gicheonkang / fast-face-android Goto Github PK
View Code? Open in Web Editor NEW๐ฆ Fast-Face : Android App for Real-time Face Landmark Detection. You can check your landmarks in 60ms
License: Apache License 2.0
๐ฆ Fast-Face : Android App for Real-time Face Landmark Detection. You can check your landmarks in 60ms
License: Apache License 2.0
How can I detect the middle of the forehead?
I don't see and landmarks to detect this...Any idea?
Hi
Why the front camera not showing when I run the app ?
Hi,
I'm trying to optimize face detection.
Can you open source your Dlib-android source code ?
Thank you! btw, Happy New Year!
ps: Here is my email address [email protected]. Thanks again.
sir, can you help me. why my camera phone didn't showing anything, it just a black screen.
thankyou very much.
@gicheonkang
Hello Gicheon Kang,
why in your app\src\main\AndroidManifest.xml have
<activity android:name=".MainActivity_"
and not
<activity android:name=".MainActivity" ?
Hello,
Thanks for yours sharing.
Looks your features of landmark detection is very exciting.
Can I use your APP realize both the function of facial landmark detections and face expression recognition, like, happy, angry and distinguished.
Best Regards!
Jun Yan
Can you open source your Dlib-android source code ? I want to know how to optimize it and make it faster, thank you!!!
tks
after updating gradle files to 3.2.2 i'm getting this error bro. trying to fix the same since two days, any quick help should be greatly appreciated . thanks in advance.
def ndkRevision() {
def ff
android {
externalNativeBuild {
ff = getNdkDirectory().toString()
}
}
return "ndk location:" + ff
}
Hi,
Do we have an IOS code for the same?.
Thanks,
Divya
can you tell me how you optimized the dlib ?
will you provide the source code?
Hi Kang,
Nice work on optimizing dlib for Android.
Still, I want to improve the performance more.
Can you share with me how did you optimize the dlib?
hey, how can I change the min face size that the detector detects,please
com.android.tools.build:gradle ่ฝๅฆๅ็บงๅฐ 7.0 ๏ผๅทฒ้้ ๆๆฐ็ AndroidStudio
2021-01-19 20:22:38.390 4539-24500/? D/CameraService: MemTotal: 5512 MB, MemFree: 199 MB, Cached: 13 MB
2021-01-19 20:22:38.392 7689-7689/? I/SensorManager: registerListenerImpl() [Sensor: LGE Rotation Vector Sensor, Rate: 66667, SensorEventListener: a.a.a.j.e@d8904d1] by a.a.a.j.e.a():12
2021-01-19 20:22:38.394 7689-7689/? D/TextureView: getHardwareLayer, createNewSurface:true
2021-01-19 20:22:38.400 4539-25776/? E/Camera3-Device: Camera 1: configureStreamsLocked: isLGCamera = 0
2021-01-19 20:22:38.402 855-855/? E/CHIUSECASE: [ERROR ] chxextensionmodule.cpp:2173 InitializeOverrideSession() depth fps = 0, op_mode = 0x0, cameraId = 1
2021-01-19 20:22:38.405 855-855/? E/CHIUSECASE: [ERROR ] chxextensionmodule.cpp:4117 LGEParsingOperationMode() CHI InitializeOverrideSession StreamConfigModeLGEapp operation_mode 0x0
2021-01-19 20:22:38.405 855-855/? E/CHIUSECASE: [ERROR ] chxextensionmodule.cpp:4176 LGEParsingOperationMode() com.lge.camera.lgaf tag = 2155282432, camID(0) Data(0)
2021-01-19 20:22:38.405 855-855/? E/CHIUSECASE: [ERROR ] chxextensionmodule.cpp:4186 LGEParsingOperationMode() com.lge.camera.lgaf tag = 2155282432, camID(3) Data(0)
2021-01-19 20:22:38.405 855-855/? E/CHIUSECASE: [ERROR ] chxextensionmodule.cpp:4196 LGEParsingOperationMode() com.lge.camera.lgaf tag = 2155282432, camID(1) Data(0)
2021-01-19 20:22:38.405 855-855/? E/CHIUSECASE: [ERROR ] chxextensionmodule.cpp:2239 InitializeOverrideSession() hasvideo : 0, logicalCameraId: 1, 4
2021-01-19 20:22:38.405 855-855/? I/chatty: uid=1047(cameraserver) [email protected] identical 2 lines
