百度OCR图片内容识别为文字
一、百度OCR图片内容转换为文字
1.进入对应链接根据图片指示进行相关操作
2.进入页面点击技术文档
3.个人示例代码实现(仅供参考)
3.1 重要提示代码中所需工具类
- FileUtil,Base64Util,HttpUtil,GsonUtils请从
https://ai.baidu.com/file/658A35ABAB2D404FBF903F64D47C1F72
package com.xigao.util;
import java.io.*;
/**
* 文件读取工具类
*/
public class FileUtil {
/**
* 读取文件内容,作为字符串返回
*/
public static String readFileAsString(String filePath) throws IOException {
File file = new File(filePath);
if (!file.exists()) {
throw new FileNotFoundException(filePath);
}
if (file.length() > 1024 * 1024 * 1024) {
throw new IOException("File is too large");
}
StringBuilder sb = new StringBuilder((int) (file.length()));
// 创建字节输入流
FileInputStream fis = new FileInputStream(filePath);
// 创建一个长度为10240的Buffer
byte[] bbuf = new byte[10240];
// 用于保存实际读取的字节数
int hasRead = 0;
while ( (hasRead = fis.read(bbuf)) > 0 ) {
sb.append(new String(bbuf, 0, hasRead));
}
fis.close();
return sb.toString();
}
/**
* 根据文件路径读取byte[] 数组
*/
public static byte[] readFileByBytes(String filePath) throws IOException {
File file = new File(filePath);
if (!file.exists()) {
throw new FileNotFoundException(filePath);
} else {
ByteArrayOutputStream bos = new ByteArrayOutputStream((int) file.length());
BufferedInputStream in = null;
try {
in = new BufferedInputStream(new FileInputStream(file));
short bufSize = 1024;
byte[] buffer = new byte[bufSize];
int len1;
while (-1 != (len1 = in.read(buffer, 0, bufSize))) {
bos.write(buffer, 0, len1);
}
byte[] var7 = bos.toByteArray();
return var7;
} finally {
try {
if (in != null) {
in.close();
}
} catch (IOException var14) {
var14.printStackTrace();
}
bos.close();
}
}
}
}
-
Base64Util
https://ai.baidu.com/file/C8D81F3301E24D2892968F09AE1AD6E2
package com.xigao.util; /** * Base64 工具类 */ public class Base64Util { private static final char last2byte = (char) Integer.parseInt("00000011", 2); private static final char last4byte = (char) Integer.parseInt("00001111", 2); private static final char last6byte = (char) Integer.parseInt("00111111", 2); private static final char lead6byte = (char) Integer.parseInt("11111100", 2); private static final char lead4byte = (char) Integer.parseInt("11110000", 2); private static final char lead2byte = (char) Integer.parseInt("11000000", 2); private static final char[] encodeTable = new char[]{'A', 'B', 'C', 'D', 'E', 'F', 'G', 'H', 'I', 'J', 'K', 'L', 'M', 'N', 'O', 'P', 'Q', 'R', 'S', 'T', 'U', 'V', 'W', 'X', 'Y', 'Z', 'a', 'b', 'c', 'd', 'e', 'f', 'g', 'h', 'i', 'j', 'k', 'l', 'm', 'n', 'o', 'p', 'q', 'r', 's', 't', 'u', 'v', 'w', 'x', 'y', 'z', '0', '1', '2', '3', '4', '5', '6', '7', '8', '9', '+', '/'}; public Base64Util() { } public static String encode(byte[] from) { StringBuilder to = new StringBuilder((int) ((double) from.length * 1.34D) + 3); int num = 0; char currentByte = 0; int i; for (i = 0; i < from.length; ++i) { for (num %= 8; num < 8; num += 6) { switch (num) { case 0: currentByte = (char) (from[i] & lead6byte); currentByte = (char) (currentByte >>> 2); case 1: case 3: case 5: default: break; case 2: currentByte = (char) (from[i] & last6byte); break; case 4: currentByte = (char) (from[i] & last4byte); currentByte = (char) (currentByte << 2); if (i + 1 < from.length) { currentByte = (char) (currentByte | (from[i + 1] & lead2byte) >>> 6); } break; case 6: currentByte = (char) (from[i] & last2byte); currentByte = (char) (currentByte << 4); if (i + 1 < from.length) { currentByte = (char) (currentByte | (from[i + 1] & lead4byte) >>> 4); } } to.append(encodeTable[currentByte]); } } if (to.length() % 4 != 0) { for (i = 4 - to.length() % 4; i > 0; --i) { to.append("="); } } return to.toString(); } }
-
HttpUtil
https://ai.baidu.com/file/544D677F5D4E4F17B4122FBD60DB82B3
package com.xigao.util; import java.io.BufferedReader; import java.io.DataOutputStream; import java.io.InputStreamReader; import java.net.HttpURLConnection; import java.net.URL; import java.util.List; import java.util.Map; /** * http 工具类 */ public class HttpUtil { public static String post(String requestUrl, String accessToken, String params) throws Exception { String contentType = "application/x-www-form-urlencoded"; return HttpUtil.post(requestUrl, accessToken, contentType, params); } public static String post(String requestUrl, String accessToken, String contentType, String params) throws Exception { String encoding = "UTF-8"; if (requestUrl.contains("nlp")) { encoding = "GBK"; } return HttpUtil.post(requestUrl, accessToken, contentType, params, encoding); } public static String post(String requestUrl, String accessToken, String contentType, String params, String encoding) throws Exception { String url = requestUrl + "?access_token=" + accessToken; return