Springboot实现OCR文字识别_springboot在线图片识别文字

作者：AllinToyou | 2024-05-25 01:27:41

踩

springboot在线图片识别文字

创建Config


package com.tesseract.tesseract.Config;
 
import net.sourceforge.tess4j.Tesseract;
import org.springframework.beans.factory.annotation.Value;
import org.springframework.context.annotation.Bean;
import org.springframework.context.annotation.Configuration;
 
@Configuration
 
public class TesseractOcrConfig {
 
    @Value("${tesseract.dataPath}")
    private static String dataPath;
 
    @Bean
    public static Tesseract tesseract() {
 
        Tesseract tesseract = new Tesseract();
        // 设置训练数据文件夹路径
        tesseract.setDatapath(dataPath);
        // 设置为中文简体
        tesseract.setLanguage("chi_sim");
        return tesseract;
    }
 
}

创建Service


package com.tesseract.tesseract.Service;
 
import net.sourceforge.tess4j.TesseractException;
import org.springframework.web.multipart.MultipartFile;
 
import java.io.IOException;
 
public interface OcrService {
    public String recognizeText(MultipartFile imageFile)throws IOException, TesseractException;
}

这个是接口，下面是实现


package com.tesseract.tesseract.Service;
 
import net.sourceforge.tess4j.Tesseract;
import net.sourceforge.tess4j.TesseractException;
import org.springframework.stereotype.Service;
import org.springframework.web.multipart.MultipartFile;
 
import javax.imageio.ImageIO;
import java.awt.image.BufferedImage;
import java.io.ByteArrayInputStream;
import java.io.IOException;
import java.io.InputStream;
 
@Service
public class OcrServiceImpl implements OcrService {
 
    private final Tesseract tesseract;
 
    public OcrServiceImpl(Tesseract tesseract) {
        this.tesseract = tesseract;
    }
 
    /**
     *
     * @param imageFile 要识别的图片
     * @return
     */
    @Override
    public String recognizeText(MultipartFile imageFile) throws IOException, TesseractException {
        // 转换
        InputStream sbs = new ByteArrayInputStream(imageFile.getBytes());
        BufferedImage bufferedImage = ImageIO.read(sbs);
 
        // 对图片进行文字识别
        return tesseract.doOCR(bufferedImage);
    }
}

最后就是最重要的Controller了


package com.tesseract.tesseract.Controller;
 
import com.tesseract.tesseract.Service.OcrService;
import lombok.extern.slf4j.Slf4j;
import net.sourceforge.tess4j.TesseractException;
import org.springframework.http.MediaType;
import org.springframework.web.bind.annotation.*;
import org.springframework.web.multipart.MultipartFile;
 
import java.io.IOException;
 
@RestController
@RequestMapping(value = "/api", method = {RequestMethod.GET,RequestMethod.POST})
@Slf4j
public class OcrController {
    private final OcrService ocrService;
 
    public OcrController(OcrService ocrService) {
        this.ocrService = ocrService;
    }
 
    @PostMapping(value = "/recognize", consumes = MediaType.MULTIPART_FORM_DATA_VALUE)
    public String recognizeImage(@RequestParam(value = "file") MultipartFile file) throws TesseractException, IOException {
 
        log.info(ocrService.recognizeText(file));
 
        // 调用OcrService中的方法进行文字识别
        return ocrService.recognizeText(file);
    }
}

最后到网页实现


<!DOCTYPE html>
<html lang="en" xmlns:th="http://www.thymeleaf.org">
<head>
    <meta charset="UTF-8">
    <title>Title</title>
</head>
<body>
<form action="/api/recognize" method="post" enctype="multipart/form-data">
    <input type="file" name="file">
    <input type="submit" value="上传">
</form>
</body>
</html>

然后就是APP


package com.tesseract.tesseract;
 
import org.springframework.boot.SpringApplication;
import org.springframework.boot.autoconfigure.SpringBootApplication;
 
@SpringBootApplication
public class TesseractApplication {
 
    public static void main(String[] args) {
        SpringApplication.run(TesseractApplication.class, args);
    }
 
}

最后看到添加的依赖


<?xml version="1.0" encoding="UTF-8"?>
<project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
         xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 https://maven.apache.org/xsd/maven-4.0.0.xsd">
    <modelVersion>4.0.0</modelVersion>
    <groupId>com.tesseract</groupId>
    <artifactId>tesseract</artifactId>
    <version>0.0.1-SNAPSHOT</version>
    <name>Tesseract</name>
    <description>Demo project for Spring Boot</description>
    <properties>
        <java.version>1.8</java.version>
        <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
        <project.reporting.outputEncoding>UTF-8</project.reporting.outputEncoding>
        <spring-boot.version>2.6.13</spring-boot.version>
    </properties>
    <dependencies>
        <dependency>
            <groupId>org.springframework.boot</groupId>
            <artifactId>spring-boot-starter-thymeleaf</artifactId>
        </dependency>
        <dependency>
            <groupId>org.springframework.boot</groupId>
            <artifactId>spring-boot-starter-web</artifactId>
        </dependency>
 
