Mike  Kozey

Mike Kozey

1620785530

Face Mask Detection App In Flutter With TensorFlow Lite

Let’s learn how to build a flutter app that detects whether the person is wearing a mask or not on a live camera.

COVID-19 crises have drastically affected our livelihood. There are many guidelines given by WHO to prevent the spread of the COVID-19 virus. This virus is very dangerous and infectious. In today’s scenarios, it has become mandatory to wear a mask in public places. In many countries, people are even charged money for not wearing a mask. So it has become our moral duty to wear a mask in public places, but some people are not following the guidelines. The system can’t identify the people who are not wearing a mask, so it has become important to build a tool to identify the person whether he/she is wearing a mask or not. With the help of Machine Learning & Deep Learning, we can easily build a model and train it with a dataset to solve this problem and help in preventing the spread of the COVID-19 virus.

In this blog, we shall learn how to build a Face Mask Detection app with flutter using tflite package to identify whether the person is wearing a mask or not.

Table of content:

Install Packages

Configure Project

Download training dataset & train our model

Initializing Camera

Load Model

Run Model

Camera Preview

Full Code

Demo Module:

#tensorflow #dart #flutter

What is GEEK

Buddha Community

Face Mask Detection App In Flutter With TensorFlow Lite

Google's Flutter 1.20 stable announced with new features - Navoki

Flutter Google cross-platform UI framework has released a new version 1.20 stable.

Flutter is Google’s UI framework to make apps for Android, iOS, Web, Windows, Mac, Linux, and Fuchsia OS. Since the last 2 years, the flutter Framework has already achieved popularity among mobile developers to develop Android and iOS apps. In the last few releases, Flutter also added the support of making web applications and desktop applications.

Last month they introduced the support of the Linux desktop app that can be distributed through Canonical Snap Store(Snapcraft), this enables the developers to publish there Linux desktop app for their users and publish on Snap Store.  If you want to learn how to Publish Flutter Desktop app in Snap Store that here is the tutorial.

Flutter 1.20 Framework is built on Google’s made Dart programming language that is a cross-platform language providing native performance, new UI widgets, and other more features for the developer usage.

Here are the few key points of this release:

Performance improvements for Flutter and Dart

In this release, they have got multiple performance improvements in the Dart language itself. A new improvement is to reduce the app size in the release versions of the app. Another performance improvement is to reduce junk in the display of app animation by using the warm-up phase.

sksl_warm-up

If your app is junk information during the first run then the Skia Shading Language shader provides for pre-compilation as part of your app’s build. This can speed it up by more than 2x.

Added a better support of mouse cursors for web and desktop flutter app,. Now many widgets will show cursor on top of them or you can specify the type of supported cursor you want.

Autofill for mobile text fields

Autofill was already supported in native applications now its been added to the Flutter SDK. Now prefilled information stored by your OS can be used for autofill in the application. This feature will be available soon on the flutter web.

flutter_autofill

A new widget for interaction

InteractiveViewer is a new widget design for common interactions in your app like pan, zoom drag and drop for resizing the widget. Informations on this you can check more on this API documentation where you can try this widget on the DartPad. In this release, drag-drop has more features added like you can know precisely where the drop happened and get the position.

Updated Material Slider, RangeSlider, TimePicker, and DatePicker

In this new release, there are many pre-existing widgets that were updated to match the latest material guidelines, these updates include better interaction with Slider and RangeSliderDatePicker with support for date range and time picker with the new style.

flutter_DatePicker

New pubspec.yaml format

Other than these widget updates there is some update within the project also like in pubspec.yaml file format. If you are a flutter plugin publisher then your old pubspec.yaml  is no longer supported to publish a plugin as the older format does not specify for which platform plugin you are making. All existing plugin will continue to work with flutter apps but you should make a plugin update as soon as possible.

Preview of embedded Dart DevTools in Visual Studio Code

Visual Studio code flutter extension got an update in this release. You get a preview of new features where you can analyze that Dev tools in your coding workspace. Enable this feature in your vs code by _dart.previewEmbeddedDevTools_setting. Dart DevTools menu you can choose your favorite page embed on your code workspace.