2021-01-19 20:22:38.405 855-855/? E/CHIUSECASE: [ERROR ] chxextensionmodule.cpp:2239 InitializeOverrideSession() hasvideo : 0, logicalCameraId: 1, 4
2021-01-19 20:22:38.405 855-855/? E/libc: Access denied finding property "minios.camera_tof"
2021-01-19 20:22:38.405 855-855/? E/CHIUSECASE: [ERROR ] chxextensionmodule.cpp:2554 InitializeOverrideSession() CAM Perflock Setting for Non-HFR: powerHintType=9
2021-01-19 20:22:38.405 855-855/? E/CHIUSECASE: [ERROR ] chxextensionmodule.cpp:2561 InitializeOverrideSession() CAM Perflock ReleasePerfLock: m_previous powerhint = 7, cameraID = 1
2021-01-19 20:22:38.405 855-855/? E/CHIUSECASE: [ERROR ] chxperf.cpp:778 ReleasePerfLock() dennis: ReleasePerfLock: Release perflock type: 7
2021-01-19 20:22:38.408 855-855/? E/CHIUSECASE: [CONFIG ] chxusecaseutils.cpp:778 GetMatchingUsecase() usecase ID:1
2021-01-19 20:22:38.408 855-855/? E/CHIUSECASE: [CONFIG ] chxextensionmodule.cpp:2635 InitializeOverrideSession() Session_parameters FPS range 7:30, BatchSize: 1 FPS: 30 SkipPattern: 1, cameraId = 1 selected use case = 1
2021-01-19 20:22:38.408 855-855/? E/CHIUSECASE: [ERROR ] chxusecaseutils.cpp:2074 CreateUsecaseObject() GetPerfLockManager GetCameraId = 1
2021-01-19 20:22:38.408 855-855/? E/CHIUSECASE: [ERROR ] chxperf.cpp:778 ReleasePerfLock() dennis: ReleasePerfLock: Release perflock type: 0
2021-01-19 20:22:38.408 855-855/? E/CHIUSECASE: [ERROR ] chxperf.cpp:778 ReleasePerfLock() dennis: ReleasePerfLock: Release perflock type: 1
2021-01-19 20:22:38.408 855-855/? E/CHIUSECASE: [ERROR ] chxperf.cpp:778 ReleasePerfLock() dennis: ReleasePerfLock: Release perflock type: 6
2021-01-19 20:22:38.408 855-855/? E/CHIUSECASE: [ERROR ] chxperf.cpp:778 ReleasePerfLock() dennis: ReleasePerfLock: Release perflock type: 23
2021-01-19 20:22:38.408 855-855/? E/CHIUSECASE: [ERROR ] chxperf.cpp:720 AcquirePerfLock() dennis: AcquirePerfLock: Acquire perflock type: 0
2021-01-19 20:22:38.409 855-855/? E/CHIUSECASE: [ERROR ] LGDistortionCorrection.cpp:176 Create() DistortionCorrection 0x716ee7dac0 Create
have you tried to make .so file for face recognition using this dlib_face_recognition_resnet_model_v1 model
Hello,
I acknowledge that the current implementation of the fast face is pretty good, but I think that the face detection + extraction is being made atomically, hence, when you skip frames (for speedup purposes) you are skipping also the landmark relocalization, and that makes the whole app a little more clunky, because you can see that the landmarks stay in the same position for N=3 frames.
My idea is basically separate the face detection and the landmark extraction, so you can make face detection once every 5 or 6 frames, but keep extracting landmarks every 1 or 2 frames. The problem is that I know from little to nothing of JNI, and I don't see how the two processes (face detect. and landmark extract.) can be separated, because they seem to be in the same native method. How could I accomplish this?
Note that this would also be useful because you could forget about HOG face detection from DLIB and try a ViolaJones from OpenCV, or even other approximations...
And other unrelated questions:
Can you provide the source code of dlib with the changes? Or at least a brief explanations of the changes made to dlib?
Why the source files of the JNI libraries are not in the project? Did you make any changes to them? (the ones in here: https://github.com/tzutalin/dlib-android/tree/master/jni)
Thanks in advance
why apk 88 mb ?
aar 11 mb
i hate this project
I am developing makeup app in android so I want to ask that how do i select only lip's landmark and fill color inside like(Lipstick)
nvm solved performance myself
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. ๐๐๐
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.