normyx / mmm-facial-recognition-ocv3 Goto Github PK
View Code? Open in Web Editor NEWLicense: MIT License
License: MIT License
Hi.
How i can get stream from IP Camera ?
I have the same issue like described here: paviro/MMM-Facial-Recognition#62
The PiCam is not opening, and the red light is not active. Anyone had this problem and has a fix?
The tools.facialrecognition.py works fine.
In the MMM-Console i can see that "Module is hidden". It doesn't say which module, but i only defined one to be not shown to everyone. But it seems the recognition is never triggered.
Hi everyone,
When i want to capture a face i have this error, do u know what it is ?
Traceback (most recent call last): File "tools.capture.py", line 35, in <module> capture.capture() File "/home/pi/MagicMirror/modules/MMM-Facial-Recognition-OCV3/lib/tools/capture.py", line 41, in capture input() File "<string>", line 0 SyntaxError: unexpected EOF while parsing
I have a ps3 eye usb cam installed. When starting "python tools.capture.py" for capture training i get:
Loading PiCamera
PiCamera loaded
Capturing positive training images.
Press enter to capture an image.
Press Ctrl-C to quit.
mmal: mmal_vc_component_create: failed to create component 'vc.ril.camera' (1:ENOMEM)
mmal: mmal_component_create_core: could not create component 'vc.ril.camera' (1)
Exception in thread Thread-1:
Traceback (most recent call last):
File "/usr/lib/python2.7/threading.py", line 801, in __bootstrap_inner
self.run()
File "/home/pi/MagicMirror/modules/MMM-Facial-Recognition-OCV3/lib/common/picam.py", line 25, in run
with picamera.PiCamera() as camera:
File "/usr/lib/python2.7/dist-packages/picamera/camera.py", line 431, in init
self._init_camera(camera_num, stereo_mode, stereo_decimate)
File "/usr/lib/python2.7/dist-packages/picamera/camera.py", line 460, in _init_camera
"Camera is not enabled. Try running 'sudo raspi-config' "
PiCameraError: Camera is not enabled. Try running 'sudo raspi-config' and ensure that the camera has been enabled.
What do I have to configure, to get it working with an usb webcam?
Traceback (most recent call last):
File "tools.capture.py", line 9, in
from lib.tools.capture import ToolsCapture
File "/home/pi/MagicMirror/modules/MMM-Facial-Recognition-OCV3/lib/tools/capture.py", line 10, in
from builtins import input
ImportError: No module named builtins
anyone can help?
when I run sudo apt-get install libavcodec-dev libavformat-dev libswscale-dev libv4l-dev
it shows error, how can I solve it?
libavcodec-dev : Depends: libavutil-dev (= 7:3.2.10-1deb9u1) but it is not going to be installeddeb9u1) but it is not going to be installed
Depends: libswresample-dev (= 7:3.2.10-1
libavformat-dev : Depends: libavformat57 (= 7:3.2.10-1deb9u1) but 7:3.2.10-1deb9u1+rpt1 is to be installed
Depends: libavutil-dev (= 7:3.2.10-1deb9u1) but it is not going to be installeddeb9u1) but it is not going to be installed
Depends: libswresample-dev (= 7:3.2.10-1
libswscale-dev : Depends: libavutil-dev (= 7:3.2.10-1deb9u1) but it is not going to be installeddeb9u1) but 7:3.2.10-1~deb9u1+rpt1 is to be installed
Depends: libswscale4 (= 7:3.2.10-1
E: Unable to correct problems, you have held broken packages.
Hi @normyx
Cool looking upgrade to OpenCV project, but what is the current status of this project.
I.e. Does it work?
Cheers,
[ 47%] Built target pch_Generate_opencv_test_flann
[ 48%] Building CXX object modules/flann/CMakeFiles/opencv_test_flann.dir/test/test_lshtable_badarg.cpp.o
c++: internal compiler error: Speicherzugriffsfehler (program cc1plus)
Please submit a full bug report,
with preprocessed source if appropriate.
