makefile
D:\Program Files\Tesseract-OCR\tessdata

```xml
<dependency>
    <groupId>net.sourceforge.tess4j</groupId>
    <artifactId>tess4j</artifactId>
    <version>5.3.0</version>
</dependency>
<!-- JavaCV: Java interface to OpenCV, FFmpeg, and more -->
<dependency>
    <groupId>org.bytedeco</groupId>
    <artifactId>javacv-platform</artifactId>
    <version>1.5.7</version>
</dependency>

```java
import net.sourceforge.tess4j.TesseractException;
import org.bytedeco.javacv.FFmpegFrameGrabber;
import org.bytedeco.javacv.Frame;
import org.bytedeco.javacv.Java2DFrameUtils;

import javax.imageio.ImageIO;
import java.awt.*;
import java.awt.image.BufferedImage;
import java.io.File;
import java.util.ArrayList;
import java.util.LinkedHashSet;
import java.util.Set;

public class VideoTextExtractor {
    // Tesseract-OCR安裝路徑
    public static final String pathToTessdataFolder = "D:\\Program Files\\Tesseract-OCR\\tessdata\\";
    // 加載視頻
    public static final String pathToVideoFile = "C:\\Users\\lixiewen\\Documents\\oCam\\錄制_2023_05_31_09_39_51_172.mp4";
    // 解析結(jié)果
    public static final String resultFile = "E:\\tmp\\tmp.txt";

    public static void main(String[] args) throws TesseractException {
        extracted();
    }

    private static void extracted() {
        // 設(shè)置Tesseract OCR庫(kù)的路徑
        File tessDataFolder = new File(pathToTessdataFolder);
        System.setProperty("TESSDATA_PREFIX", tessDataFolder.getAbsolutePath());
        FFmpegFrameGrabber grabber = new FFmpegFrameGrabber(pathToVideoFile);
        try {
            grabber.start();
            Set<String> set = new LinkedHashSet<>();
            // 遍歷視頻幀
            int lengthInFrames = grabber.getLengthInFrames();
            for (int i = 0; i < lengthInFrames; i++) {
                System.out.println("進(jìn)度 " + i + " / " + lengthInFrames);
                try {
                    Frame frame = grabber.grabImage();
                    if (frame == null) continue;
                    BufferedImage bufferedImage = Java2DFrameUtils.toBufferedImage(frame);

                    // 將幀轉(zhuǎn)換為灰度圖像
                    BufferedImage grayImage = new BufferedImage(bufferedImage.getWidth(), bufferedImage.getHeight(), BufferedImage.TYPE_BYTE_GRAY);
                    Graphics2D graphics = grayImage.createGraphics();
                    graphics.drawImage(bufferedImage, 0, 0, null);
                    graphics.dispose();

                    // 創(chuàng)建臨時(shí)文件保存圖像
                    File tempImageFile = File.createTempFile("frame", ".png");
                    ImageIO.write(grayImage, "png", tempImageFile);

                    Tesseract tesseract = getTesseract(tessDataFolder);
                    String result = tesseract.doOCR(tempImageFile);
                    set.add(result);
                    // 刪除臨時(shí)文件
                    tempImageFile.delete();
                } catch (Exception e) {
                    e.printStackTrace();
                }
            }
            File file = new File(resultFile);

            FileUtils.write2File(file, new ArrayList<>(set));

            grabber.stop();
        } catch (Exception e) {
            e.printStackTrace();
        }
    }

    private static Tesseract getTesseract(File tessDataFolder) {
        // 使用Tesseract OCR進(jìn)行文字識(shí)別
        Tesseract tesseract = new Tesseract();
        // 設(shè)置中文訓(xùn)練庫(kù)
        tesseract.setLanguage("chi_sim");
        tesseract.setDatapath(tessDataFolder.getAbsolutePath());
        return tesseract;
    }
}

```java
import net.sourceforge.tess4j.Tesseract;

public class OCRUtil {
    public static ITesseract getTesseract() throws Exception {
        // 使用 Tesseract 識(shí)別文本
        ITesseract tesseract = new Tesseract();
        // 設(shè)置訓(xùn)練數(shù)據(jù)文件夾路徑
        tesseract.setDatapath("src/main/resources/traineddata");
        // 設(shè)置為中文簡(jiǎn)體
        tesseract.setLanguage("chi_sim");
        return tesseract;
    }
}

```java
    // 轉(zhuǎn)換為灰度圖像
    BufferedImage grayImage = new BufferedImage(image.getWidth(), image.getHeight(), BufferedImage.TYPE_BYTE_GRAY);
    Graphics2D graphics = grayImage.createGraphics();
    graphics.drawImage(image, 0, 0, null);
    graphics.dispose();

    // 二值化處理
    for (int y = 0; y < grayImage.getHeight(); y++) {
        for (int x = 0; x < grayImage.getWidth(); x++) {
            int rgb = grayImage.getRGB(x, y);
            int gray = (rgb & 0xff);
            gray = gray > 128 ? 255 : 0;
            grayImage.setRGB(x, y, (gray << 16) | (gray << 8) | gray);
        }
    }
    return grayImage;
}