Network tracking

The updated the Dev tools comes with the network page that enables network profiling. You can track the timings and other information like status and content type of your** network calls** within your app. You can also monitor gRPC traffic.

Generate type-safe platform channels for platform interop

Pigeon is a command-line tool that will generate types of safe platform channels without adding additional dependencies. With this instead of manually matching method strings on platform channel and serializing arguments, you can invoke native class and pass nonprimitive data objects by directly calling the Dartmethod.

There is still a long list of updates in the new version of Flutter 1.2 that we cannot cover in this blog. You can get more details you can visit the official site to know more. Also, you can subscribe to the Navoki newsletter to get updates on these features and upcoming new updates and lessons. In upcoming new versions, we might see more new features and improvements.

You can get more free Flutter tutorials you can follow these courses:

#dart #developers #flutter #app developed #dart devtools in visual studio code #firebase local emulator suite in flutter #flutter autofill #flutter date picker #flutter desktop linux app build and publish on snapcraft store #flutter pigeon #flutter range slider #flutter slider #flutter time picker #flutter tutorial #flutter widget #google flutter #linux #navoki #pubspec format #setup flutter desktop on windows

Idrish Dhankot

Idrish Dhankot

1622532470

Hire Dedicated Flutter App Developer USA| Flutter App Developers

Hire Flutter App Developers: WebClues Infotech is a Flutter App Development company. Our Flutter mobile app development team can create cross-platform apps for different industry verticals. Our Flutter developers will help you extend your business’s scope by developing enhanced functionality and a feature-rich app. To provide a rich user experience to your users, hire dedicated Flutter app developers from WebClues Infotech today!

#hire flutter app developers #hire dedicated flutter app developer usa #hire flutter app developer usa #hire dedicated flutter app developer #hire flutter developer #flutter app development company

Best Flutter App Development Company

Are you looking for the best flutter app development company? Then AppClues Infotech is the leading flutter app development company in USA offering the best service worldwide. We focused on developing hybrid mobile apps on Android & iOS and assures our end-user about exceptional and functionally-rich mobile apps.

For more info:
Website: https://www.appcluesinfotech.com/
Email: info@appcluesinfotech.com
Call: +1-978-309-9910

#top flutter app development company in usa #best flutter app development service #best flutter app development company #hire flutter app developers #flutter app development company #expert flutter app development company

Best Flutter App Development Company in USA & India

AppClues Infotech is one of the best flutter app development company in USA & India. Our diverse and experienced team of developers can help you sketch the smartest and quickest solution for your mobile app development projects with the most superior technology.

For more info:
Website: https://www.appcluesinfotech.com/
Email: info@appcluesinfotech.com
Call: +1-978-309-9910

#top flutter app development company in usa #best flutter app development service #best flutter app development company #hire flutter app developers #flutter app development company in usa & india #custom flutter app development service

A Lightweight Face Recognition and Facial Attribute Analysis

deepface

Deepface is a lightweight face recognition and facial attribute analysis (age, gender, emotion and race) framework for python. It is a hybrid face recognition framework wrapping state-of-the-art models: VGG-Face, Google FaceNet, OpenFace, Facebook DeepFace, DeepID, ArcFace and Dlib.

Experiments show that human beings have 97.53% accuracy on facial recognition tasks whereas those models already reached and passed that accuracy level.

Installation

The easiest way to install deepface is to download it from PyPI. It's going to install the library itself and its prerequisites as well. The library is mainly based on TensorFlow and Keras.

pip install deepface

Then you will be able to import the library and use its functionalities.

from deepface import DeepFace

Facial Recognition - Demo

A modern face recognition pipeline consists of 5 common stages: detect, align, normalize, represent and verify. While Deepface handles all these common stages in the background, you don’t need to acquire in-depth knowledge about all the processes behind it. You can just call its verification, find or analysis function with a single line of code.

