初始化项目

pom.xml

@@ -48,6 +48,13 @@
             <artifactId>spring-boot-starter-test</artifactId>
             <scope>test</scope>
         </dependency>
+
+        <!-- Tess4J 依赖 -->
+        <dependency>
+            <groupId>net.sourceforge.tess4j</groupId>
+            <artifactId>tess4j</artifactId>
+            <version>5.18.0</version>
+        </dependency>
     </dependencies>
     <build>
         <plugins>

src/main/java/com/tem/bocai/config/TessConfig.java

@@ -0,0 +1,18 @@
+package com.tem.bocai.config;
+
+import net.sourceforge.tess4j.Tesseract;
+import org.springframework.context.annotation.Bean;
+import org.springframework.context.annotation.Configuration;
+
+@Configuration
+public class TessConfig {
+
+    @Bean
+    public Tesseract tesseract() {
+
+        Tesseract instance = new Tesseract();
+        instance.setLanguage("oci"); // 设置语言包，这里使用英语
+        instance.setDatapath("src/main/resources/tessdata"); // 设置语言包路径
+        return instance;
+    }
+}

src/main/java/com/tem/bocai/controller/TestController.java

@@ -0,0 +1,37 @@
+package com.tem.bocai.controller;
+
+import com.tem.bocai.util.ImageOcrService;
+import net.sourceforge.tess4j.TesseractException;
+import org.springframework.beans.factory.annotation.Autowired;
+import org.springframework.http.ResponseEntity;
+import org.springframework.web.bind.annotation.GetMapping;
+import org.springframework.web.bind.annotation.RestController;
+
+import java.io.IOException;
+
+@RestController
+public class TestController {
+
+
+    private final ImageOcrService imageOcrService;
+
+    @Autowired
+    public TestController(ImageOcrService imageOcrService) {
+
+        this.imageOcrService = imageOcrService;
+    }
+
+    @GetMapping("/ocr/local")
+    public ResponseEntity<String> ocrLocalImage(String imagePath) throws IOException, TesseractException {
+        imagePath = "b.jpg";
+        String result = imageOcrService.ocrLocalImage(imagePath);
+        return ResponseEntity.ok(result);
+    }
+
+    @GetMapping("/ocr/remote")
+    public ResponseEntity<String> ocrRemoteImage(String imageUrl) throws IOException, TesseractException {
+
+        String result = imageOcrService.ocrRemoteImage(imageUrl);
+        return ResponseEntity.ok(result);
+    }
+}

src/main/java/com/tem/bocai/util/ImageOcrService.java

@@ -0,0 +1,56 @@
+package com.tem.bocai.util;
+
+import net.sourceforge.tess4j.Tesseract;
+import net.sourceforge.tess4j.TesseractException;
+import org.apache.commons.io.IOUtils;
+import org.springframework.beans.factory.annotation.Autowired;
+import org.springframework.core.io.Resource;
+import org.springframework.core.io.ResourceLoader;
+import org.springframework.stereotype.Service;
+
+import javax.imageio.ImageIO;
+import java.awt.image.BufferedImage;
+import java.io.ByteArrayInputStream;
+import java.io.IOException;
+import java.io.InputStream;
+
+@Service
+public class ImageOcrService {
+
+
+    private final Tesseract tesseract;
+    private final ResourceLoader resourceLoader;
+
+    @Autowired
+    public ImageOcrService(Tesseract tesseract, ResourceLoader resourceLoader) {
+
+        this.tesseract = tesseract;
+        this.resourceLoader = resourceLoader;
+    }
+
+    /**
+     * 从本地文件路径读取图片并进行 OCR 处理
+     *
+     * @param imagePath 图片文件路径
+     * @return OCR 结果文本
+     */
+    public String ocrLocalImage(String imagePath) throws IOException, TesseractException {
+
+        InputStream inputStream = getClass().getClassLoader().getResourceAsStream(imagePath);
+        BufferedImage image = ImageIO.read(inputStream);
+        return tesseract.doOCR(image);
+    }
+
+    /**
+     * 从远程 URL 获取图片并进行 OCR 处理
+     *
+     * @param imageUrl 图片 URL
+     * @return OCR 结果文本
+     */
+    public String ocrRemoteImage(String imageUrl) throws IOException, TesseractException {
+
+        byte[] imageData = IOUtils.toByteArray(new ByteArrayInputStream(IOUtils.toByteArray(imageUrl)));
+        BufferedImage image = ImageIO.read(new ByteArrayInputStream(imageData));
+        return tesseract.doOCR(image);
+    }
+}