印刷文字识别-身份证

公司要求作身份证识别，一开始在网上搜索java方面有Tesseract-OCR的开源技术识别率可以达到99.99%。但真正接触下来，是说这个技术识别率可以达到99.99%，但需要大量的训练数据，也就是人工智能那一套。搞了半天根本达不到理想要求。那有没有其他办法那，查找了下中国的3大巨头公司阿里，腾讯、百度都有提供身份证识别接口。那就走调用第三方的方法吧。我选择了阿里。

前提：

1、需要申请一个阿里账号，有淘宝号的用淘宝号登录也可以。

2、然后在云市场搜索“印刷文字识别-身份证”。

3、阿里免费提供500次识别。需要购买该产品。

4、产品购买成功后，获取appcode值，这个要放到header中去的。

5、就可调用用了。

需要的jar包：

Maven项目直接配置依赖就可以，非maven项目就需要导入jar包：

Commons-lang-2.4.jar、fastjson-1.2.7.jar、httpclient-4.5.6.jar、httpcode-4.4.10.jar、servlet-api.jar基本这几个就够用了。

官方文档：https://market.aliyun.com/products/57124001/cmapi010401.html?spm=5176.730005.productlist.d_cmapi010401.stMjsY#sku=yuncode440100000

其他的不说调用代码如下：

import com.alibaba.fastjson.JSON;
import com.alibaba.fastjson.JSONArray;
import com.alibaba.fastjson.JSONException;
import com.alibaba.fastjson.JSONObject;
import com.aliyun.api.gateway.demo.util.HttpUtils;
import org.apache.http.HttpResponse;
import org.apache.http.util.EntityUtils;

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

import static org.apache.commons.codec.binary.Base64.encodeBase64;



/**
 * 使用APPCODE进行云市场ocr服务接口调用
 */

public class APPCodeDemo {

    /*
     * 获取参数的json对象
     */
    public static JSONObject getParam(int type, String dataValue) {
        JSONObject obj = new JSONObject();
        try {
            obj.put("dataType", type);
            obj.put("dataValue", dataValue);
        } catch (JSONException e) {
            e.printStackTrace();
        }
        return obj;
    }

    public static void main(String[] args){

        String host = "http://dm-51.data.aliyun.com";
        String path = "/rest/160601/ocr/ocr_idcard.json";
        String appcode = "你的APPCODE";
        String imgFile = "图片路径";
        Boolean is_old_format = false;//如果文档的输入中含有inputs字段，设置为True， 否则设置为False
        //请根据线上文档修改configure字段
        JSONObject configObj = new JSONObject();
        configObj.put("side", "face");
        String config_str = configObj.toString();
        //            configObj.put("min_size", 5);
        //            String config_str = "";

        String method = "POST";
        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);

        Map<String, String> querys = new HashMap<String, String>();

        // 对图像进行base64编码
        String imgBase64 = "";
        try {
            File file = new File(imgFile);
            byte[] content = new byte[(int) file.length()];
            FileInputStream finputstream = new FileInputStream(file);
            finputstream.read(content);
            finputstream.close();
            imgBase64 = new String(encodeBase64(content));
        } catch (IOException e) {
            e.printStackTrace();
            return;
        }
        // 拼装请求body的json字符串
        JSONObject requestObj = new JSONObject();
        try {
            if(is_old_format) {
                JSONObject obj = new JSONObject();
                obj.put("image", getParam(50, imgBase64));
                if(config_str.length() > 0) {
                    obj.put("configure", getParam(50, config_str));
                }
                JSONArray inputArray = new JSONArray();
                inputArray.add(obj);
                requestObj.put("inputs", inputArray);
            }else{
                requestObj.put("image", imgBase64);
                if(config_str.length() > 0) {
                    requestObj.put("configure", config_str);
                }
            }
        } catch (JSONException e) {
            e.printStackTrace();
        }
        String bodys = requestObj.toString();

        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);
            int stat = response.getStatusLine().getStatusCode();
            if(stat != 200){
                System.out.println("Http code: " + stat);
                System.out.println("http header error msg: "+ response.getFirstHeader("X-Ca-Error-Message"));
                System.out.println("Http body error msg:" + EntityUtils.toString(response.getEntity()));
                return;
            }

            String res = EntityUtils.toString(response.getEntity());
            JSONObject res_obj = JSON.parseObject(res);
            if(is_old_format) {
                JSONArray outputArray = res_obj.getJSONArray("outputs");
                String output = outputArray.getJSONObject(0).getJSONObject("outputValue").getString("dataValue");
                JSONObject out = JSON.parseObject(output);
                System.out.println(out.toJSONString());
            }else{
                System.out.println(res_obj.toJSONString());
            }
        } catch (Exception e) {
            e.printStackTrace();
        }
    }
}

工具类HttpUtils:

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;

public class HttpUtils {

    /**
     * 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);
        }
    }
}

识别结果正确率已经达到可用。

{"sex":"男","num":"410527**********","birth":"1990**","request_id":"20180801150222_a325b5b8ea94c5c3ab2b7c98310252ef","nationality":"汉","address":"河南省******","name":"***","config_str":"{"side":"face"}","success":true,"face_rect":{"center":{"y":488,"x":1412},"angle":-90,"size":{"height":240,"width":208}}}