java 读取图片中的文字

Maven依赖导入Tess4j

        
        
            net.sourceforge.tess4j
            tess4j
            4.5.4
        

下载Tessdata语言库

https://gitcode.net/mirrors/tesseract-ocr/tessdata?utm_source=csdn_github_accelerator

解压后的文件库：

代码实现：

package com.ypk.swagger.utils.PDFUtils;

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

import net.sourceforge.tess4j.ITesseract;
import net.sourceforge.tess4j.Tesseract;

public class OCR {

    /**
     *
     * @param srImage 图片路径
     * @param ZH_CN 是否使用中文训练库,true-是
     * @return 识别结果
     */
    public static String FindOCR(String srImage, boolean ZH_CN) {
        try {
            System.out.println("start");
            double start=System.currentTimeMillis();
            File imageFile = new File(srImage);
            if (!imageFile.exists()) {
                return "图片不存在";
            }
            BufferedImage textImage = ImageIO.read(imageFile);
            //Tesseract instance=Tesseract.getInstance();
            ITesseract instance = new Tesseract();  // JNA Interface Mapping

            instance.setDatapath("D:\\software\\tessdata\\tessdata-master");//设置训练库
            if (ZH_CN)
                instance.setLanguage("chi_sim");//中文识别
            String result = null;
            result = instance.doOCR(textImage);
            double end=System.currentTimeMillis();
            System.out.println("耗时"+(end-start)/1000+" s");
            return result;
        } catch (Exception e) {
            e.printStackTrace();
            return "发生未知错误";
        }
    }
    public static void main(String[] args) throws Exception {
        String result=FindOCR("C:\\Users\\Administrator\\Desktop\\图片-0.png",true);
        System.out.println(result);
    }
}