        <dependency>
            <groupId>org.springframework.boot</groupId>
            <artifactId>spring-boot-starter-test</artifactId>
            <scope>test</scope>
        </dependency>
        <!-- https://mvnrepository.com/artifact/net.sourceforge.tess4j/tess4j -->
        <dependency>
            <groupId>net.sourceforge.tess4j</groupId>
            <artifactId>tess4j</artifactId>
            <version>5.3.0</version>
        </dependency>
        <dependency>
            <groupId>org.projectlombok</groupId>
            <artifactId>lombok</artifactId>
        </dependency>
        <dependency>
            <groupId>org.projectlombok</groupId>
            <artifactId>lombok</artifactId>
            <version>1.18.20</version>
        </dependency>
    </dependencies>
    <dependencyManagement>
        <dependencies>
            <dependency>
                <groupId>org.springframework.boot</groupId>
                <artifactId>spring-boot-dependencies</artifactId>
                <version>${spring-boot.version}</version>
                <type>pom</type>
                <scope>import</scope>
            </dependency>
        </dependencies>
    </dependencyManagement>
 
    <build>
        <plugins>
            <plugin>
                <groupId>org.apache.maven.plugins</groupId>
                <artifactId>maven-compiler-plugin</artifactId>
                <version>3.8.1</version>
                <configuration>
                    <source>1.8</source>
                    <target>1.8</target>
                    <encoding>UTF-8</encoding>
                </configuration>
            </plugin>
            <plugin>
                <groupId>org.springframework.boot</groupId>
                <artifactId>spring-boot-maven-plugin</artifactId>
                <version>${spring-boot.version}</version>
                <configuration>
                    <mainClass>com.tesseract.tesseract.TesseractApplication</mainClass>
                    <skip>true</skip>
                </configuration>
                <executions>
                    <execution>
                        <id>repackage</id>
                        <goals>
                            <goal>repackage</goal>
                        </goals>
                    </execution>
                </executions>
            </plugin>
        </plugins>
    </build>
 
</project>

最最后就是application的配置了


# THYMELEAF (ThymeleafAutoConfiguration)
# å¼å¯æ¨¡æ¿ç¼åï¼é»è®¤å¼ï¼ true ï¼
spring.thymeleaf.cache=true
# æ£æ¥æ¨¡æ¿æ¯å¦åå¨ï¼ç¶åååç°
spring.thymeleaf.check-template=true
# æ£æ¥æ¨¡æ¿ä½ç½®æ¯å¦æ£ç¡®ï¼é»è®¤å¼ :true ï¼
spring.thymeleaf.check-template-location=true
#Content-Type çå¼ï¼é»è®¤å¼ï¼ text/html ï¼
spring.thymeleaf.content-type=text/html
# å¼å¯ MVC Thymeleaf è§å¾è§£æï¼é»è®¤å¼ï¼ true ï¼
spring.thymeleaf.enabled=true
# æ¨¡æ¿ç¼ç 
spring.thymeleaf.encoding=UTF-8
# è¦è¢«æé¤å¨è§£æä¹å¤çè§å¾åç§°åè¡¨ï¼â½¤éå·åé
spring.thymeleaf.excluded-view-names=
# è¦è¿â½¤äºæ¨¡æ¿ä¹ä¸çæ¨¡æ¿æ¨¡å¼ãå¦â» StandardTemplate-ModeHandlers( é»è®¤å¼ï¼ HTML5)
spring.thymeleaf.mode=HTML5
# å¨æå»º URL æ¶æ·»å å°è§å¾åç§°åçåç¼ï¼é»è®¤å¼ï¼ classpath:/templates/ ï¼
spring.thymeleaf.prefix=classpath:/templates/
# å¨æå»º URL æ¶æ·»å å°è§å¾åç§°åçåç¼ï¼é»è®¤å¼ï¼ .html ï¼
spring.thymeleaf.suffix=.html
# åºç¨æå¡ WEB è®¿é®ç«¯å£
server.port=8080
# Tesseract OCRçæ°æ®è·¯å¾éç½®ï¼ç¡®ä¿æååæ¾ .traineddata æä»¶çç®å½
tesseract.dataPath=classpath:/tessdata/

然后不要忘记在添加环境变量

声明：本文内容由网友自发贡献，不代表【wpsshop博客】立场，版权归原作者所有，本站不承担相应法律责任。如您发现有侵权的内容，请联系我们。转载请注明出处：https://www.wpsshop.cn/w/AllinToyou/article/detail/619972