karan-malik / facemaskdetector Goto Github PK

Real time face-mask detection using Deep Learning and OpenCV

License: MIT License

Python 100.00%

opencv computer-vision python3 python deep-learning deep-neural-networks convolutional-neural-networks cnn cnn-keras face-mask-detection

facemaskdetector's Introduction

Face-Mask Detector

Real time face-mask detection using Deep Learning and OpenCV

About Project

This project uses a Deep Neural Network, more specifically a Convolutional Neural Network, to differentiate between images of people with and without masks. The CNN manages to get an accuracy of 98.2% on the training set and 97.3% on the test set. Then the stored weights of this CNN are used to classify as mask or no mask, in real time, using OpenCV. With the webcam capturing the video, the frames are preprocessed and and fed to the model to accomplish this task. The model works efficiently with no apparent lag time between wearing/removing mask and display of prediction.

The model is capable of predicting multiple faces with or without masks at the same time

Working

With Mask

No Mask

Dataset

The data used can be downloaded through this link or can be downloaded from this repository as well (folders 'test' and 'train'). There are 1314 training images and 194 test images divided into two catgories, with and without mask.

How to Use

To use this project on your system, follow these steps:

1.Clone this repository onto your system by typing the following command on your Command Prompt:

git clone https://github.com/Karan-Malik/FaceMaskDetector.git

followed by:

cd FaceMaskDetector

Download all libaries using::

pip install -r requirements.txt

Run facemask.py by typing the following command on your Command Prompt:

python facemask.py

The Project is now ready to use !!

facemaskdetector's People

Contributors

Stargazers

Watchers

Forkers

haroldmurcia vinashak9 jeet2610 sarangdeshmukh7 spursbyte pradhansuman3112 abhishekkagautam ishyanth khalilcse mohamedalarosy dwaltsch sai-sumith tienhoangvan shalu228 sindhujarajidi pintu1803 jeet-singh-win akpythonyt aarushisingh09 subhankar-biswas-dot radfar whoabhaysharma manikantasripadi hippyaki preethamkonu nimisharenjith123 umairjavaid nabin-01 lisaterumi juparave harshithav-csr jeslone tanzimrusho annehalate chris-netizen makkatech manasdas17 hari-stack swetabhofficial divineanon josh-algors kripanshu ktasneem103 ankur-singh12 yassir21-max maheshv18 gilgamesh-bot subithou nitinjaiswal7537 ta00000 marenan semeer37 anshumalivfx jagan-satwik-reddy raskrreia leonile j-sudhanshu phoenix26012000 nivu webstorage119 jianglanni ishanvohra2 doctornemesis erikalty shreymukh rohan1805 sreelakshmisatheesh itahir7 srajanagrawal bryanffs1 adhi-t rajaram-reghuram akshitsingh07 ajunlonglive ryanbekabe sanju-31 alenscaria ramshankerg techcodershayakray shikhacodes ubaidkhan08 cquinn05 jooewood harshitbh92 akkhileshdk shiran98 gargeetrishra affandi-arc stysky ritesg temphezrumi loicengu dhruvshelke15 sahilchaudhari-746 varshanipreddy rcky225 varsha-sunil anhlinhai mo3taz208 gerazayisti

facemaskdetector's Issues

Error while running code

Can you please tell me that on which version of python the code was written? I'm getting this error now after trying a lot.

Can you please tell me that on which version of python the code was written? I'm getting this error now after trying a lot.
help me with this...
or please tell me step by step which version of python I have to use then which are the libraries I have to install.
I have followed all the instructions from the readme file in the project, still, I'm not able to run that.

Originally posted by @deepanshuparuthi in #8 (comment)

How to deal with the problem "NameError: name 'mymodel' is not defined"

Hi, I'm glad to find your work.

I'm trying to use this work, but I face the problem "NameError: name 'mymodel' is not defined".
I don't have any idea to solve this problem so far because I've never used Keras and like MLs so on before.

Please could you tell me how to do it?

Thanks.

no requirements.txt found

requirements.txt is not there for ease of use for the users

[cheeky feature request] detect funky masks (next-gen)

some are more easy (non human faces)

some are human based but distorted or have an obvious (non-mask) overlay

this is probably still detectable

challenge accepted... (partial mask is part of the graphics) ;)

source: https://www.ebay.com/sch/i.html?_nkw=funny+face+mask

seams and joints (requires high resolution), nose shadow non-consistent with other shadow cast on face, and skin tone difference would normally improve (heuristic) results. I wonder how ML would handle it..

regarding how to use

Inorder to clone this repository that particular command is not getting executed...it is showing invalid syntax can you please provide solution to this problem pls...

Regarding Face mask Detector Project

I am not able to run the file which shows an error for numpy libs in anaconda site packages

Error while running the code

C:\Users\Ganesh\AppData\Local\Programs\Python\Python39\lib\site-packages\keras\engine\training.py:1915: UserWarning: Model.fit_generator is deprecated and will be removed in a future version. Please use Model.fit, which supports generators.
warnings.warn('Model.fit_generator is deprecated and '
Traceback (most recent call last):
File "C:\Users\Ganesh\Desktop\FaceMask\FaceMaskDetector\facemask.py", line 58, in
model_saved=model.fit_generator(
File "C:\Users\Ganesh\AppData\Local\Programs\Python\Python39\lib\site-packages\keras\engine\training.py", line 1918, in fit_generator
return self.fit(
File "C:\Users\Ganesh\AppData\Local\Programs\Python\Python39\lib\site-packages\keras\engine\training.py", line 1108, in fit
data_handler = data_adapter.get_data_handler(
File "C:\Users\Ganesh\AppData\Local\Programs\Python\Python39\lib\site-packages\keras\engine\data_adapter.py", line 1348, in get_data_handler
return DataHandler(*args, **kwargs)
File "C:\Users\Ganesh\AppData\Local\Programs\Python\Python39\lib\site-packages\keras\engine\data_adapter.py", line 1138, in init
self._adapter = adapter_cls(
File "C:\Users\Ganesh\AppData\Local\Programs\Python\Python39\lib\site-packages\keras\engine\data_adapter.py", line 916, in init
super(KerasSequenceAdapter, self).init(
File "C:\Users\Ganesh\AppData\Local\Programs\Python\Python39\lib\site-packages\keras\engine\data_adapter.py", line 793, in init
peek, x = self._peek_and_restore(x)
File "C:\Users\Ganesh\AppData\Local\Programs\Python\Python39\lib\site-packages\keras\engine\data_adapter.py", line 927, in _peek_and_restore
return x[0], x
File "C:\Users\Ganesh\AppData\Local\Programs\Python\Python39\lib\site-packages\keras_preprocessing\image\iterator.py", line 65, in getitem
return self._get_batches_of_transformed_samples(index_array)
File "C:\Users\Ganesh\AppData\Local\Programs\Python\Python39\lib\site-packages\keras_preprocessing\image\iterator.py", line 231, in _get_batches_of_transformed_samples
x = img_to_array(img, data_format=self.data_format)
File "C:\Users\Ganesh\AppData\Local\Programs\Python\Python39\lib\site-packages\keras_preprocessing\image\utils.py", line 309, in img_to_array
x = np.asarray(img, dtype=dtype)
File "C:\Users\Ganesh\AppData\Local\Programs\Python\Python39\lib\site-packages\numpy\core_asarray.py", line 83, in asarray
return array(a, dtype, copy=False, order=order)
TypeError: array() takes 1 positional argument but 2 were given

typo

from keras.optimizers import Adam
instead of
from keras.optimizers import adam

Error Encountered

please help me resolve this