百度ai人脸对比:
首先由个百度账号,进入百度开发者中心
百度开发者中心
登录后选择百度ai开发平台
进入右侧控制台后选择人脸识别:
进入后先创建一个应用,将所有不收费的都领取一下
创建完成后就能获得密钥了
接着进入sdk中
找到java SDK
进入后,下载SDK
JAVA SDK下载地址
这里是主要的结构图
创建一个空的SpringBoot项目(方便后续跟前端连接,web项目也可以)
官方给出的jar包好像不用导入也可以,直接导入下列两个jar包
<dependency>
<groupId>org.slf4j</groupId>
<artifactId>slf4j-simple</artifactId>
<version>1.7.25</version>
</dependency>
<dependency>
<groupId>org.json</groupId>
<artifactId>json</artifactId>
<version>20180130</version>
</dependency>
基本的项目结构是这样子,再准备两张图片和一个前端页面用于拍照
接着进入api的关键类,AipFace这里面就是百度提供给我们的所有方法,可直接使用
新建一个测试类:
直接调用他的方法即可,这里要注意传入的照片格式为Base64,所以我写了一个类,将照片转为Base64
public class Test {
public static final String APP_ID = "APP_ID ";
public static final String API_KEY = "API_KEY ";
public static final String SECRET_KEY = "SECRET_KEY ";
public static void main(String[] args) {
AipFace aipFace = new AipFace(APP_ID, API_KEY, SECRET_KEY);
String img1="D:\\FaceDemo\\src\\main\\resources\\imgs\\img1.jpg";
String img2="D:\\FaceDemo\\src\\main\\resources\\imgs\\img2.jpg";
//两张不一样的图片
String getImageStr1 = GetImageStr(img1);
String getImageStr2 = GetImageStr(img2);
// String getImageStr3 = GetImageStr(img1);
List<MatchRequest> input = new ArrayList<>();
MatchRequest mr1 = new MatchRequest(getImageStr1, "BASE64");
MatchRequest mr2 = new MatchRequest(getImageStr2, "BASE64");
// MatchRequest mr2 = new MatchRequest(getImageStr3, "BASE64");
input.add(mr1);
input.add(mr2);
JSONObject match = aipFace.match(input);
System.out.println(match);
}
public static String GetImageStr(String imgFile) {//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
InputStream in = null;
byte[] data = null;
//读取图片字节数组
try {
in = new FileInputStream(imgFile);
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
}
}
官方给出的参数信息:
返回值,这个score就是两张图片的相似度了!!
{
"score": 44.3,
"face_list": [ //返回的顺序与传入的顺序保持一致
{
"face_token": "fid1"
},
{
"face_token": "fid2"
}
]
}
前端代码:
<!DOCTYPE html>
<html lang="en">
<head>
<meta charset="utf-8"/>
<title></title>
<!-- 样式部分可以忽略 -->
<style>
* {
padding: 0;
margin: 0;
}
div {
width: 100vw;
height: 100vh;
display: flex;
justify-content: center;
align-items: center;
}
.btn {
width: 100px;
height: 50px;
border-radius: 10px;
background: #ff9900;
line-height: 50px;
text-align: center;
color: #fff;
box-shadow: 0 0 10px #999;
}
#video {
width: 300px;
height: 300px;
border: 5px solid #000;
border-radius: 10px;
margin-left: 5px;
}
#canvas {
width: 300px;
height: 300px;
border: 5px solid #000;
border-radius: 10px;
margin-left: 5px;
}
</style>
</head>
<script src="js/jquery-3.3.1.min.js" type="text/javascript" charset="utf-8"></script>
<body>
<div>
<div id="play" class="btn">开始摄像</div>
<div id="take" class="btn">拍照</div>
<div id="sub_btn" class="btn">登录</div>
<video id="video"></video>
<!-- 尽量在canvas标签上设置宽高 -->
<canvas id="canvas" width="300px" height="300px"></canvas>
</div>
<script>
$(function () {
// 开启摄像
document.getElementById('play').onclick = () => {
let constraints = {
// video属性设置
video: {
width: 300,
height: 300
},
// audio属性设置
audio: false
}
navigator.mediaDevices.getUserMedia(constraints)
.then(mediaStream => {
// 成功返回promise对象,接收一个mediaStream参数与video标签进行对接
document.getElementById('video').srcObject = mediaStream
document.getElementById('video').play()
})
// 失败就失败了
}
// 拍照、canvas绘制
document.getElementById('take').onclick = () => {
let ctx = document.getElementById("canvas").getContext('2d')
ctx.drawImage(document.getElementById("video"), 0, 0, 300, 300)
}
$("body").on("click", "#sub_btn", function () {
var imgdata = document.getElementById("canvas").toDataURL("image/jpeg");
console.log(imgdata)
$.ajax({
url:"/Face/test",
type:"post",
async: true,
dataType:"json",
contentType : "application/x-www-form-urlencoded; charset=utf-8",
data:{
image:imgdata
},
success:function (res) {
if (res.result.score>70)
alert("登录成功")
else alert("登录失败")
}
})
});
})
</script>
</body>
</html>
编写url路径,修改测试类:
package com.baidu.aip.Controller;
import com.baidu.aip.face.AipFace;
import com.baidu.aip.face.MatchRequest;
import org.json.JSONObject;
import org.springframework.web.bind.annotation.*;
import sun.misc.BASE64Encoder;
import java.io.FileInputStream;
import java.io.IOException;
import java.io.InputStream;
import java.util.ArrayList;
import java.util.List;
@RestController
@RequestMapping("/Face")
public class FaceController {
public static final String APP_ID = "APP_ID ";
public static final String API_KEY = "API_KEY ";
public static final String SECRET_KEY = "SECRET_KEY ";
@PostMapping( "/test")
public String Test(@RequestParam("image") String image) {
String substring = image.substring("data:image/jpeg;base64,".length());
AipFace aipFace = new AipFace(APP_ID, API_KEY, SECRET_KEY);
String img1="D:\\FaceDemo\\src\\main\\resources\\imgs\\img1.jpg";
//两张不一样的图片
String getImageStr1 = GetImageStr(img1);
List<MatchRequest> input = new ArrayList<>();
MatchRequest mr1 = new MatchRequest(getImageStr1, "BASE64");
MatchRequest mr2 = new MatchRequest(substring, "BASE64");
input.add(mr1);
input.add(mr2);
JSONObject match = aipFace.match(input);
System.out.println(match);
return match.toString();
}
public static String GetImageStr(String imgFile) {//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
InputStream in = null;
byte[] data = null;
//读取图片字节数组
try {
in = new FileInputStream(imgFile);
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
}
}
接下来直接启动项目,测试就可以了