基于tess4j的图片文字提取

1.文件结构目录

2.具体实现

  ①添加maven依赖

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

   ②建立tessdata文字识别库,并添加识别库

     资源地址  ：https://github.com/tesseract-ocr/tessdata/tree/3.04.00

      chi_sim.traineddata （中文）

      eng.traineddata          （英文）

    ③Tess4jTest.java   

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()); } } }

 3.结果展示

     你自己试试就晓得了

转载于:https://www.cnblogs.com/20158424-hxlz/p/8727549.html