See <file:///usr/share/doc/gcc-6/README.Bugs> for instructions.
modules/flann/CMakeFiles/opencv_test_flann.dir/build.make:62: die Regel für Ziel „modules/flann/CMakeFiles/opencv_test_flann.dir/test/test_lshtable_badarg.cpp.o“ scheiterte
make[2]: *** [modules/flann/CMakeFiles/opencv_test_flann.dir/test/test_lshtable_badarg.cpp.o] Fehler 4
CMakeFiles/Makefile2:1793: die Regel für Ziel „modules/flann/CMakeFiles/opencv_test_flann.dir/all“ scheiterte
make[1]: *** [modules/flann/CMakeFiles/opencv_test_flann.dir/all] Fehler 2
Makefile:160: die Regel für Ziel „all“ scheiterte
make: *** [all] Fehler 2
Sorry for german language ... i know i should make a report issue but that does not help me.
Happens when i make opencv, no difference between make -j4 or make VERBOSE=1 oder just make ...
greetings
I received this error while building opencv:
make[2]: *** [modules/videoio/CMakeFiles/opencv_videoio.dir/build.make:128: modules/videoio/CMakeFiles/opencv_videoio.dir/src/cap_ffmpeg.cpp.o] Error 1
make[1]: *** [CMakeFiles/Makefile2:8811: modules/videoio/CMakeFiles/opencv_videoio.dir/all] Error 2
make: *** [Makefile:163: all] Error 2
It was after entering "make -j4" in the command line.
There were a few red marked words before the code up here. Let me know if you would like to take a look.
i just installed and added the facial recognition module in the config.js.
facial recognition is working fine but,other modules that have been added in config.js is not showing up
bash: /etc/dphys-swapfile: permission denied
getting this error
need help
Remember to set the name list environment variable FACE_USERS
Loading PiCamera
PiCamera loaded
Loading training data...
mmal: mmal_vc_port_enable: failed to enable port vc.null_sink:in:0(OPQV): ENOSPC
mmal: mmal_port_enable: failed to enable connected port (vc.null_sink:in:0(OPQV))0x695147f0 (ENOSPC)
mmal: mmal_connection_enable: output port couldn't be enabled
Exception in thread Thread-1:
Traceback (most recent call last):
File "/usr/lib/python2.7/threading.py", line 801, in __bootstrap_inner
self.run()
File "/home/pi/MagicMirror/modules/MMM-Facial-Recognition-OCV3/lib/common/picam.py", line 25, in run
with picamera.PiCamera() as camera:
File "/usr/lib/python2.7/dist-packages/picamera/camera.py", line 433, in init
self._init_preview()
File "/usr/lib/python2.7/dist-packages/picamera/camera.py", line 513, in _init_preview
self, self._camera.outputs[self.CAMERA_PREVIEW_PORT])
File "/usr/lib/python2.7/dist-packages/picamera/renderers.py", line 558, in init
self.renderer.inputs[0].connect(source).enable()
File "/usr/lib/python2.7/dist-packages/picamera/mmalobj.py", line 2212, in enable
prefix="Failed to enable connection")
File "/usr/lib/python2.7/dist-packages/picamera/exc.py", line 184, in mmal_check
raise PiCameraMMALError(status, prefix)
PiCameraMMALError: Failed to enable connection: Out of resources
Training data loaded!
