-
准备工作：
使用之前需要获取对应的项目API_KEY，SECRET_KEY，这些参数在使用API的时候必须用到，用于生成access_token.
如何获取这些参数?
http://ai.baidu.com/tech/ocr/general
登陆后创建一个应用
百度文字识别后台
点击创建应用,填入对应的信息.点击应用列表就可以得到API_KEY，SECRET_KEY了
API_KEY和SECRET_KEY
下载java的SDK,并将jar包引入项目
选择Java SDK
-
获取access_token
package com.baidu.ai.aip.auth;
import org.json.JSONObject;
import java.io.BufferedReader;
import java.io.InputStreamReader;
import java.net.HttpURLConnection;
import java.net.URL;
import java.util.List;
import java.util.Map;
/**
* 获取token类
*/
public class AuthService {
/**
* 获取权限token
* @return 返回示例：
* {
* "access_token": "24.460da4889caad24cccdb1fea17221975.2592000.1491995545.282335-1234567",
* "expires_in": 2592000
* }
*/
public static String getAuth() {
// 官网获取的 API Key 更新为你注册的
String clientId = "百度云应用的AK";
// 官网获取的 Secret Key 更新为你注册的
String clientSecret = "百度云应用的SK";
return getAuth(clientId, clientSecret);
}
/**
* 获取API访问token
* 该token有一定的有效期，需要自行管理，当失效时需重新获取.
* @param ak - 百度云官网获取的 API Key
* @param sk - 百度云官网获取的 Securet Key
* @return assess_token 示例：
* "24.460da4889caad24cccdb1fea17221975.2592000.1491995545.282335-1234567"
*/
public static String getAuth(String ak, String sk) {
// 获取token地址
String authHost = "https://aip.baidubce.com/oauth/2.0/token?";
String getAccessTokenUrl = authHost
// 1. grant_type为固定参数
+ "grant_type=client_credentials"
// 2. 官网获取的 API Key
+ "&client_id=" + ak
// 3. 官网获取的 Secret Key
+ "&client_secret=" + sk;
try {
URL realUrl = new URL(getAccessTokenUrl);
// 打开和URL之间的连接
HttpURLConnection connection = (HttpURLConnection) realUrl.openConnection();
connection.setRequestMethod("GET");
connection.connect();
// 获取所有响应头字段
Map<String, List<String>> map = connection.getHeaderFields();
// 遍历所有的响应头字段
for (String key : map.keySet()) {
System.err.println(key + "--->" + map.get(key));
}
// 定义 BufferedReader输入流来读取URL的响应
BufferedReader in = new BufferedReader(new InputStreamReader(connection.getInputStream()));
String result = "";
String line;
while ((line = in.readLine()) != null) {
result += line;
}
/**
* 返回结果示例
*/
System.err.println("result:" + result);
JSONObject jsonObject = new JSONObject(result);
String access_token = jsonObject.getString("access_token");
return access_token;
} catch (Exception e) {
System.err.printf("获取token失败！");
e.printStackTrace(System.err);
}
return null;
}
}
-
编写将图片转化成base64后再转化成urlencode的工具类
package com.baidu.ai.aip.auth;
import sun.misc.BASE64Encoder;
import java.io.FileInputStream;
import java.io.IOException;
import java.io.InputStream;
import java.net.URLEncoder;
/**
* 图片转化base64后再UrlEncode结果
*/
public class BaseImg64 {
/**
* 将一张本地图片转化成Base64字符串
*/
public static String getImageStrFromPath(String imgPath) {
InputStream in;
byte[] data = null;
// 读取图片字节数组
try {
in = new FileInputStream(imgPath);
data = new byte[in.available()];
in.read(data);
in.close();
} catch (IOException e) {
e.printStackTrace();
}
// 对字节数组Base64编码
BASE64Encoder encoder = new BASE64Encoder();
// 返回Base64编码过再URLEncode的字节数组字符串
return URLEncoder.encode(encoder.encode(data));