Face Verification - Demo

This function verifies face pairs as same person or different persons. It expects exact image paths as inputs. Passing numpy or based64 encoded images is also welcome. Then, it is going to return a dictionary and you should check just its verified key.

result = DeepFace.verify(img1_path = "img1.jpg", img2_path = "img2.jpg")

Face recognition - Demo

Face recognition requires applying face verification many times. Herein, deepface has an out-of-the-box find function to handle this action. It's going to look for the identity of input image in the database path and it will return pandas data frame as output.

df = DeepFace.find(img_path = "img1.jpg", db_path = "C:/workspace/my_db")

Face recognition models - Demo

Deepface is a hybrid face recognition package. It currently wraps many state-of-the-art face recognition models: VGG-Face , Google FaceNet, OpenFace, Facebook DeepFace, DeepID, ArcFace and Dlib. The default configuration uses VGG-Face model.

models = ["VGG-Face", "Facenet", "Facenet512", "OpenFace", "DeepFace", "DeepID", "ArcFace", "Dlib"]

#face verification
result = DeepFace.verify(img1_path = "img1.jpg", img2_path = "img2.jpg", model_name = models[1])

#face recognition
df = DeepFace.find(img_path = "img1.jpg", db_path = "C:/workspace/my_db", model_name = models[1])

FaceNet, VGG-Face, ArcFace and Dlib are overperforming ones based on experiments. You can find out the scores of those models below on both Labeled Faces in the Wild and YouTube Faces in the Wild data sets declared by its creators.

ModelLFW ScoreYTF Score
Facenet51299.65%-
ArcFace99.41%-
Dlib99.38 %-
Facenet99.20%-
VGG-Face98.78%97.40%
Human-beings97.53%-
OpenFace93.80%-
DeepID-97.05%

Similarity

Face recognition models are regular convolutional neural networks and they are responsible to represent faces as vectors. We expect that a face pair of same person should be more similar than a face pair of different persons.

Similarity could be calculated by different metrics such as Cosine Similarity, Euclidean Distance and L2 form. The default configuration uses cosine similarity.

metrics = ["cosine", "euclidean", "euclidean_l2"]

#face verification
result = DeepFace.verify(img1_path = "img1.jpg", img2_path = "img2.jpg", distance_metric = metrics[1])

#face recognition
df = DeepFace.find(img_path = "img1.jpg", db_path = "C:/workspace/my_db", distance_metric = metrics[1])

Euclidean L2 form seems to be more stable than cosine and regular Euclidean distance based on experiments.

Facial Attribute Analysis - Demo

Deepface also comes with a strong facial attribute analysis module including age, gender, facial expression (including angry, fear, neutral, sad, disgust, happy and surprise) and race (including asian, white, middle eastern, indian, latino and black) predictions.

obj = DeepFace.analyze(img_path = "img4.jpg", actions = ['age', 'gender', 'race', 'emotion'])

Age model got ± 4.65 MAE; gender model got 97.44% accuracy, 96.29% precision and 95.05% recall as mentioned in its tutorial.

Streaming and Real Time Analysis - Demo

You can run deepface for real time videos as well. Stream function will access your webcam and apply both face recognition and facial attribute analysis. The function starts to analyze a frame if it can focus a face sequantially 5 frames. Then, it shows results 5 seconds.

DeepFace.stream(db_path = "C:/User/Sefik/Desktop/database")

Even though face recognition is based on one-shot learning, you can use multiple face pictures of a person as well. You should rearrange your directory structure as illustrated below.

user
├── database
│   ├── Alice
│   │   ├── Alice1.jpg
│   │   ├── Alice2.jpg
│   ├── Bob
│   │   ├── Bob.jpg

Face Detectors - Demo

Face detection and alignment are important early stages of a modern face recognition pipeline. Experiments show that just alignment increases the face recognition accuracy almost 1%. OpenCV, SSD, Dlib, MTCNN and RetinaFace detectors are wrapped in deepface.

