xiaoyaoyou1212 / Viseface
Licence: apache-2.0
简易人脸检测库,不依赖三方库,可快速接入人脸检测功能。
Stars: ✭ 186
Programming Languages
java
68154 projects - #9 most used programming language
Labels
Projects that are alternatives of or similar to Viseface
Face Detection With Mobilenet Ssd
Face detection with mobilenet-ssd written by tf.keras.
Stars: ✭ 154 (-17.2%)
Mutual labels: face-detection
Facepause
Look Away to Pause Youtube - Experimental Chrome Extension
Stars: ✭ 171 (-8.06%)
Mutual labels: face-detection
Retinaface Tf2
RetinaFace (RetinaFace: Single-stage Dense Face Localisation in the Wild, published in 2019) reimplemented in Tensorflow 2.0, with pretrained weights available !
Stars: ✭ 176 (-5.38%)
Mutual labels: face-detection
Wechat Miniprogram Webar
A WeChat MiniProgram Image AR using computer vision. No OpenCV, No Deep Learning. Only JavaScript Implementation.
Stars: ✭ 163 (-12.37%)
Mutual labels: face-detection
Human
Human: 3D Face Detection, Body Pose, Hand & Finger Tracking, Iris Tracking and Age & Gender Prediction
Stars: ✭ 172 (-7.53%)
Mutual labels: face-detection
Yolo Face With Landmark
yoloface大礼包 使用pytroch实现的基于yolov3的轻量级人脸检测(包含关键点)
Stars: ✭ 180 (-3.23%)
Mutual labels: face-detection
Face Api.js
JavaScript API for face detection and face recognition in the browser and nodejs with tensorflow.js
Stars: ✭ 13,258 (+7027.96%)
Mutual labels: face-detection
Attendance Using Face
Face-recognition using Siamese network
Stars: ✭ 174 (-6.45%)
Mutual labels: face-detection
Facemoji Kit
Face tracker with blend shapes coefficients, 3D head pose and dense mesh in real-time on iOS, Android, Mac, PC and Linux.
Stars: ✭ 158 (-15.05%)
Mutual labels: face-detection
Facenet Pytorch
Pretrained Pytorch face detection (MTCNN) and facial recognition (InceptionResnet) models
Stars: ✭ 2,564 (+1278.49%)
Mutual labels: face-detection
Proctoring Ai
Creating a software for automatic monitoring in online proctoring
Stars: ✭ 155 (-16.67%)
Mutual labels: face-detection
Opencv Facial Landmark Detection
使用OpenCV实现人脸关键点检测
Stars: ✭ 153 (-17.74%)
Mutual labels: face-detection
Instabotai
Instagram AI bot with face detection. It works without instagram api, need only login and password.
Stars: ✭ 181 (-2.69%)
Mutual labels: face-detection
Retinaface Tf2
RetinaFace (Single-stage Dense Face Localisation in the Wild, 2019) implemented (ResNet50, MobileNetV2 trained on single GPU) in Tensorflow 2.0+. This is an unofficial implementation. With Colab.
Stars: ✭ 178 (-4.3%)
Mutual labels: face-detection
ViseFace
简易人脸检测库,不依赖三方库,可快速接入人脸检测功能。
-
项目依赖:
compile 'com.vise.xiaoyaoyou:viseface:1.1.0'
版本说明
代码托管
为什么打造该库
1、想简单快速接入人脸检测功能;
2、Google 提供的人脸检测功能部分手机无法适配;
3、第三方提供的人脸检测功能接入门槛过高;
4、依赖第三方库会增加 APK 大小。
功能介绍
1、可快速识别人脸;
2、可适配所有机型;
3、可配置最大检测人脸数;
4、可配置是否显示人脸检测框;
5、可配置当前检测人脸摄像头为前置和后置;
6、可检测到最近人脸范围的光照值,光照范围 0 - 255;
7、可检测到的最近人脸相对于屏幕宽度的比例。
效果演示
使用介绍
1、导入人脸检测库
在工程的 build 文件中添加如下依赖:
compile 'com.vise.xiaoyaoyou:viseface:1.1.0'
2、创建相机预览布局
<?xml version="1.0" encoding="utf-8"?>
<FrameLayout xmlns:android="http://schemas.android.com/apk/res/android"
android:layout_width="match_parent"
android:layout_height="match_parent"
>
<!--相机预览界面,必须设置-->
<com.vise.face.CameraPreview
android:id="@+id/face_detector_preview"
android:layout_width="match_parent"
android:layout_height="match_parent"/>
<!--绘制人脸识别框,可依需配置-->
<com.vise.face.FaceRectView
android:id="@+id/face_detector_face"
android:layout_width="match_parent"
android:layout_height="match_parent"/>
<!--拍照按钮,点击后进行拍照,按照需要进行添加-->
<Button
android:id="@+id/face_detector_take_photo"
android:layout_width="100dp"
android:layout_height="100dp"
android:layout_marginBottom="30dp"
android:layout_gravity="bottom|center_horizontal"
android:background="@android:drawable/ic_menu_camera"
/>
</FrameLayout>
注意:最外层布局必须是 FrameLayout
;如果代码中配置需要绘制人脸检测框,那么布局必须添加 FaceRectView
。
3、创建人脸检测实现对象
IFaceDetector mFaceDetector = new NormalFaceDetector();
4、创建权限检查监听
ICameraCheckListener mCameraCheckListener = new ICameraCheckListener() {
@Override
public void checkPermission(boolean isAllow) {
//权限是否允许
ViseLog.i("checkPermission" + isAllow);
}
@Override
public void checkPixels(long pixels, boolean isSupport) {
//手机像素是否满足要求
ViseLog.i("checkPixels" + pixels);
}
};
5、创建检测数据监听
IDataListener mDataListener = new IDataListener() {
@Override
public void onDetectorData(DetectorData detectorData) {
//回调识别到的数据
ViseLog.i("识别数据:" + detectorData);
}
};
6、设置相关配置,创建人脸检测代理
该库的核心思想就是快速接入人脸检测功能,所以该库的功能都是通过 DetectorProxy
代理类来实现,使用简单明了。具体使用场景如下:
//创建代理类,必须传入相机预览界面
DetectorProxy mDetectorProxy = new DetectorProxy.Builder(mFace_detector_preview)
//设置权限检查监听
.setCheckListener(mCameraCheckListener)
//设置人脸检测实现
.setFaceDetector(mFaceDetector)
//设置检测数据回调监听
.setDataListener(mDataListener)
//设置绘制人脸识别框界面
.setFaceRectView(mFace_detector_face)
//设置是否绘制人脸检测框
.setDrawFaceRect(true)
//设置预览相机的相机ID
.setCameraId(Camera.CameraInfo.CAMERA_FACING_BACK)
//设置可检测的最大人脸数
.setMaxFacesCount(5)
//设置人脸识别框是否为完整矩形
.setFaceIsRect(false)
//设置人脸识别框的RGB颜色
.setFaceRectColor(Color.rgb(255, 203, 15))
//创建代理类
.build();
7、开启人脸检测
if (mDetectorProxy != null) {
mDetectorProxy.detector();
}
8、释放资源
if (mDetectorProxy != null) {
mDetectorProxy.release();
}
关于我
最后
如果觉得该项目有帮助,请点下Star,您的支持是我开源的动力。如果有好的想法和建议,也欢迎Fork项目参与进来。使用中如果有任何问题和建议都可以进群交流,QQ群二维码如下:
Note that the project description data, including the texts, logos, images, and/or trademarks,
for each open source project belongs to its rightful owner.
If you wish to add or remove any projects, please contact us at [email protected].