standard output
        pb.redirectErrorStream(true);

        long startTime = System.currentTimeMillis();
        System.out.println("Start time:" + startTime);
        //Start execution and return the process instance
        Process process = pb.start();
        //The final execution command is: Tesseract 1 png test -l chi_ sim+equ+eng
        // Input / output stream optimization
//        printMessage(process.getInputStream());
//        printMessage(process.getErrorStream());
        int w = process.waitFor();
        //Delete temporary working files
        tempImage.delete();
        if(w==0){
            // 0 means normal exit
            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();

            long endTime = System.currentTimeMillis();
            System.out.println("End time:" + endTime);
            System.out.println("Time consuming:" + (endTime - startTime) + "millisecond");

        }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);
        }
        // Delete temporary files extracted to text
        new File(outputFile.getAbsolutePath()+".txt").delete();
        return strB.toString().replaceAll("\\s*", "");
    }


    private static void printMessage(final InputStream input) {
        new Thread(new Runnable() {
            @Override
            public void run() {
                Reader reader = new InputStreamReader(input);
                BufferedReader bf = new BufferedReader(reader);
                String line = null;
                try {
                    while ((line = bf.readLine()) != null) {
                        System.out.println(line);
                    }
                } catch (IOException e) {
                    e.printStackTrace();
                }
            }
        }).start();
    }
}

4.TestOcr test code

package com.lk.integutils.utils;

import java.io.File;
import java.io.IOException;

public class TestOcr {

    /**
     * @param args
     */
    public static void main(String[] args) {
        //Enter picture address
        String path = "d://1640144341(1).png";
        try {
            String valCode = new OCRUtil().recognizeText(new File(path), "png");
            System.out.println(valCode);
        } catch (IOException e) {
            e.printStackTrace();
        } catch (Exception e) {
            e.printStackTrace();
        }
    }

}

ending

The effect is not good. It needs to be adjusted

Reference articles

mall4j: https://segmentfault.com/a/1190000039362377
SyKay: https://www.jianshu.com/p/f7cb0b3f337a

Keywords: Java Maven intellij-idea

Added by Xager on Sat, 25 Dec 2021 14:58:50 +0200

Programming VIP