OpenCV Error: Assertion failed (!buf.empty() && buf.isContinuous()) in imdecode_, file /home/pi/opencv/modules/imgcodecs/src/loadsave.cpp, line 637
Traceback (most recent call last):
File "tools.facerecognition.py", line 45, in
frame = camera.read()
File "/home/pi/MagicMirror/modules/MMM-Facial-Recognition-OCV3/lib/common/picam.py", line 55, in read
image = cv2.imdecode(data, 1)
cv2.error: /home/pi/opencv/modules/imgcodecs/src/loadsave.cpp:637: error: (-215) !buf.empty() && buf.isContinuous() in function imdecode_
Once again me ... another problem:
When i start training i get the following result:
python tools.train.py
Pictures and names are recognized .. but then this follows:
Training model with threshold 80 Traceback (most recent call last): File "tools.train.py", line 14, in <module> ToolsTrain().train() File "/home/pi/MagicMirror/modules/MMM-Facial-Recognition-OCV3/lib/tools/train.py", line 71, in train model = ToolsConfig.model() File "/home/pi/MagicMirror/modules/MMM-Facial-Recognition-OCV3/lib/tools/config.py", line 99, in model return CommonConfig.model(cls.POSITIVE_THRESHOLD) File "/home/pi/MagicMirror/modules/MMM-Facial-Recognition-OCV3/lib/common/commonconfig.py", line 51, in model model = cv2.face.LBPHFaceRecognizer_create(threshold=thresh) AttributeError: 'module' object has no attribute 'face'
I got some config syntax error when I change some config.js to setup in other module.
I already done training and test.
{
module: "calendar",
header: "SCHEDULE",
position: "top_left",
config: {
calendars: [
{
symbol: "calendar-check-o ",
url: "*******"
}
]
}
classes: "User1"
},
I already used {} and "", ''. But I got the same error.
What did I wrong with this?
Thank you for your support anyway.
Hi, I have already done the capturing, training and testing of the model. Everything up to here works well. However, when I try to add the module to the config.js file and tried running the mirror, I received an error: "WARNING! Could not validate config file. Please correct syntax errors. Starting with default configuration." The mirror still launches, but I will get an error message of "Please create config file. See README for more information. If you get this message, while your config file is already corrected, your config file probably contains an error. Use a JavaScript linter to validate your file."
Only when I removed the MMM-Facial-Recognition-OCV3 module then the magic mirror runs as per normal.
Hi there, we have trained two separate faces and .pgm images have appeared in /home/pi/training_data but no .xml file. Terminal printout as follows:
Training model with threshold 80
('Training data saved to', 'training.xml')
No error messages but no .xml file anywhere. Please help - this is final stage of school project due in this weekend!
Hi Normyx,
Why when the magic mirror running with this module the is black display.
Please give the script to magicmirror so it doesn't turn black covering all other modules
Thanks
When I want to run python tools.train.py
I get an AttributeError: 'module' object has no attribute 'face'.
Had anyone the same error or/and a solution?
Hello,
I started to build opencv according to the installation instructions on a Raspi 3 plus , running buster.
I tried two times - first installing python 3 , then another clean installation and python 2. In both cases "make -j4" terminates with error 2 after "Built target opencv_dnn ". I find the messages "AVFMT_RAWPICTURE was not declared in this scope" and "CODEC_FLAG_GLOBAL_HEADER was not declared in this scope"
I have no clues what could be the reason. Has anyone an idea, what could be the reason. Any help would be very appreciated.
Thanks in advance
Greetings;
Well after two weeks of trying to install Facial Recognition on my MM, it all works. Now one last final bug to squash and I should be able to reap the rewards.
So Facial Recognition is loading fine and my modules have the appropriate classes assigned. Terminal output reads that I am indeed recognized;
[MMM-Facial-Recognition-OCV3] User Stiofan with confidence 70.7123926022 logged in.
However, none of the modules with classes assigned to my profile are revealed. Any idea why???
can i enable/disable the facial recognition modules using PIR sensors.
facial recognition is keeping camera busy all the time. so if i want to use camera for some other purpose its hard to do.
so is it possible ?
Thank you
I have captured and trained the module using terminal on my mac, but when adding to the config file and adding classes to each other module, I continue to get errors in the config. Before adding the facial recognition module, the magicmirror would start up without a problem, now adding the single module creates a config problem. I am very new to this and just wondering if i am missing something simple, thanks!