HttpUtil.postGeneralUrl(url, contentType, params, encoding); } public static String postGeneralUrl(String generalUrl, String contentType, String params, String encoding) throws Exception { URL url = new URL(generalUrl); // 打开和URL之间的连接 HttpURLConnection connection = (HttpURLConnection) url.openConnection(); connection.setRequestMethod("POST"); // 设置通用的请求属性 connection.setRequestProperty("Content-Type", contentType); connection.setRequestProperty("Connection", "Keep-Alive"); connection.setUseCaches(false); connection.setDoOutput(true); connection.setDoInput(true); // 得到请求的输出流对象 DataOutputStream out = new DataOutputStream(connection.getOutputStream()); out.write(params.getBytes(encoding)); out.flush(); out.close(); // 建立实际的连接 connection.connect(); // 获取所有响应头字段 Map<String, List<String>> headers = connection.getHeaderFields(); // 遍历所有的响应头字段 for (String key : headers.keySet()) { System.err.println(key + "--->" + headers.get(key)); } // 定义 BufferedReader输入流来读取URL的响应 BufferedReader in = null; in = new BufferedReader( new InputStreamReader(connection.getInputStream(), encoding)); String result = ""; String getLine; while ((getLine = in.readLine()) != null) { result += getLine; } in.close(); System.err.println("result:" + result); return result; } }
-
GsonUtils
https://ai.baidu.com/file/470B3ACCA3FE43788B5A963BF0B625F3/* * Copyright (C) 2017 Baidu, Inc. All Rights Reserved. */ package com.xigao.util; import com.google.gson.Gson; import com.google.gson.GsonBuilder; import com.google.gson.JsonParseException; import java.lang.reflect.Type; /** * Json工具类. */ public class GsonUtils { private static Gson gson = new GsonBuilder().create(); public static String toJson(Object value) { return gson.toJson(value); } public static <T> T fromJson(String json, Class<T> classOfT) throws JsonParseException { return gson.fromJson(json, classOfT); } public static <T> T fromJson(String json, Type typeOfT) throws JsonParseException { return (T) gson.fromJson(json, typeOfT); } }
3.2 controller层代码(前端照片以Base64格式传输)
package com.xigao.controller;
import com.xigao.service.OcrService;
import lombok.AllArgsConstructor;
import org.springframework.http.MediaType;
import org.springframework.web.bind.annotation.*;
import org.springframework.web.multipart.MultipartFile;
@RequestMapping("/api")
@RestController
@AllArgsConstructor
@CrossOrigin(origins = "*")
public class OcrController {
private final OcrService ocrService;
@PostMapping(value = "/recognize")
public String recognizeImage(@RequestParam("file") String file){
// 调用OcrService中的方法进行文字识别
return ocrService.recognizeText(file);
}
}
3.3 service实现类层代码
package com.xigao.service.impl;
/**
* 重要提示代码中所需工具类
* FileUtil,Base64Util,HttpUtil,GsonUtils请从
* https://ai.baidu.com/file/658A35ABAB2D404FBF903F64D47C1F72
* https://ai.baidu.com/file/C8D81F3301E24D2892968F09AE1AD6E2
* https://ai.baidu.com/file/544D677F5D4E4F17B4122FBD60DB82B3
* https://ai.baidu.com/file/470B3ACCA3FE43788B5A963BF0B625F3
* 下载
*/
import com.xigao.service.OcrService;
import com.xigao.util.*;
import org.springframework.stereotype.Service;
import java.io.File;
import java.io.FileOutputStream;
import java.io.IOException;
import java.io.OutputStream;
import java.net.URLEncoder;
import java.util.Base64;
/**
* 通用文字识别(高精度版)
*/
@Service
public class OcrServiceImpl implements OcrService {
public String recognizeText(String file) {
String substring = file.substring(file.lastIndexOf(",") + 1);
String replace = substring.replace(" ", "+");
// 请求url
String url = "https://aip.baidubce.com/rest/2.0/ocr/v1/accurate_basic";
try {
String imgParam = URLEncoder.encode(replace, "UTF-8");
String param = "image=" + imgParam;
String auth = GetTokenUtil.getAuth();
// 注意这里仅为了简化编码每一次请求都去获取access_token,线上环境access_token有过期时间, 客户端可自行缓存,过期后重新获取。
String accessToken = auth;
String result = HttpUtil.post(url, accessToken, param);
System.out.println(result);
return result;
} catch (Exception e) {
e.printStackTrace();
}
return null;
}
}
3.4 获取token的代码
package com.xigao.util;
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;
/**
* 获取权限token
* @return 返回示例:
* {
* "access_token": "24.460da4889caad24cccdb1fea17221975.2592000.1491995545.282335-1234567",
* "expires_in": 2592000
* }
*/
public class GetTokenUtil {
public static String getAuth() {
// 官网获取的 API Key 更新为你注册的
String clientId = "API Key";
// 官网获取的 Secret Key 更新为你注册的
String clientSecret = "Secret Key";
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;
}
}
二、百度开发Api创建并生成API Key(新手可领取免费测试版本)
1.进入对应的创建界面
(https://console.bce.baidu.com/ai/#/ai/ocr/overview/index)
2.根据需求选择相应的文字识别接口
3.创建成功的资源将会显示在[资源列表]的「已领取资源」中。您可以选择「查看领取记录」去往「资源列表」查看。
资源列表地址:资源列表
4.创建应用
4.1 进入 文字识别控制台,点击 「去创建」,即可进入应用创建页面。
文字识别控制台地址:文字识别控制台