JAVA演示阿里云图像识别API,印刷文字识别-营业执照识别

2020年3月13日21:05:48JAVA演示阿里云图像识别API,印刷文字识别-营业执照识别已关闭评论 706 16524字阅读55分4秒
摘要

最近有由于工作需要,开始接触阿里云的云市场的印刷文字识别API-营业执照识别这里我加上了官网的申请说明,只要你有阿里云账号就可以用,前500次是免费的,API说明很简陋,只能做个简单参考

最近有由于需要,我开始接触阿里云的云市场的印刷文字识别-营业执照识别这里我加上了官网的申请说明,只要你有阿里云账号就可以用,前500次是免费的,API说明很简陋,只能做个简单参考。

一、API介绍

JAVA示例: 

public static void main(String[] args) {
   String host = "https://dm-58.data.aliyun.com";
   String path = "/rest/160601/ocr/ocr_business_license.json";
   String method = "POST";
   String appcode = "你自己的AppCode";
   Map<String, String> headers = new HashMap<String, String>();
   //最后在header中的格式(中间是英文空格)为Authorization:APPCODE 83359fd73fe94948385f570e3c139105
   headers.put("Authorization", "APPCODE " + appcode);
   //根据API的要求,定义相对应的Content-Type
   headers.put("Content-Type", "application/json; charset=UTF-8");
   Map<String, String> querys = new HashMap<String, String>();
   String bodys = "{\"image\":\"对图片内容进行Base64编码\"}";


   try {
   /**
   * 重要提示如下:
   * HttpUtils请从
   * https://github.com/aliyun/api-gateway-demo-sign-java/blob/master/src/main/java/com/aliyun/api/gateway/demo/util/HttpUtils.java
   * 下载
   *
   * 相应的依赖请参照
   * https://github.com/aliyun/api-gateway-demo-sign-java/blob/master/pom.xml
   */
   HttpResponse response = HttpUtils.doPost(host, path, method, headers, querys, bodys);
   System.out.println(response.toString());
   //获取response的body
   //System.out.println(EntityUtils.toString(response.getEntity()));
   } catch (Exception e) {
   e.printStackTrace();
   }
 }

返回码:

{
  "config_str" : "null\n", #配置字符串信息
  "angle" : float, #输入图片的角度(顺时针旋转),[0, 90, 180,270]
  "reg_num" : string, #注册号,没有识别出来时返回"FailInRecognition"
  "name" : string, #公司名称,没有识别出来时返回"FailInRecognition"
  "type" : string, #公司类型,没有识别出来时返回"FailInRecognition"
  "person" : string, #公司法人,没有识别出来时返回"FailInRecognition"
  "establish_date": string, #公司注册日期(例:证件上为"2014年04月16日",算法返回"20140416")
  "valid_period": string, #公司营业期限终止日期(例:证件上为"2014年04月16日至2034年04月15日",算法返回"20340415")
  #当前算法将日期格式统一为输出为"年月日"(如"20391130"),并将"长期"表示为"29991231",若证件上没有营业期限,则默认其为"长期",返回"29991231"。
  "address" : string, #公司地址,没有识别出来时返回"FailInRecognition"
  "capital" : string, #注册资本,没有识别出来时返回"FailInRecognition"
  "business": string, #经营范围,没有识别出来时返回"FailInRecognition"
  "emblem" : string, #国徽位置[top,left,height,width],没有识别出来时返回"FailInDetection"
  "title" : string, #标题位置[top,left,height,width],没有识别出来时返回"FailInDetection"
  "stamp" : string, #印章位置[top,left,height,width],没有识别出来时返回"FailInDetection"
  "qrcode" : string, #二维码位置[top,left,height,width],没有识别出来时返回"FailInDetection"
  "success" : bool, #识别成功与否 true/false
  "request_id": string
}

购买后,在云市场列表里展示,你可要点击进去查看AppCode等其主要信息(接口调用里需要AppCode)

简单的API介绍,但挺有效了的,唯一不好的就是没有错误返回码的描述,需要自己测试。

二、代码开发

闲话少说,上代码:

