spring boot tesseract-ocr

Spring Boot与Tesseract-OCR结合使用可以实现图片识别文字的功能。下面是四种实现方式：

1. 使用Tesseract-OCR命令行工具

import org.springframework.boot.CommandLineRunner;
import org.springframework.stereotype.Component;

@Component
public class TesseractOCRCommandLineRunner implements CommandLineRunner {

    @Override
    public void run(String... args) throws Exception {
        // 调用Tesseract-OCR命令行工具进行图片识别文字
        String command = "tesseract image.png output";
        Process process = Runtime.getRuntime().exec(command);
        process.waitFor();
    }
}

2. 使用Tesseract-OCR的Java API

import net.sourceforge.tess4j.Tesseract;
import net.sourceforge.tess4j.TesseractException;
import org.springframework.stereotype.Component;

@Component
public class TesseractOCRJavaAPI {

    public String recognizeText(String imagePath) throws TesseractException {
        Tesseract tesseract = new Tesseract();
        tesseract.setDatapath("path/to/tessdata"); // 设置tessdata目录的路径
        return tesseract.doOCR(new File(imagePath));
    }
}

3. 使用Spring Boot集成的Tesseract-OCR Starter
在pom.xml文件中添加以下依赖：

<dependency>
    <groupId>net.sourceforge.tess4j</groupId>
    <artifactId>tess4j-spring-boot-starter</artifactId>
    <version>4.5.1</version>
</dependency>

然后在代码中使用TesseractOCRService进行图片识别文字：

import net.sourceforge.tess4j.TesseractException;
import org.springframework.beans.factory.annotation.Autowired;
import org.springframework.stereotype.Component;

@Component
public class TesseractOCRService {

    @Autowired
    private TesseractOCR tesseractOCR;

    public String recognizeText(String imagePath) throws TesseractException {
        return tesseractOCR.doOCR(new File(imagePath));
    }
}

4. 使用Spring Boot集成的Tesseract-OCR Starter和Spring Cloud Stream
在pom.xml文件中添加以下依赖：

<dependency>
    <groupId>net.sourceforge.tess4j</groupId>
    <artifactId>tess4j-spring-boot-starter</artifactId>
    <version>4.5.1</version>
</dependency>
<dependency>
    <groupId>org.springframework.cloud</groupId>
    <artifactId>spring-cloud-stream-binder-kafka</artifactId>
</dependency>

然后在代码中使用TesseractOCRProcessor进行图片识别文字：

import net.sourceforge.tess4j.TesseractException;
import org.springframework.beans.factory.annotation.Autowired;
import org.springframework.cloud.stream.annotation.EnableBinding;
import org.springframework.cloud.stream.annotation.StreamListener;
import org.springframework.cloud.stream.messaging.Processor;
import org.springframework.messaging.handler.annotation.Payload;
import org.springframework.stereotype.Component;

@Component
@EnableBinding(Processor.class)
public class TesseractOCRProcessor {

    @Autowired
    private TesseractOCR tesseractOCR;

    @StreamListener(Processor.INPUT)
    public void processImage(@Payload byte[] imageBytes) throws TesseractException {
        String text = tesseractOCR.doOCR(imageBytes);
        // 处理识别到的文字
    }
}