基于tess4j的图片文字提取

        <dependency>
            <groupId>net.sourceforge.tess4j</groupId>
            <artifactId>tess4j</artifactId>
            <version>3.2.1</version>
        </dependency>

package com.hxlz.test;

import java.io.File;

import net.sourceforge.tess4j.Tesseract;
import net.sourceforge.tess4j.TesseractException;
import net.sourceforge.tess4j.util.LoadLibs;

public class Tess4jTest {
    public static void main(String[] args) {
        File imageFile = new File("C:\\1.jpeg");
        Tesseract instance = Tesseract.getInstance();


        File tessDataFolder = LoadLibs.extractTessResources("tessdata");

        instance.setLanguage("chi_sim");
        //instance.setLanguage("eng");

        instance.setDatapath(tessDataFolder.getAbsolutePath());

        try {
            String result = instance.doOCR(imageFile);
            System.out.println(result);
        } catch (TesseractException e) {
            System.err.println(e.getMessage());
    }
    
    }
}