AliyunImageRecognitionUtil :阿里云图像识别工具类

package com.casic.cloud.qcy.util;

import java.io.FileInputStream;
import java.io.IOException;
import java.io.InputStream;
import java.util.HashMap;
import java.util.Map;

import org.apache.http.HttpResponse;
import org.apache.http.util.EntityUtils;
import org.springframework.web.multipart.commons.CommonsMultipartFile;

import com.alibaba.fastjson.JSONObject;
import com.casic.cloud.qcy.constant.Constants;

import sun.misc.BASE64Encoder;

/** 
 * @ClassName: AliyunImageRecognitionUtil 
 * @Description: 阿里云图像识别工具类
 * @author: tianpengw
 * @date 2019年3月21日 上午8:49:08 
 * 
 */
public class AliyunImageRecognitionUtil {

 private static String businessLicenceHost = PropertiesUtil.getProperties("businessLicenceHost");
 
 private static String businessLicencePath = PropertiesUtil.getProperties("businessLicencePath");
 
 private static String method = "POST";
 
 private static String appCode = PropertiesUtil.getProperties("appCode");
 

 /**
 * 
 * @Description: 根据文件全路径识别
 * @author: tianpengw
 * @param imgPath
 * @return
 */
 public static Map<String,Object> bussinessLicenceRecognition(String imgPath){
 Map<String,Object> resultMap = new HashMap<String,Object>();
 
 Map<String, String> headers = new HashMap<String, String>();
 //最后在header中的格式(中间是英文空格)为Authorization:APPCODE 83359fd73fe94948385f570e3c139105
   headers.put("Authorization", "APPCODE " + appCode);
   headers.put("Content-Type", "application/json; charset=UTF-8");
   
   Map<String, String> querys = new HashMap<String, String>();
   String bodys = "{\"image\":\""+imageToBase64Str(imgPath)+"\"}";
   try {
   /**
   * 重要提示如下:
   * HttpUtils请从
   * https://github.com/aliyun/api-gateway-demo-sign-java/blob/master/src/main/java/com/aliyun/api/gateway/demo/util/HttpUtils.java
   * 下载
   *
   * 相应的依赖请参照
   * https://github.com/aliyun/api-gateway-demo-sign-java/blob/master/pom.xml
   */
   HttpResponse response = AliyunHttpUtils.doPost(businessLicenceHost, businessLicencePath, method, headers, querys, bodys);
   String resStr = EntityUtils.toString(response.getEntity());
   System.out.println(resStr);
   
   resultMap = JSONObject.parseObject(resStr, Map.class);
   //获取response的body
   } catch (Exception e) {
   e.printStackTrace();
   }
   return resultMap;
 }
 
 /**
 * 
 * @Description: 根据InputStream识别
 * @author: tianpengw
 * @param imgPath
 * @return
 */
 public static Map<String,Object> bussinessLicenceRecognition(InputStream inputStream){
 Map<String,Object> resultMap = new HashMap<String,Object>();
 
 Map<String, String> headers = new HashMap<String, String>();
 //最后在header中的格式(中间是英文空格)为Authorization:APPCODE 83359fd73fe94948385f570e3c139105
   headers.put("Authorization", "APPCODE " + appCode);
   headers.put("Content-Type", "application/json; charset=UTF-8");
   
   Map<String, String> querys = new HashMap<String, String>();
   // 加密
   BASE64Encoder encoder = new BASE64Encoder();
   byte[] data = null;
   try {
    data = new byte[inputStream.available()];
    inputStream.read(data);
    inputStream.close();
   } catch (IOException e) {
    e.printStackTrace();
   }
   String bodys = "{\"image\":\""+encoder.encode(data)+"\"}";
   try {
   /**
   * 重要提示如下:
   * HttpUtils请从
   * https://github.com/aliyun/api-gateway-demo-sign-java/blob/master/src/main/java/com/aliyun/api/gateway/demo/util/HttpUtils.java
   * 下载
   *
   * 相应的依赖请参照
   * https://github.com/aliyun/api-gateway-demo-sign-java/blob/master/pom.xml
   */
   HttpResponse response = AliyunHttpUtils.doPost(businessLicenceHost, businessLicencePath, method, headers, querys, bodys);
   String resStr = EntityUtils.toString(response.getEntity());
   System.out.println(resStr);
   