Hello @normyx ,
I recently found this module and installed all the requirements successfully.
However, when I run the command
python tools.capture.py
I always run into the error
Traceback (most recent call last):
File "tools.capture.py", line 9, in <module>
from lib.tools.capture import ToolsCapture
File "/home/pi/MagicMirror/modules/MMM-Facial-Recognition-OCV3/lib/tools/capture.py", line 20 in <module>
from config import ToolsConfig
ImportError: No module named 'config'
Do you have any clues what I might be missing?
Thanks!
Hi,
great Tutorial! Unfortunatly, the module is unlocking every module automatically! The recognition (when I try it with tools.facerecognition.py gives me weak:User1) seems to work..
Down you can see my config, where I tried to unlock my news Feed as a test, but it is unlocked from the beginning.. Any guesses?
Thank you!
Hi,
first of all, good job for your works.
I want to integrate the facial recognition with the pir sensor to preserve CPU load.
So I want to start a facial recognition only when a USER_PRESENCE is send by PIR SENSOR.
I saw on your code (facerecognition.py) :
if detecion is true, will be used to disable detection if you use a PIR sensor and no motion is detected
if detection_active is True:
but do not understand how to change the status of this variable as the python script is running.
My other idea is to start the python script when USER_PRESENCE is true and try to stop it when USER_PRESENCE is false, but i do not know how to stop it properly.
what do you think about it ? can you give me the right direction in order to do it ?
Hello,
i have a problem with this module. All went well till i came to the point where i have to run the
python tools.capture.py
I always run into the error
pi@raspberrypi:~/MagicMirror/modules/MMM-Facial-Recognition-OCV3 $ python tools.capture.py Traceback (most recent call last): File "tools.capture.py", line 9, in <module> from lib.tools.capture import ToolsCapture File "/home/pi/MagicMirror/modules/MMM-Facial-Recognition-OCV3/lib/tools/capture.py", line 16, in <module> import cv2 ImportError: No module named cv2
Do you have any clues to fix this? Thanks!
Ive been trying to find somewhere in the code for inverting the camera because it does not recognize upside down faces.
Hello,
When I exec this command line :
make -j4
I have this error after few minutes exec :
error "This header with legacy C API declarations has been removed from OpenCV. Legacy contants are available from legacy/constants_c.h file.
Is it normal ?
Thank !
So I got it all running without any errors, but I'm not recognized when i use python tools.facerecognition.py
The point i have come to:
So I have taken pictures, got them converted into the folder named Daniel in MMM-Facial-Recognition-OCV3/training_data
I ran python tools.train.py.
and got the training file and this output:
pi@raspberrypi:~/MagicMirror/modules/MMM-Facial-Recognition-OCV3 $ python tools.train.py
['Daniel']
Reading training images...
Assign label 1 to Daniel
Read 186 positive images and 400 negative images.
186 images from subject Daniel
Training model with threshold 80
('Training data saved to', 'training.xml')
Please add or update (if you added new people not just new images) ['Daniel'] inside config.js (mirror module) or config.py (model tester). You can change the names to whatever you want, just keep the same order and you'll be fine.`
if I use python tools.facerecognition.py
it just says "None" when face recognized, and I get this:
pi@raspberrypi:~/MagicMirror/modules/MMM-Facial-Recognition-OCV3 $ python tools.facerecognition.py
['Daniel']
Loading PiCamera
PiCamera loaded
Loading training data...
Training data loaded!
1.79769313486e+308
None
1.79769313486e+308
None
I have tried to change User1 into Daniel within config.py in the folder MMM-Facial-Recognition-OCV3/lib/tools without success.
What do i do?
