estebanuri / face_recognition Goto Github PK

Do you have plans to quantize the model?
Or can you provide the original .h5 file or saved model for me to do uint8 quantization?

Thanks.

please can you help me to merge both face recognition and face mask detector

Hello esteban, very nice work and research, thanks for you blog thats so enlightened me, but can i want ask something about mobilefacenet output size, is there any reason for using 192 as output size of mobilefacenet model

Is there an easy way to port to pi with the current model ?

I'v been run into this error as below,please help me:

Internal error: Cannot create interpreter: Op builtin_code out or range: 101. Are you using old TFLite binary with newer model?Registration failed.

    at org.tensorflow.lite.NativeInterpreterWrapper.createInterpreter(Native Method)
    at org.tensorflow.lite.NativeInterpreterWrapper.<init>(NativeInterpreterWrapper.java:73)
    at org.tensorflow.lite.NativeInterpreterWrapper.<init>(NativeInterpreterWrapper.java:52)
    at org.tensorflow.lite.Interpreter.<init>(Interpreter.java:114)
    at com.zh.lite.detection.tflite.TFLiteObjectDetectionAPIModel.create(TFLiteObjectDetectionAPIModel.java:145)

The app works great with mobilefacenet tflite model but when i switch to facenet model and changing input size to 160 and output to 512, it crashes as soon as a face is seen

IT is NOT an ERROR.There is code written as a comment in the project. What they mean. I'm just studying the code itself and don't quite understand everything

Now I want to make it running background so that the feature is available while I am using other applications. It means I should open camera in service without preview, and process it in service.

Thanks for support!

Hi Sir,
Sometimes the recognition is wrong, for example personA is recognized as personC. Is there any cutoff score of percentage confidence or probability, so that we can show the name only when its confidence is lets say "more than 90%" ?

Thanks for the Good App.

But when you add any picture it save it temporarily and it worked fine with back camera as long as you are on the app but once you exit out and come back you need to add these pictures again it does not saved permanently on local phone .

So request you to save it locally so next time if I want to scan any face I dont need to add it again and again.

Same front camera problem is there but back camera is working perfectly.

Just need to know which model you used in the app

Facenet.tflite or facenet_hiroki.tflite

Or you have used both the modes in the app

Because it is increases the app size

Thanks again for the good work

tried this on my samsung a20 on the front camera didn't work. also it has "please update" warning when initiating the camera

@estebanuri
Hi i need to add the images from local storage. I tried but that is not showing the name of that image after detected. can you explain how to add the images from local storage?

otherwise how you added the images to that one?

Invalid argument(s): Failed to lookup symbol (undefined symbol: TfLiteGpuDelegateV2Create)

Hello @estebanuri or anyone else. Please has anyone finally been able to store the images locally or online , am facing an issue trying to do that. i've gone through all the #issues but still no solution. Please can anyone help

how to save and retrieve data from database online like firebase ?

When the app closes or pauses state It does not recognize the face. How to save it to the local Database if I can recognize registered user after closing the app.

Hi, wonderful project! Can you add a license to this project? Thanks!

Is there a way to save person's picture and name after adding a person?

Thanks,
Kaishi

Can I transform java code into kotlin and how because when i convert them and fix error the application crashs in the launch phase

How to make the training with the names entered saved? After closing the app, when I come back I have to do the face registration again

Am getting this error
A/libc: Fatal signal 11 (SIGSEGV), code 1, fault addr 0xb9e93668 in tid 19004 (FinalizerDaemon)

What could be the issue

Hi sir can you please extend this project so any image in Gallery can be used for face recognition not necessary to capture image using camera

Thanks in advance
Raja

Sir I used your project to integrate in my project in which I used tensorflow API for object detection. But when I integerate your project with my project , the app crash because there are two tflite file (1 is from your project and 1 of my project) . Kindly help me to sort out the problem.

I was stored data bt the data is in gson format i want to seprate data column wise and store it. and fetch data for comparing faces.

is it possible and if it is can anyone share how to do it with me

I'm very happy with your project and it has solved most of my problems,
how can i implement liveness detection using this very solution, thanks
1405.2227.pdf

Hi,
Face detection not working in Landscape orientation. How to fix this?

Thanks for sharing this awesome work!

I now set the FaceDetectorOptions flag to be "LANDMARK_MODE_ALL" and would like to draw the landmarks on faceBmp, but i am new to the Google ML Kit. Could you please show me some code snipet to achieve this?

Hi
I have implemented your code in my application very successfully and I really appreciate you for the effort you have put in providing this code.

Now my problem is if a person is in database then it recognize him or her properly but if he is a new face which is not in the database still it recognizes as some one else.

I have tried with a database of 350 users and every unknown entry it recognize as some or other name from the database.

Please help and tell me what mistake I have been doing .

Thanks
Raja

Hi is this possible to add images from internal storage. Please anyone help me to resolve my issue.

Thanks in advance

Hi ,

This is an excellent example for face recognition , I have tried many examples , this seems to be more accurate .
Please consider my request to enhance the feature i.e add the images from the local directory and save them permanently .

Regards,
Ganeshc

Thank you for the amazing project!
I did not see that you did face alignment based on landmarks before feeding the model, did I miss it in the code?
Are there any plans to add this?

Hi, I want to add the images from external storage. How can i add images from external storage. please help me to resolve this issue.