   resultMap = JSONObject.parseObject(resStr, Map.class);
   resultMap.put("errCode", Constants.RESULT_SUCCESS);
   //获取response的body
   } catch (Exception e) {
   e.printStackTrace();
   resultMap.put("errCode", Constants.RESULT_FAIL);
   }
   return resultMap;
 }

 /**
 * 
 * @Description: 根据byte[]识别
 * @author: tianpengw
 * @param imgPath
 * @return
 */
 public static Map<String,Object> bussinessLicenceRecognition( byte[] data){
 Map<String,Object> resultMap = new HashMap<String,Object>();
 
 Map<String, String> headers = new HashMap<String, String>();
 //最后在header中的格式(中间是英文空格)为Authorization:APPCODE 83359fd73fe94948385f570e3c139105
   headers.put("Authorization", "APPCODE " + appCode);
   headers.put("Content-Type", "application/json; charset=UTF-8");
   
   Map<String, String> querys = new HashMap<String, String>();
   // 加密
   BASE64Encoder encoder = new BASE64Encoder();
   
   String bodys = "{\"image\":\""+encoder.encode(data)+"\"}";
   try {
   /**
   * 重要提示如下:
   * HttpUtils请从
   * https://github.com/aliyun/api-gateway-demo-sign-java/blob/master/src/main/java/com/aliyun/api/gateway/demo/util/HttpUtils.java
   * 下载
   *
   * 相应的依赖请参照
   * https://github.com/aliyun/api-gateway-demo-sign-java/blob/master/pom.xml
   */
   HttpResponse response = AliyunHttpUtils.doPost(businessLicenceHost, businessLicencePath, method, headers, querys, bodys);
   String resStr = EntityUtils.toString(response.getEntity());
   System.out.println(resStr);
   
   resultMap = JSONObject.parseObject(resStr, Map.class);
   resultMap.put("errCode", Constants.RESULT_SUCCESS);
   //获取response的body
   } catch (Exception e) {
   e.printStackTrace();
   resultMap.put("errCode", Constants.RESULT_FAIL);
   }
   return resultMap;
 }

 
 /**
  * 图片转base64字符串
  * @param imgFile 图片路径
  * @return
  */
  public static String imageToBase64Str(String imgFile) {
   InputStream inputStream = null;
   byte[] data = null;
   try {
    inputStream = new FileInputStream(imgFile);
    data = new byte[inputStream.available()];
    inputStream.read(data);
    inputStream.close();
   } catch (IOException e) {
    e.printStackTrace();
   }
   // 加密
   BASE64Encoder encoder = new BASE64Encoder();
   return encoder.encode(data);
  }
  
  public static void main(String[] args) {
 String imgPath = "d:/yyzznew1.jpg";
 Map<String,Object> map = AliyunImageRecognitionUtil.bussinessLicenceRecognition(imgPath);
 System.out.println(map.get("person"));
 System.out.println(map.get("reg_num"));
 }
}

AliyunHttpUtils :阿里云httpUtils

package com.casic.cloud.qcy.util;

import java.io.UnsupportedEncodingException;
import java.net.URLEncoder;
import java.security.KeyManagementException;
import java.security.NoSuchAlgorithmException;
import java.security.cert.X509Certificate;
import java.util.ArrayList;
import java.util.List;
import java.util.Map;

import javax.net.ssl.SSLContext;
import javax.net.ssl.TrustManager;
import javax.net.ssl.X509TrustManager;

