feat(omr): 新增基于OCR的试卷ID识别功能

- 集成Tess4J实现OCR识别，新增analyzeExamWordsId方法提取试卷ID
- 对试卷图片左上角区域进行裁剪和预处理以提升识别准确率
- 添加Mat到BufferedImage的转换辅助方法，支持OCR读取
- 在测试用例中增加对OCR识别功能的集成测试
- 修改配置文件添加OCR数据路径，完善依赖引入OpenCV和Tess4J库

enlish-service/src/main/java/com/yinlihupo/enlish/service/utils/PngUtil.java

@@ -4,15 +4,23 @@ import com.yinlihupo.enlish.service.constant.ExamWordsConstant;
 import com.yinlihupo.enlish.service.model.bo.CoordinatesXY;
 import com.yinlihupo.enlish.service.model.bo.Word;
 import lombok.extern.slf4j.Slf4j;
+import net.sourceforge.tess4j.ITesseract;
+import net.sourceforge.tess4j.Tesseract;
+import net.sourceforge.tess4j.TesseractException;
 import nu.pattern.OpenCV;
 import org.checkerframework.checker.nullness.qual.NonNull;
 import org.opencv.core.*;
 import org.opencv.imgcodecs.Imgcodecs;
 import org.opencv.imgproc.Imgproc;
+import org.springframework.beans.factory.annotation.Value;
 
+import java.awt.image.BufferedImage;
+import java.awt.image.DataBufferByte;
 import java.util.ArrayList;
 import java.util.Comparator;
 import java.util.List;
+import java.util.regex.Matcher;
+import java.util.regex.Pattern;
 
 @Slf4j
 public class PngUtil {
@@ -184,6 +192,82 @@ public class PngUtil {
         }
     }
 
+    public static Integer analyzeExamWordsId(String imagePath, String tessdataPath, List<CoordinatesXY> coordinatesXIES) {
+        // 1. 读取图片
+        Mat src = Imgcodecs.imread(imagePath);
+        if (src.empty()) {
+            System.out.println("无法加载图片");
+            return 0;
+        }
+
+        // 2. 截取左上角区域 (ROI)
+        // 根据图片大概估算：从 (0,0) 开始，宽约 300像素，高约 80像素
+        // 你可以根据实际情况调整这个范围
+        CoordinatesXY left = coordinatesXIES.get(0);
+        Rect roiRect = new Rect(0, 0, left.getX(), left.getY());
+        Mat roi = new Mat(src, roiRect);
+
+        // 3. 图像预处理 (提高 OCR 准确率)
+        // 3.1 转为灰度图
+        Mat gray = new Mat();
+        Imgproc.cvtColor(roi, gray, Imgproc.COLOR_BGR2GRAY);
+
+        // 3.2 二值化 (Thresholding)
+        // 使用 OTSU 算法自动寻找最佳阈值，或者手动指定阈值
+        Mat binary = new Mat();
+        Imgproc.threshold(gray, binary, 0, 255, Imgproc.THRESH_BINARY | Imgproc.THRESH_OTSU);
+
+        // 可选：保存预处理后的图片查看效果
+        Imgcodecs.imwrite("debug_roi.jpg", binary);
+
+        // 4. 将 OpenCV Mat 转换为 BufferedImage (供 Tess4J 使用)
+        BufferedImage processedImage = matToBufferedImage(binary);
+
+        // 5. 使用 Tesseract 进行 OCR 识别
+        ITesseract instance = new Tesseract();
+        instance.setDatapath(tessdataPath);
+        instance.setLanguage("eng");
+
+        try {
+            String result = instance.doOCR(processedImage);
+            System.out.println("OCR 识别原始内容: \n" + result);
+
+            // 6. 使用正则表达式提取 ID
+            // 匹配 "Assessment_id" 后面的数字
+            Pattern pattern = Pattern.compile("id[:\\s_]+(\\d+)");
+            Matcher matcher = pattern.matcher(result);
+
+            if (matcher.find()) {
+                String id = matcher.group(1);
+                System.out.println("-------------------------");
+                System.out.println("成功提取 ID: " + id);
+                System.out.println("-------------------------");
+                return Integer.parseInt(id);
+            } else {
+                System.out.println("未找到匹配的 ID 格式");
+            }
+
+        } catch (TesseractException e) {
+            System.err.println("OCR 识别出错: " + e.getMessage());
+        }
+        return 0;
+    }
+
+    // 辅助方法：Mat 转 BufferedImage
+    public static BufferedImage matToBufferedImage(Mat m) {
+        int type = BufferedImage.TYPE_BYTE_GRAY;
+        if (m.channels() > 1) {
+            type = BufferedImage.TYPE_3BYTE_BGR;
+        }
+        int bufferSize = m.channels() * m.cols() * m.rows();
+        byte[] b = new byte[bufferSize];
+        m.get(0, 0, b); // 获取所有像素
+        BufferedImage image = new BufferedImage(m.cols(), m.rows(), type);
+        final byte[] targetPixels = ((DataBufferByte) image.getRaster().getDataBuffer()).getData();
+        System.arraycopy(b, 0, targetPixels, 0, b.length);
+        return image;
+    }
+
     private static @NonNull List<CoordinatesXY> getCoordinatesXIES(List<CoordinatesXY> list, int height) {
         List<CoordinatesXY> ans = new ArrayList<>();
         CoordinatesXY left = new CoordinatesXY();

enlish-service/src/main/resources/config/application-dev.yml

@@ -24,5 +24,6 @@ spring:
 templates:
     word: C:\project\java\enlish_edu\enlish\enlish-service\src\main\resources\templates\assessment_v5.docx
     count: 100
+    data: C:\project\tess
 tmp:
     png: C:\project\java\enlish_edu\enlish\enlish-service\src\main\resources\tmp\png

enlish-service/src/test/java/com/yinlihupo/enlish/service/omr/TestOmr.java

@@ -6,6 +6,7 @@ import jakarta.annotation.Resource;
 import lombok.extern.slf4j.Slf4j;
 import nu.pattern.OpenCV;
 import org.junit.jupiter.api.Test;
+import org.springframework.beans.factory.annotation.Value;
 import org.springframework.boot.test.context.SpringBootTest;
 
 import java.util.Arrays;
@@ -15,6 +16,9 @@ import java.util.List;
 @Slf4j
 public class TestOmr {
 
+    @Value("${templates.data}")
+    private String tessdataPath;
+
     @Test
     public void testOmr(){
         OpenCV.loadLocally();
@@ -33,5 +37,11 @@ public class TestOmr {
 
     }
 
-
+    @Test
+    public void testInteger(){
+        String filePath = "C:\\project\\java\\enlish_edu\\enlish\\enlish-service\\src\\main\\resources\\templates\\p3.png";
+        List<CoordinatesXY> coordinatesXIES = PngUtil.analysisXY(filePath);
+        Integer examWordsId = PngUtil.analyzeExamWordsId(filePath, tessdataPath, coordinatesXIES);
+        log.info("examWordsId:{}", examWordsId);
+    }
 }