When I run python tools.capture.py
I get the following:
Traceback (most recent call last):
File "tools.capture.py", line 9, in
from lib.tools.capture import ToolsCapture
File "/home/pi/MagicMirror/modules/MMM-Facial-Recognition-OCV3/lib/tools/capture.py", line 27, in
from config import ToolsConfig
File "/home/pi/MagicMirror/modules/MMM-Facial-Recognition-OCV3/lib/tools/config.py", line 12, in
from commonconfig import CommonConfig
File "/home/pi/MagicMirror/modules/MMM-Facial-Recognition-OCV3/lib/common/commonconfig.py", line 16, in
class CommonConfig:
File "/home/pi/MagicMirror/modules/MMM-Facial-Recognition-OCV3/lib/common/commonconfig.py", line 28, in CommonConfig
(CV_MAJOR_VER, CV_MINOR_VER, mv1) = cv2.version.split(".")
ValueError: too many values to unpack
Any help with this would be much appreciated!
Hey,
How can I speed up the facial recognition? Right now it takes about 5-6 seconds if I stand perfectly still.
It seems to detect me as Stranger really quickly but then take a few seconds and then load my name/profile.
When i run capture.py i get the following error:
Traceback (most recent call last):
File "tools.capture.py", line 9, in
from lib.tools.capture import ToolsCapture
File "/home/pi/MagicMirror/modules/MMM-Facial-Recognition-OCV3/lib/tools/capture.py", line 10, in
from builtins import input
ImportError: No module named builtins
When I run the python tools.facerecognition.py to test, my results were above 70. However, when I run the magic mirror, I keep getting the "User undefined with confidence null logged in". I have adjusted the threshold under the config.js to a value of 70, but still this issue occurs. I have also took over 60 images of myself, just to ensure that there is enough sample size. Should I take more pictures, or what should I do?
after running
"cmake -D CMAKE_BUILD_TYPE=RELEASE
-D CMAKE_INSTALL_PREFIX=/usr/local
-D INSTALL_C_EXAMPLES=OFF
-D INSTALL_PYTHON_EXAMPLES=ON
-D OPENCV_EXTRA_MODULES_PATH=~/opencv_contrib/modules
-D BUILD_EXAMPLES=ON .."
I get the following error:
CMake Error: The following variables are used in this project, but they are set to NOTFOUND.
Please set them or make sure they are set and tested correctly in the CMake files:
Protobuf_LIBRARY
linked by target "opencv_dnn_modern" in directory /home/pi/opencv_contrib/modules/dnn_modern
-- Configuring incomplete, errors occurred!
I've setup my smart mirror freshly just to make sure that everything is on the latest version.
This is the full log:
-- cvconfig.h is in: /home/pi/opencv/build
--
CMake Error: The following variables are used in this project, but they are set to NOTFOUND.
Please set them or make sure they are set and tested correctly in the CMake files:
Protobuf_LIBRARY
linked by target "opencv_dnn_modern" in directory /home/pi/opencv_contrib/modules/dnn_modern
-- Configuring incomplete, errors occurred!
See also "/home/pi/opencv/build/CMakeFiles/CMakeOutput.log".
See also "/home/pi/opencv/build/CMakeFiles/CMakeError.log".
When i run python tools.capture.py.
on python 3.4.2
it's show error
Traceback (most recent call last):
File "/home/pi/MagicMirror/modules/MMM-Facial-Recognition-OCV3/tools.capture.py", line 9, in
from lib.tools.capture import ToolsCapture
File "/home/pi/MagicMirror/modules/MMM-Facial-Recognition-OCV3/lib/tools/capture.py", line 19, in
from config import ToolsConfig
ImportError: No module named 'config'
i have a problem with the code in facialrecognition in mm directory in lib
Traceback (most recent call last):
File "/home/pi/MagicMirror/modules/MMM-Facial-Recognition-OCV3/lib/mm/config.py", line 18, in
class MMConfig (CommonConfig):
File "/home/pi/MagicMirror/modules/MMM-Facial-Recognition-OCV3/lib/mm/config.py", line 20, in MMConfig
CONFIG_DATA = json.loads(sys.argv[1]);
IndexError: list index out of range
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 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. 📊📈🎉
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 ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.