import org.apache.commons.lang.StringUtils;
import org.apache.http.HttpResponse;
import org.apache.http.NameValuePair;
import org.apache.http.client.HttpClient;
import org.apache.http.client.entity.UrlEncodedFormEntity;
import org.apache.http.client.methods.HttpDelete;
import org.apache.http.client.methods.HttpGet;
import org.apache.http.client.methods.HttpPost;
import org.apache.http.client.methods.HttpPut;
import org.apache.http.conn.ClientConnectionManager;
import org.apache.http.conn.scheme.Scheme;
import org.apache.http.conn.scheme.SchemeRegistry;
import org.apache.http.conn.ssl.SSLSocketFactory;
import org.apache.http.entity.ByteArrayEntity;
import org.apache.http.entity.StringEntity;
import org.apache.http.impl.client.DefaultHttpClient;
import org.apache.http.message.BasicNameValuePair;

/** 
 * @ClassName: AliyunHttpUtils 
 * @Description: 
 * @author: tianpengw
 * @date 2019年3月21日 上午8:44:51 
 * 
 */
public class AliyunHttpUtils {

 /**
 * get
 * 
 * @param host
 * @param path
 * @param method
 * @param headers
 * @param querys
 * @return
 * @throws Exception
 */
 public static HttpResponse doGet(String host, String path, String method, 
  Map<String, String> headers, 
  Map<String, String> querys)
      throws Exception {   
   HttpClient httpClient = wrapClient(host);

   HttpGet request = new HttpGet(buildUrl(host, path, querys));
    for (Map.Entry<String, String> e : headers.entrySet()) {
     request.addHeader(e.getKey(), e.getValue());
    }
    
    return httpClient.execute(request);
  }
 
 /**
 * post form
 * 
 * @param host
 * @param path
 * @param method
 * @param headers
 * @param querys
 * @param bodys
 * @return
 * @throws Exception
 */
 public static HttpResponse doPost(String host, String path, String method, 
  Map<String, String> headers, 
  Map<String, String> querys, 
  Map<String, String> bodys)
      throws Exception {   
   HttpClient httpClient = wrapClient(host);

   HttpPost request = new HttpPost(buildUrl(host, path, querys));
    for (Map.Entry<String, String> e : headers.entrySet()) {
     request.addHeader(e.getKey(), e.getValue());
    }

    if (bodys != null) {
      List<NameValuePair> nameValuePairList = new ArrayList<NameValuePair>();

      for (String key : bodys.keySet()) {
        nameValuePairList.add(new BasicNameValuePair(key, bodys.get(key)));
      }
      UrlEncodedFormEntity formEntity = new UrlEncodedFormEntity(nameValuePairList, "utf-8");
      formEntity.setContentType("application/x-www-form-urlencoded; charset=UTF-8");
      request.setEntity(formEntity);
    }

    return httpClient.execute(request);
  } 
 
 /**
 * Post String
 * 
 * @param host
 * @param path
 * @param method
 * @param headers
 * @param querys
 * @param body
 * @return
 * @throws Exception
 */
 public static HttpResponse doPost(String host, String path, String method, 
  Map<String, String> headers, 
  Map<String, String> querys, 
  String body)
      throws Exception {   
   HttpClient httpClient = wrapClient(host);

   HttpPost request = new HttpPost(buildUrl(host, path, querys));
    for (Map.Entry<String, String> e : headers.entrySet()) {
     request.addHeader(e.getKey(), e.getValue());
    }

    if (StringUtils.isNotBlank(body)) {
     request.setEntity(new StringEntity(body, "utf-8"));
    }

    return httpClient.execute(request);
  }
 
 /**
 * Post stream
 * 
 * @param host
 * @param path
 * @param method
 * @param headers
 * @param querys
 * @param body
 * @return
 * @throws Exception
 */
 public static HttpResponse doPost(String host, String path, String method, 
  Map<String, String> headers, 
  Map<String, String> querys, 
  byte[] body)
      throws Exception {   
   HttpClient httpClient = wrapClient(host);

