JAVA实现百度OCR文字识别功能

闲来无事，发现百度有一个OCR文字识别接口，感觉挺有意思的，拿来研究一下。       

百度服务简介：文字识别是百度自然场景OCR服务，依托百度业界领先的OCR算法，提供了整图文字检测、识别、整图文字识别、整图文字行定位和单字图像识别等功能。

不多说啦，直接看demo吧！

package com.oa.test;

import java.io.BufferedReader;
import java.io.File;
import java.io.InputStream;
import java.io.InputStreamReader;
import java.net.HttpURLConnection;
import java.net.URL;

import com.oa.commons.util.BASE64;

public class OCRTest {

	public static String request(String httpUrl, String httpArg) {
		BufferedReader reader = null;
		String result = null;
		StringBuffer sbf = new StringBuffer();

		try {
			URL url = new URL(httpUrl);
			HttpURLConnection connection = (HttpURLConnection) url
					.openConnection();
			connection.setRequestMethod("POST");
			connection.setRequestProperty("Content-Type",
					"application/x-www-form-urlencoded");
			// 填入apikey到HTTP header
			connection.setRequestProperty("apikey", "您自己的apikey");
			connection.setDoOutput(true);
			connection.getOutputStream().write(httpArg.getBytes("UTF-8"));
			connection.connect();
			InputStream is = connection.getInputStream();
			reader = new BufferedReader(new InputStreamReader(is, "UTF-8"));
			String strRead = null;
			while ((strRead = reader.readLine()) != null) {
				sbf.append(strRead);
				sbf.append("\r\n");
			}
			reader.close();
			result = sbf.toString();
		} catch (Exception e) {
			e.printStackTrace();
		}
		return result;
	}

	<pre name="code" class="java">/**
	 * @param args
	 */
	public static void main(String[] args) {
		File file = new File("d:\\che4.jpg");
		String imageBase = BASE64.encodeImgageToBase64(file);
		imageBase = imageBase.replaceAll("\r\n","");
		imageBase = imageBase.replaceAll("\\+","%2B");
		String httpUrl = "http://apis.baidu.com/apistore/idlocr/ocr";
		String httpArg = "fromdevice=pc&clientip=10.10.10.0&detecttype=LocateRecognize&languagetype=CHN_ENG&imagetype=1&image="+imageBase;
		String jsonResult = request(httpUrl, httpArg);
		System.out.println("返回的结果--------->"+jsonResult);

	}

	/**
	 * 将本地图片进行Base64位编码
	 * 
	 * @param imgUrl
	 *            图片的url路径，如d:\\中文.jpg
	 * @return
	 */
	public static String encodeImgageToBase64(File imageFile) {// 将图片文件转化为字节数组字符串，并对其进行Base64编码处理
		// 其进行Base64编码处理
		byte[] data = null;
		// 读取图片字节数组
		try {
			InputStream in = new FileInputStream(imageFile);
			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();
		return encoder.encode(data);// 返回Base64编码过的字节数组字符串
	}

附件： （che4.jpg）

运行后结果：

{"errNum":"0","errMsg":"success","querySign":"2289891521,4081625058","retData":[{"rect":{"left":"32","top":"15","width":"418","height":"118"},"word":"\u8c6bC88888"},{"rect":{"left":"45","top":"137","width":"373","height":"18"},"word":"\u4e1c\u98ce\u672c\u7530\u6d1b\u9633\u952e\u901a\u5e97\u7535\u8bdd\uff1a03796358222"}]}

注意：将此结果放到 在线JSON校验格式化工具中（http://www.bejson.com/）会得到你想要的结果：

{
    "errNum": "0",
    "errMsg": "success",
    "querySign": "2289891521,4081625058",
    "retData": [
        {
            "rect": {
                "left": "32",
                "top": "15",
                "width": "418",
                "height": "118"
            },
            "word": "豫C88888"
        },
        {
            "rect": {
                "left": "45",
                "top": "137",
                "width": "373",
                "height": "18"
            },
            "word": "东风本田洛阳键通店电话：03796358222"
        }
    ]
}

怎么样，感觉很神奇吧，感兴趣的试一下吧！
最后，解释一下几个参数的含义：

apikey：API密钥 也就是您自己的apikey

fromdevice：来源，例如：android、iPhone 默认是PC

clientip：客户端出口IP

detecttype：OCR接口类型

languagetype：要检测的文字类型

imagetype：图片资源类型

image：图片资源，目前仅支持jpg格式