}
}
-
编写调用百度API接口的方法，获取识别结果
package com.baidu.ai.aip.auth;
import org.apache.http.HttpResponse;
import org.apache.http.client.HttpClient;
import org.apache.http.client.methods.HttpPost;
import org.apache.http.entity.StringEntity;
import org.apache.http.impl.client.DefaultHttpClient;
import org.apache.http.util.EntityUtils;
import java.io.File;
import java.io.IOException;
import java.net.URI;
import java.net.URISyntaxException;
/**
* 图像文字识别
*/
public class Check {
private static final String POST_URL = "https://aip.baidubce.com/rest/2.0/ocr/v1/general_basic?access_token=" + AuthService.getAuth();
/**
* 识别本地图片的文字
*/
public static String checkFile(String path) throws URISyntaxException, IOException {
File file = new File(path);
if (!file.exists()) {
throw new NullPointerException("图片不存在");
}
String image = BaseImg64.getImageStrFromPath(path);
String param = "image=" + image;
return post(param);
}
/**
* 图片url
* 识别结果，为json格式
*/
public static String checkUrl(String url) throws IOException, URISyntaxException {
String param = "url=" + url;
return post(param);
}
/**
* 通过传递参数：url和image进行文字识别
*/
private static String post(String param) throws URISyntaxException, IOException {
//开始搭建post请求
HttpClient httpClient = new DefaultHttpClient();
HttpPost post = new HttpPost();
URI url = new URI(POST_URL);
post.setURI(url);
//设置请求头，请求头必须为application/x-www-form-urlencoded，因为是传递一个很长的字符串，不能分段发送
post.setHeader("Content-Type", "application/x-www-form-urlencoded");
StringEntity entity = new StringEntity(param);
post.setEntity(entity);
HttpResponse response = httpClient.execute(post);
System.out.println(response.toString());
if (response.getStatusLine().getStatusCode() == 200) {
String str;
try {
//读取服务器返回过来的json字符串数据
str = EntityUtils.toString(response.getEntity());
System.out.println(str);
return str;
} catch (Exception e) {
e.printStackTrace();
return null;
}
}
return null;
}
public static void main(String[] args) {
String path = "test.jpg";
try {
long now = System.currentTimeMillis();
checkFile(path);
System.out.println("耗时：" + (System.currentTimeMillis() - now) / 1000 + "s");
} catch (URISyntaxException | IOException e) {
e.printStackTrace();
}
}
}
-
运行
运行结果
控制台打印:
HTTP/1.1 200 OK [.....] org.apache.http.conn.BasicManagedEntity@ca263c2
{"log_id": 6831958521466827273, "words_result_num": 22, "words_result":
[{"words": "BadU百度"},
{"words": "百度一下"},
{"words": "只我的关注推荐"},
{"words": "导航"},
{"words": "公以下信息根据您的兴趣推荐"},
{"words": "实时热点"}, {"words": "心换"},
{"words": "孙茜回应网友谩骂捆蟹大妈月入万元"},
{"words": "7要开会明,@格溢学长"},
{"words": "杨主席是你们直接@的?”好大的官威"},
{"words": "平文涛欠一个道歉国庆上高速卖炒粉"},
{"words": "啊"}, {"words": "搜狐新闻10-021207"},
{"words": "安倍改组内阁名单摩托车违法闯高速"},
{"words": "EDG开门红"},
{"words": "国有景区门票降价"},
{"words": "警方重新调查罗中国女排vS加"},
{"words": "一样的国庆节,不一样的守护"},
{"words": "女排3-0加拿大"},
{"words": "国防部回应美舰"},
{"words": "德普女儿恋情曝光葛晨虹教授去世"},
{"words": "上海南京路的武警五周杀人案赔偿"}]}
耗时：1s
test.jpg
对比原图片识别率还是很高的,耗时也很短.
我这里只测试了百度的通用识别,如果想提高识别精度,还可以使用高精度识别.
网友评论