   HttpPost request = new HttpPost(buildUrl(host, path, querys));
    for (Map.Entry<String, String> e : headers.entrySet()) {
     request.addHeader(e.getKey(), e.getValue());
    }

    if (body != null) {
     request.setEntity(new ByteArrayEntity(body));
    }

    return httpClient.execute(request);
  }
 
 /**
 * Put String
 * @param host
 * @param path
 * @param method
 * @param headers
 * @param querys
 * @param body
 * @return
 * @throws Exception
 */
 public static HttpResponse doPut(String host, String path, String method, 
  Map<String, String> headers, 
  Map<String, String> querys, 
  String body)
      throws Exception {   
   HttpClient httpClient = wrapClient(host);

   HttpPut request = new HttpPut(buildUrl(host, path, querys));
    for (Map.Entry<String, String> e : headers.entrySet()) {
     request.addHeader(e.getKey(), e.getValue());
    }

    if (StringUtils.isNotBlank(body)) {
     request.setEntity(new StringEntity(body, "utf-8"));
    }

    return httpClient.execute(request);
  }
 
 /**
 * Put stream
 * @param host
 * @param path
 * @param method
 * @param headers
 * @param querys
 * @param body
 * @return
 * @throws Exception
 */
 public static HttpResponse doPut(String host, String path, String method, 
  Map<String, String> headers, 
  Map<String, String> querys, 
  byte[] body)
      throws Exception {   
   HttpClient httpClient = wrapClient(host);

   HttpPut request = new HttpPut(buildUrl(host, path, querys));
    for (Map.Entry<String, String> e : headers.entrySet()) {
     request.addHeader(e.getKey(), e.getValue());
    }

    if (body != null) {
     request.setEntity(new ByteArrayEntity(body));
    }

    return httpClient.execute(request);
  }
 
 /**
 * Delete
 * 
 * @param host
 * @param path
 * @param method
 * @param headers
 * @param querys
 * @return
 * @throws Exception
 */
 public static HttpResponse doDelete(String host, String path, String method, 
  Map<String, String> headers, 
  Map<String, String> querys)
      throws Exception {   
   HttpClient httpClient = wrapClient(host);

   HttpDelete request = new HttpDelete(buildUrl(host, path, querys));
    for (Map.Entry<String, String> e : headers.entrySet()) {
     request.addHeader(e.getKey(), e.getValue());
    }
    
    return httpClient.execute(request);
  }
 
 private static String buildUrl(String host, String path, Map<String, String> querys) throws UnsupportedEncodingException {
   StringBuilder sbUrl = new StringBuilder();
   sbUrl.append(host);
   if (!StringUtils.isBlank(path)) {
   sbUrl.append(path);
    }
   if (null != querys) {
   StringBuilder sbQuery = new StringBuilder();
     for (Map.Entry<String, String> query : querys.entrySet()) {
     if (0 < sbQuery.length()) {
      sbQuery.append("&");
     }
     if (StringUtils.isBlank(query.getKey()) && !StringUtils.isBlank(query.getValue())) {
      sbQuery.append(query.getValue());
        }
     if (!StringUtils.isBlank(query.getKey())) {
      sbQuery.append(query.getKey());
      if (!StringUtils.isBlank(query.getValue())) {
      sbQuery.append("=");
      sbQuery.append(URLEncoder.encode(query.getValue(), "utf-8"));
      }      
        }
     }
     if (0 < sbQuery.length()) {
     sbUrl.append("?").append(sbQuery);
     }
    }
   
   return sbUrl.toString();
  }
 
 private static HttpClient wrapClient(String host) {
 HttpClient httpClient = new DefaultHttpClient();
 if (host.startsWith("https://")) {
  sslClient(httpClient);
 }
 
 return httpClient;
 }
 
 private static void sslClient(HttpClient httpClient) {
    try {
      SSLContext ctx = SSLContext.getInstance("TLS");
      X509TrustManager tm = new X509TrustManager() {
        public X509Certificate[] getAcceptedIssuers() {
          return null;
        }
        public void checkClientTrusted(X509Certificate[] xcs, String str) {
         