All deepface functions accept an optional detector backend input argument. You can switch among those detectors with this argument. OpenCV is the default detector.

backends = ['opencv', 'ssd', 'dlib', 'mtcnn', 'retinaface']

#face verification
obj = DeepFace.verify(img1_path = "img1.jpg", img2_path = "img2.jpg", detector_backend = backends[4])

#face recognition
df = DeepFace.find(img_path = "img.jpg", db_path = "my_db", detector_backend = backends[4])

#facial analysis
demography = DeepFace.analyze(img_path = "img4.jpg", detector_backend = backends[4])

#face detection and alignment
face = DeepFace.detectFace(img_path = "img.jpg", target_size = (224, 224), detector_backend = backends[4])

Face recognition models are actually CNN models and they expect standard sized inputs. So, resizing is required before representation. To avoid deformation, deepface adds black padding pixels according to the target size argument after detection and alignment.

RetinaFace and MTCNN seem to overperform in detection and alignment stages but they are much slower. If the speed of your pipeline is more important, then you should use opencv or ssd. On the other hand, if you consider the accuracy, then you should use retinaface or mtcnn.

The performance of RetinaFace is very satisfactory even in the crowd as seen in the following illustration. Besides, it comes with an incredible facial landmark detection performance. Highlighted red points show some facial landmarks such as eyes, nose and mouth. That's why, alignment score of RetinaFace is high as well.

You can find out more about RetinaFace on this repo.

API - Demo

Deepface serves an API as well. You can clone /api/api.py and pass it to python command as an argument. This will get a rest service up. In this way, you can call deepface from an external system such as mobile app or web.

python api.py

Face recognition, facial attribute analysis and vector representation functions are covered in the API. You are expected to call these functions as http post methods. Service endpoints will be http://127.0.0.1:5000/verify for face recognition, http://127.0.0.1:5000/analyze for facial attribute analysis, and http://127.0.0.1:5000/represent for vector representation. You should pass input images as base64 encoded string in this case. Here, you can find a postman project.

Tech Stack - Vlog, Tutorial

Face recognition models represent facial images as vector embeddings. The idea behind facial recognition is that vectors should be more similar for same person than different persons. The question is that where and how to store facial embeddings in a large scale system. Herein, deepface offers a represention function to find vector embeddings from facial images.

embedding = DeepFace.represent(img_path = "img.jpg", model_name = 'Facenet')

Tech stack is vast to store vector embeddings. To determine the right tool, you should consider your task such as face verification or face recognition, priority such as speed or confidence, and also data size.

Contribution

Pull requests are welcome. You should run the unit tests locally by running test/unit_tests.py. Please share the unit test result logs in the PR. Deepface is currently compatible with TF 1 and 2 versions. Change requests should satisfy those requirements both.

Support

There are many ways to support a project - starring⭐️ the GitHub repo is just one 🙏

You can also support this work on Patreon

 

Citation

Please cite deepface in your publications if it helps your research. Here are its BibTeX entries:

@inproceedings{serengil2020lightface,
  title        = {LightFace: A Hybrid Deep Face Recognition Framework},
  author       = {Serengil, Sefik Ilkin and Ozpinar, Alper},
  booktitle    = {2020 Innovations in Intelligent Systems and Applications Conference (ASYU)},
  pages        = {23-27},
  year         = {2020},
  doi          = {10.1109/ASYU50717.2020.9259802},
  url          = {https://doi.org/10.1109/ASYU50717.2020.9259802},
  organization = {IEEE}
}
@inproceedings{serengil2021lightface,
  title        = {HyperExtended LightFace: A Facial Attribute Analysis Framework},
  author       = {Serengil, Sefik Ilkin and Ozpinar, Alper},
  booktitle    = {2021 International Conference on Engineering and Emerging Technologies (ICEET)},
  pages        = {1-4},
  year         = {2021},
  doi          = {10.1109/ICEET53442.2021.9659697},
  url.         = {https://doi.org/10.1109/ICEET53442.2021.9659697},
  organization = {IEEE}
}

Also, if you use deepface in your GitHub projects, please add deepface in the requirements.txt.

Author: Serengil
Source Code: https://github.com/serengil/deepface 
License: MIT License

#python #machine-learning