第一句子网 > Java-基于百度API的图片文字识别（支持中文英文和中英文混合）

Java-基于百度API的图片文字识别（支持中文英文和中英文混合）

时间：2019-10-06 05:49:43

具体文档：/docs#/OCR-API/e1bd77f3

PS：

基于Java 1.8

版本控制：maven

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：在百度开发者中心申请一个“通用文字识别”项目，然后就可以获取到这些参数。

准备条件都完成了，现在开始进行图像识别了。

Github地址：/wsk1103/baidu

test4j图片文字识别教程：/wsk1103/article/details/54173282

1. 准备pom文件

<dependency><groupId>com.alibaba</groupId><artifactId>fastjson</artifactId><version>1.2.46</version></dependency><dependency><groupId>org.apache.httpcomponents</groupId><artifactId>httpclient</artifactId><version>4.5.5</version></dependency>

2. 获取access_token

package ty.check;import org.json.JSONObject;import java.io.BufferedReader;import java.io.InputStreamReader;import .HttpURLConnection;import .URL;import java.util.List;import java.util.Map;/*** 获取token类** @Author : WuShukai* @Date :/2/12 10:04*/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 = "**";// 官网获取的 Secret Key 更新为你注册的String clientSecret = "**";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"*/private static String getAuth(String ak, String sk) {// 获取token地址String authHost = "/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()));StringBuilder result = new StringBuilder();String line;while ((line = in.readLine()) != null) {result.append(line);}/*** 返回结果示例*/System.err.println("result:" + result);JSONObject jsonObject = new JSONObject(result.toString());return jsonObject.getString("access_token");} catch (Exception e) {System.err.printf("获取token失败！");e.printStackTrace(System.err);}return null;}public static void main(String[] args) {getAuth();}}

3. 编写将图片转化成base64后再转化成urlencode的工具类

package ty.check;import sun.misc.BASE64Encoder;import java.io.FileInputStream;import java.io.IOException;import java.io.InputStream;import .URLEncoder;/*** 图片转化base64后再UrlEncode结果* @Author : WuShukai* @Date :/2/12 10:43*/public class BaseImg64 {/*** 将一张本地图片转化成Base64字符串* @param imgPath 本地图片地址* @return 图片转化base64后再UrlEncode结果*/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));}}

4. 编写调用百度API接口的方法，获取识别结果

package ty.check;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 .URI;import .URISyntaxException;/*** 图像文字识别** @Author : WuShukai* @Date :/2/12 10:25*/public class Check {private static final String POST_URL = "/rest/2.0/ocr/v1/general_basic?access_token=" + AuthService.getAuth();/*** 识别本地图片的文字** @param path 本地图片地址* @return 识别结果，为json格式* @throws URISyntaxException URI打开异常* @throws IOException io流异常*/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);}/*** @param url 图片url* @return 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** @param param 区分是url还是image识别* @return 识别结果* @throws URISyntaxException URI打开异常* @throws IOException IO流异常*/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 = "E:\\find.png";try {long now = System.currentTimeMillis();checkFile(path);checkUrl("/-Po3dSag_xI4khGkpoWK1HF6hhy/baike/c0%3Dbaike80%2C5%2C5%2C80%2C26/sign=08c05c0e8444ebf8797c6c6db890bc4f/fc1f4134970a304e46bfc5f7d2c8a786c9175c19.jpg");System.out.println("耗时：" + (System.currentTimeMillis() - now) / 1000 + "s");} catch (URISyntaxException | IOException e) {e.printStackTrace();}}}