        }
        public void checkServerTrusted(X509Certificate[] xcs, String str) {
         
        }
      };
      ctx.init(null, new TrustManager[] { tm }, null);
      SSLSocketFactory ssf = new SSLSocketFactory(ctx);
      ssf.setHostnameVerifier(SSLSocketFactory.ALLOW_ALL_HOSTNAME_VERIFIER);
      ClientConnectionManager ccm = httpClient.getConnectionManager();
      SchemeRegistry registry = ccm.getSchemeRegistry();
      registry.register(new Scheme("https", 443, ssf));
    } catch (KeyManagementException ex) {
      throw new RuntimeException(ex);
    } catch (NoSuchAlgorithmException ex) {
     throw new RuntimeException(ex);
    }
  }
}

PropertiesUtil :读取配置文件工具

package com.casic.cloud.qcy.util;

import java.io.IOException;
import java.io.InputStream;
import java.util.Properties;

import org.apache.logging.log4j.LogManager;
import org.apache.logging.log4j.Logger;

/** 
 * @ClassName: PropertiesUtil 
 * @Description: 
 * @author tianpengw
 * @date 2018年6月27日 下午3:09:08 
 * 
 */
public class PropertiesUtil {

 private static Logger log = LogManager.getLogger(PropertiesUtil.class);
 
 private static Properties prop;
 
 static{
 try{
  if(null == prop){
  prop = new Properties();
  }
  InputStream fis = null;
  fis = ClassLoaderUtils.getResourceAsStream("common.properties", PropertiesUtil.class);
  if(fis!=null){
  prop.load(fis);// 将属性文件流装载到Properties对象中  
  fis.close();// 关闭流  
  }
 }catch (Exception e) {
  log.error("读取配置文件出错:" + e );
 }
 }
 
 /**
 * 
 * @Description: 根据key获取配置的值
 * @author tianpengw 
 * @param key
 * @return
 */
 public static String getProperties(String key){
 if(key==null) return null;
 return prop.getProperty(key);
 
 }
 
 
 /**
 * 
 * @Description: 
 * @author tianpengw 
 * @param proper 读取配置的文件名称
 * @param key
 * @return
 */
 public static String getPropertie(String resourceName,String key){
 InputStream fis = ClassLoaderUtils.getResourceAsStream(resourceName, PropertiesUtil.class);
 if(fis!=null){
  try {
  prop.load(fis);
  fis.close();// 关闭流  
  } catch (IOException e) {
  e.printStackTrace();
  }  
  
 }
 if(key==null) return null;
 return prop.getProperty(key);
 }
 
 
 /**
 * 
 * @Description: 根据key获取配置的值,若没有,则取传过来的默认的值
 * @author tianpengw 
 * @param key
 * @param defaultValue 默认值
 * @return
 */
 public static String getProperties(String key,String defaultValue){
 if(key==null) return null;
 return prop.getProperty(key, defaultValue);
 
 }
}

配置文件common.properties(放在 src/main/resources下)

#aliyun business licence recognition
businessLicenceHost = https://dm-58.data.aliyun.com
businessLicencePath = /rest/160601/ocr/ocr_business_license.json
appCode = XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX

三、测试结果

成功的结果:

失败结果,当处理非营业执照的图片时将会返回“invalid business licence”结果,我这么没有进行判断处理直接按照正确的json解析,所以报错,此处你们可以按照自己需求选择处理逻辑。从这返回结果也看的出该接口做的不合理,返回内容不统一,导致接口使用者,必须知晓各种情况才能做有效的处理,如果此处能返回json串,给错误码那对于调用者来说就方便多了。

四、后记

此API适合一般的营业执照和新的三证合一的营业执照,但是字段获取的含义不同,此处需要注意;
由于API并未列出错误码,在未知的错误情况还包含识别次数不够的时候是报错还是有错误提示(由于条件限制,此情况无法验证);

工具是死的,人是活的,开发需要考虑尽可能多的情况,来保证代码的完善。
至此,工具介绍完毕,欢迎交流。

继续阅读
历史上的今天
三月
13
编程十万个怎么办