隨著直播漸漸的火起來，像抱著直播大腿的其他功能也漸漸的火起來了，比如說人臉識別。說起人臉識別用處甚廣，比如說有以這個功能為核心的app：美顏相機(jī)、美圖秀秀、SNOW等等，但是美顏相機(jī)和美圖秀秀是用的國內(nèi)SDK《Face++》來做的，這個sdk呢好像是他們自己的后臺進(jìn)行識別并不是app本身做識別。這樣就跟我們今天要了解的動態(tài)識別不是很對路，肯定不能拿到攝像頭的一幀畫面去調(diào)一次接口再接回參數(shù)吧，這樣性能肯定不行。所以今天就拿SNOW的例子來說，雖然我不知道他是用什么做的，但是我們可以用openCV也能實(shí)現(xiàn)。

我們先看看效果圖：

實(shí)現(xiàn)步驟如下：

2、然后新建個項目我這里以studio里為基準(zhǔn)，在main目錄里面新建jniLibs文件夾，為什么叫jniLibs呢，因為這是調(diào)用c庫的默認(rèn)文件夾命名，當(dāng)然你也可以命名其他的，但是需要在build里面指定這個文件夾。好了，打開我們剛才下載的文件，然后一次打開sdk\native\libs，最后把libs目錄里面的所有文件夾拷貝到j(luò)niLibs里面去。請看圖：

3、加好jniLibs之后呢還需要導(dǎo)入一個module，在studio里面點(diǎn)擊file->new->import module->導(dǎo)入module目錄是剛才下載的sdk\java這個目錄。請看圖：

4、導(dǎo)入之后呢右鍵項目打開open module setting選項，在app選項里點(diǎn)擊Dependencies這個，然后點(diǎn)擊最右邊的+號把剛剛導(dǎo)入的module加進(jìn)去。請看圖：

5、現(xiàn)在開始寫代碼了，這里我把需要寫的代碼文件會一一貼出來，下面請看圖：

首先是MainActivity的代碼：

package com.wyw.facedemo;

import android.content.Context;

import android.os.Bundle;

import android.support.v7.app.AppCompatActivity;

import android.util.Log;

import android.view.View;

import android.view.WindowManager;

import android.widget.Button;

import android.widget.RelativeLayout;

import org.opencv.android.CameraBridgeViewBase;

import org.opencv.android.JavaCameraView;

import org.opencv.android.OpenCVLoader;

import org.opencv.core.Core;

import org.opencv.core.CvType;

import org.opencv.core.Mat;

import org.opencv.core.MatOfRect;

import org.opencv.core.Rect;

import org.opencv.core.Scalar;

import org.opencv.core.Size;

import org.opencv.objdetect.CascadeClassifier;

import java.io.File;

import java.io.FileOutputStream;

import java.io.InputStream;

public class MainActivity extends AppCompatActivity implements CameraBridgeViewBase.CvCameraViewListener {

private CameraBridgeViewBase openCvCameraView;

private CascadeClassifier cascadeClassifier;

//圖像人臉小于高度的多少就不檢測

private int absoluteFaceSize;

//臨時圖像對象

private Mat matLin;

//最終圖像對象

private Mat mat;

//前置攝像頭

public static int CAMERA_FRONT = 0;

//后置攝像頭

public static int CAMERA_BACK = 1;

private int camera_scene = CAMERA_BACK;

private void initializeOpenCVDependencies() {

try {

// Copy the resource into a temp file so OpenCV can load it

InputStream is = getResources().openRawResource(R.raw.lbpcascade_frontalface);

File cascadeDir = getDir("cascade", Context.MODE_PRIVATE);

File mCascadeFile = new File(cascadeDir, "lbpcascade_frontalface.xml");

FileOutputStream os = new FileOutputStream(mCascadeFile);

byte[] buffer = new byte[4096];

int bytesRead;

while ((bytesRead = is.read(buffer)) != -1) {

os.write(buffer, 0, bytesRead);

}

is.close();

os.close();

// Load the cascade classifier

cascadeClassifier = new CascadeClassifier(mCascadeFile.getAbsolutePath());

} catch (Exception e) {

Log.e("OpenCVActivity", "Error loading cascade", e);

}

// And we are ready to go

openCvCameraView.enableView();

}

@Override

public void onCreate(Bundle savedInstanceState) {

super.onCreate(savedInstanceState);

getWindow().addFlags(WindowManager.LayoutParams.FLAG_KEEP_SCREEN_ON);

setContentView(R.layout.activity_main);

final RelativeLayout relativeLayout = (RelativeLayout) findViewById(R.id.relative);

openCvCameraView = new JavaCameraView(this, CameraBridgeViewBase.CAMERA_ID_FRONT);

openCvCameraView.setCvCameraViewListener(this);

final Button button = new Button(MainActivity.this);

button.setText("切換攝像頭");

button.setOnClickListener(new View.OnClickListener() {

@Override

public void onClick(View v) {

if (camera_scene == CAMERA_FRONT) {//如果是前置攝像頭就切換成后置

relativeLayout.removeAllViews();

openCvCameraView.disableView();

openCvCameraView = null;

cascadeClassifier = null;

openCvCameraView = new JavaCameraView(MainActivity.this, CameraBridgeViewBase.CAMERA_ID_BACK);

openCvCameraView.setCvCameraViewListener(MainActivity.this);

openCvCameraView.setCameraIndex(CameraBridgeViewBase.CAMERA_ID_BACK);//后置攝像頭

camera_scene = CAMERA_BACK;

relativeLayout.addView(openCvCameraView);

relativeLayout.addView(button);

initializeOpenCVDependencies();

