SpringBoot实现图片识别文字的四种方式小结

<!-- tess4j -->
<dependency>
    <groupId>net.sourceforge.tess4j</groupId>
    <artifactId>tess4j</artifactId>
    <version>4.5.4</version>
</dependency>

server:
  port: 8888

# 训练数据文件夹的路径
tess4j:
  datapath: E:/gitee/OCR/tess4j_data

@Configuration

public class TesseractOcrConfig {

    @Value("${tess4j.dataPath}")
    private String dataPath;

    @Bean
    public 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;
    }

}

@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);
    }
}

@RestController
@RequestMapping("/api")
@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("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);
    }
}

<!--百度ocr-->
<dependency>
    <groupId>com.baidu.aip</groupId>
    <artifactId>java-sdk</artifactId>
    <version>4.16.10</version>
</dependency>

server:
  port: 8090

baidu:
  APP_ID: #应用的appid
  API_KEY: #你的app_key
  SECRET_KEY: #你的secret_key

@Setter
@Configuration
@ConfigurationProperties(prefix = "baidu")
public class baiduOcrConfig {

    private String APP_ID;
    private String API_KEY;
    private String SECRET_KEY;

    @Bean
    public AipOcr aipOcr() {
        return new AipOcr(APP_ID, API_KEY, SECRET_KEY);
    }

}

@RestController
@Slf4j
@RequestMapping("/api")
public class BaiduOcrController {


    @Autowired
    private AipOcr aipOcr;

    @PostMapping(value = "/process",consumes = MediaType.MULTIPART_FORM_DATA_VALUE)
    public String processImage(@RequestParam("file") MultipartFile file) {
        HashMap<String, String> options = new HashMap<String, String>();
        options.put("detect_direction", "true");
        options.put("probability", "true");
        try {
            byte[] imageBytes = file.getBytes();
            JSONObject result = aipOcr.basicGeneral(imageBytes, options);

            // 解析百度OCR的识别结果
            StringBuilder sb = new StringBuilder();
            result.getJSONArray("words_result").forEach(item -> {
                JSONObject word = (JSONObject) item;
                sb.append(word.getString("words")).append("\n");
            });

            return sb.toString();
        } catch (IOException e) {
            e.printStackTrace();
            return "Error processing image";
        }

    }

}

<dependency>
  <groupId>com.aliyun</groupId>
  <artifactId>ocr_api20210707</artifactId>
  <version>1.2.0</version>
</dependency>

server:
  port: 8099

aliyun:
  KeyId: #你的KeyId
  KeySecret: #你的KeySecret
  endpoint: ocr-api.cn-hangzhou.aliyuncs.com

@Setter
@Component
@ConfigurationProperties(prefix = "aliyun")
public class AliyunOcrConfig {
    private String KeyId;
    private String KeySecret;
    private String endpoint;

    @Bean
    public Client ocrClient(){
        try {

            Client client = new Client(new Config().setAccessKeyId(KeyId).setAccessKeySecret(KeySecret).setEndpoint(endpoint));
            return client;
        } catch (Exception e) {
            throw new RuntimeException(e);
        }
    }
}

@RestController
@RequestMapping("/api")
@Slf4j
public class AliyunOcrController {

    @Resource
    private Client client;

    @PostMapping(value = "ocr",consumes = MediaType.MULTIPART_FORM_DATA_VALUE)
    public String OcrTest(@RequestParam("file")MultipartFile file) throws IOException {
        RecognizeGeneralRequest request = new RecognizeGeneralRequest();
        request.setBody(file.getInputStream());
        try {
            RecognizeGeneralResponse response = client.recognizeGeneral(request);
            String json = new Gson().toJson(response.getBody());
            String[] split = json.split(",");
            return split[1].split(":")[1].replace("\\","");

//            return json;
        } catch (TeaException error) {
            Common.assertAsString(error.message);
        } catch (Exception e) {
            TeaException error = new TeaException(e.getMessage(), e);
            // 如有需要，请打印 error
            Common.assertAsString(error.message);
        }
        return null;
    }

}

<dependency>
    <groupId>com.tencentcloudapi</groupId>
    <artifactId>tencentcloud-sdk-java</artifactId>
    <version>3.1.909</version>
</dependency>

server:
  port: 9090

tencent:
  SecretId: #你的SecretId
  SecretKey: #你的SecretKey

@Setter
@Configuration
@ConfigurationProperties(prefix = "tencent")
public class TencentOcrConfig {

    private String SecretId;
    private String SecretKey;

    @Bean
    public Credential credential(){
        return new Credential(SecretId,SecretKey);
    }

}

public class ByteToBase64Converter {

    public static String encodeBytesToBase64(byte[] bytes) {
        return Base64.getEncoder().encodeToString(bytes);
    }

}

@RestController
@RequestMapping("/api")
@Slf4j
public class TencentOcrController {
    @Resource
    private Credential credential;


    @PostMapping(value = "/tencent",consumes = MediaType.MULTIPART_FORM_DATA_VALUE)
    public String TencentOCR(@RequestParam("file")MultipartFile file) throws TencentCloudSDKException, IOException {

        // 实例化一个http选项，可选的，没有特殊需求可以跳过
        HttpProfile httpProfile = new HttpProfile();
        httpProfile.setEndpoint("ocr.tencentcloudapi.com");

        // 实例化一个client选项，可选的，没有特殊需求可以跳过
        ClientProfile clientProfile = new ClientProfile();
        clientProfile.setHttpProfile(httpProfile);

        // 实例化要请求产品的client对象,clientProfile是可选的
        OcrClient client = new OcrClient(credential, "ap-guangzhou", clientProfile);

        //将上传的文件转换成base64编码
        String encodeBytesToBase64 = ByteToBase64Converter.encodeBytesToBase64(file.getBytes());


        // 实例化一个请求对象,每个接口都会对应一个request对象
        GeneralBasicOCRRequest req = new GeneralBasicOCRRequest();
        req.setImageBase64(encodeBytesToBase64);

       // req.setImageUrl("https://ltmyblog.oss-cn-shenzhen.aliyuncs.com/myBlog/article/image-20230924213423855.png");

        // 返回的resp是一个GeneralBasicOCRResponse的实例，与请求对象对应
        GeneralBasicOCRResponse resp = client.GeneralBasicOCR(req);


        GeneralBasicOCRResponse.toJsonString(resp);
        // 输出json格式的字符串回包
        System.out.println(GeneralBasicOCRResponse.toJsonString(resp));
        return GeneralBasicOCRResponse.toJsonString(resp);
    }

}