Tesseract-OCR安装与使用.获取图片中文字信息

Tesseract-OCR下载地址：https://github.com/UB-Mannheim/tesseract/wiki，下载tesseract安装包

安装tesseract，双击进行运行安装。全部点next就行。自己选择安装的位置

系统环境变量–>path，添加Tesseract-OCR的路径位置

系统变量–>新建
变量名：TESSDATA_PREFIX
变量值:   D:java工具Tesseract-ocrtessdata 你Tesseract安装的位置我是默认的安装位置
这一步是添加Tesseract-OCR的语言库，语言库地址：https://github.com/tesseract-ocr/tessdata。你还可以根据实际情况去自己训练自己的语言

import javax.imageio.ImageIO;
import java.awt.*;
import java.awt.image.BufferedImage;
import java.io.File;
import java.io.IOException;

public class xxx {
    public static void main(String[] args) {
        try {

            jp();

            //图片文件：此图片是需要被识别的图片
            File file = new File("D:\java工具\Tesseract-ocr\tessdata\图片\test.png");
            System.out.println("begin.........");
            String recognizeText1 = new test01().recognizeText(file);
            System.out.print(recognizeText1+"t");

        } catch (IOException e) {
            e.printStackTrace();
        } catch (Exception e) {
            e.printStackTrace();
        }
    }
    //截屏
    public static void jp(){
        Dimension screenSize = Toolkit.getDefaultToolkit().getScreenSize();

        // 创建需要截取的矩形区域
        Rectangle rect = new Rectangle(0, 0, screenSize.width, screenSize.height);

        // 截屏操作
        BufferedImage bufImage = null;
        try {
            bufImage = new Robot().createScreenCapture(rect);                   //存入截图
            if (ImageIO.write(bufImage, "PNG", new File("D:\java工具\Tesseract-ocr\tessdata\图片\test.png"))) {
                System.out.println("截屏成功");
            }
        } catch (Exception e) {
            throw new RuntimeException(e);
        }

    }
}

调用下面的test01方法，进行读取数据

import java.io.BufferedReader;
import java.io.File;
import java.io.FileInputStream;
import java.io.InputStreamReader;
import java.util.ArrayList;
import java.util.List;

public class test01 {

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

    
    private String tessPath = "D://java工具//Tesseract-ocr";

    
    public String recognizeText(File imageFile) throws Exception {
        
        File outputFile = new File(imageFile.getParentFile(), "output");

        StringBuffer strB = new StringBuffer();
        List cmd = new ArrayList();

        cmd.add(tessPath + "\tesseract");

        cmd.add("");
        cmd.add(outputFile+"\"+outputFile.getName());
        cmd.add(LANG_OPTION);
//        cmd.add("chi_sim");// 切换中文识别语言或者你自己训练的语言
        cmd.add("eng");

        ProcessBuilder pb = new ProcessBuilder();

        pb.directory(new File(tessPath));
        cmd.set(1, imageFile.getParentFile()+"\"+imageFile.getName());
        pb.command(cmd);
        pb.redirectErrorStream(true);


        long startTime = System.currentTimeMillis();
        System.out.println("开始时间：" + startTime);
        Process process = pb.start();

        int w = process.waitFor();
        if (w == 0)// 0代表正常退出
        {
            BufferedReader in = new BufferedReader(new InputStreamReader(
                    new FileInputStream(outputFile+"\"+outputFile.getName()+".txt"),
                    "UTF-8"));
            String str;
            while ((str = in.readLine()) != null) {
                strB.append(str).append(EOL);
            }
            in.close();

            long endTime = System.currentTimeMillis();
            System.out.println("结束时间：" + endTime);
            System.out.println("耗时：" + (endTime - startTime) + "毫秒");
        } 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 recognize the image or its selected region.";
                    break;
                case 31:
                    msg = "Unsupported image format.";
                    break;
                default:
                    msg = "Errors occurred.";
            }
            throw new RuntimeException(msg);
        }
        // 删除生成的文件
        new File(outputFile+"\"+outputFile.getName()+".txt").delete();
        return strB.toString().replaceAll("\s*", "");
    }
}

结果：