} else {

relativeLayout.removeAllViews();

openCvCameraView.disableView();

openCvCameraView = null;

cascadeClassifier = null;

openCvCameraView = new JavaCameraView(MainActivity.this, CameraBridgeViewBase.CAMERA_ID_FRONT);

openCvCameraView.setCvCameraViewListener(MainActivity.this);

openCvCameraView.setCameraIndex(CameraBridgeViewBase.CAMERA_ID_FRONT);//前置攝像頭

camera_scene = CAMERA_FRONT;

relativeLayout.addView(openCvCameraView);

relativeLayout.addView(button);

initializeOpenCVDependencies();

}

}

});

relativeLayout.addView(openCvCameraView);

relativeLayout.addView(button);

if (camera_scene == CAMERA_FRONT) {

openCvCameraView.setCameraIndex(CameraBridgeViewBase.CAMERA_ID_FRONT);//前置攝像頭

} else if (camera_scene == CAMERA_BACK) {

openCvCameraView.setCameraIndex(CameraBridgeViewBase.CAMERA_ID_BACK);//后置攝像頭

}

}

@Override

public void onCameraViewStarted(int width, int height) {

matLin = new Mat(height, width, CvType.CV_8UC4);//臨時圖像

// 人臉小于高度的百分之30就不檢測

absoluteFaceSize = (int) (height * 0.3);

}

@Override

public void onCameraViewStopped() {

}

@Override

public Mat onCameraFrame(Mat aInputFrame) {

//轉(zhuǎn)置函數(shù),將圖像翻轉(zhuǎn)(順時針90度)

Core.transpose(aInputFrame, matLin);

if (camera_scene == CAMERA_FRONT) {//前置攝像頭

//轉(zhuǎn)置函數(shù),將圖像翻轉(zhuǎn)(對換)

Core.flip(matLin, aInputFrame, 1);

//轉(zhuǎn)置函數(shù),將圖像順時針順轉(zhuǎn)(對換)

Core.flip(aInputFrame, matLin, 0);

mat = matLin;

} else if (camera_scene == CAMERA_BACK) {//后置攝像頭

//轉(zhuǎn)置函數(shù),將圖像翻轉(zhuǎn)(對換)

Core.flip(matLin, aInputFrame, 1);

mat = aInputFrame;

}

MatOfRect faces = new MatOfRect();

Log.i("123456", "absoluteFaceSize = " + absoluteFaceSize);

// Use the classifier to detect faces

if (cascadeClassifier != null) {

cascadeClassifier.detectMultiScale(mat, faces, 1.1, 1, 1,

new Size(absoluteFaceSize, absoluteFaceSize), new Size());

}

// 檢測出多少個

Rect[] facesArray = faces.toArray();

for (int i = 0; i < facesArray.length; i++) {

Log.i("123456", "facesArray[i].tl()坐上坐標(biāo) == " + facesArray[i].tl() + " facesArray[i].br() == 右下坐標(biāo)" + facesArray[i].br());

Core.rectangle(mat, facesArray[i].tl(), facesArray[i].br(), new Scalar(0, 255, 0, 255), 3);

}

return mat;

}

@Override

public void onResume() {

super.onResume();

if (!OpenCVLoader.initDebug()) {

Log.e("log_wons", "OpenCV init error");

// Handle initialization error

}

initializeOpenCVDependencies();

//OpenCVLoader.initAsync(OpenCVLoader.OPENCV_VERSION_2_4_6, this, mLoaderCallback);

}

}

然后是layout的xml代碼：

現(xiàn)在是raw文件夾里面的xml(這個xml是圖片解析出來進(jìn)行對比校驗人臉的模型庫)由于這個文件有一千多行就不貼了，如有需要請去下載本demo查看！當(dāng)然也可以去你下載的openCV的sdk里面拿，目錄是\samples\face-detection\res\raw。請看圖：

最后就是AndroidManifest文件了：

做到這一步就趕緊把你的代碼運(yùn)行起來吧！！本篇博客就到這里，如果有有疑問的歡迎留言討論。同時希望大家多多關(guān)注我的博客，多多支持我。

總結(jié)

以上是生活随笔為你收集整理的android 动态人脸识别码,android OpenCV研究之动态人脸识别的全部內(nèi)容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網(wǎng)站內(nèi)容還不錯，歡迎將生活随笔推薦給好友。