Face Mask Detector 😷

by Live Camera

Detecting masked or unmasked faces by live camera with percentange of mask occupation

About Project:

This an Artificial Intelligence based project in which we can detect person's faces by live camera and system can predict that person weared a mask or not. A programming language that I used in this project is Python. Where I build a predective model with the help of Neural Networks (Deep Learning). Dataset contains two classes that means two type of images such as With Mask and Without Mask

Overview:

Importing machine learning libraries - Tensorflow, Keras and Sklearn
Loading dataset and divding into two categories - With Mask and Without Mask
Converting Categories into numbers by LabelBinarizer
Splitting data into train, test and split
Data Augmentation by ImageDataGenerator
Creating neural network with MobileNetV2, and connected entire layers
Compiling the model Adam optimizer and binray_cross entropy loss
Using callbacks while model training to avoid overfitting
Evaluating the model by classification report and confusion matrix
Visualized model accuracy and val_loss
Serializing the model and implementing into python code for live camera
Using OpenCv and imutils for live implementation

Live Demo:

https://twitter.com/KuchBhiKaran/status/1482999558536036352?t=RgL5Rt0QA9uZgXHCNAHKuQ&s=19

Face Mask Detector by live camera using tensorflow-keras, openCV and Python

Related tags

Overview

Face Mask Detector 😷

About Project:

Overview:

Live Demo:

Owner

Karan Shingde

PyTorch implementation of the paper:A Convolutional Approach to Melody Line Identification in Symbolic Scores.

This is the official pytorch implementation of the BoxEL for the description logic EL++

DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification

A lightweight library designed to accelerate the process of training PyTorch models by providing a minimal

Mosaic of Object-centric Images as Scene-centric Images (MosaicOS) for long-tailed object detection and instance segmentation.

ANEA: Automated (Named) Entity Annotation for German Domain-Specific Texts

Official PyTorch code for WACV 2022 paper "CFLOW-AD: Real-Time Unsupervised Anomaly Detection with Localization via Conditional Normalizing Flows"

Propose a principled and practically effective framework for unsupervised accuracy estimation and error detection tasks with theoretical analysis and state-of-the-art performance.

Code release for our paper, "SimNet: Enabling Robust Unknown Object Manipulation from Pure Synthetic Data via Stereo"

Source code for the GPT-2 story generation models in the EMNLP 2020 paper "STORIUM: A Dataset and Evaluation Platform for Human-in-the-Loop Story Generation"

Simulation environments for the CrazyFlie quadrotor: Used for Reinforcement Learning and Sim-to-Real Transfer

FMA: A Dataset For Music Analysis

Scrutinizing XAI with linear ground-truth data

In this project, we create and implement a deep learning library from scratch.

A Shading-Guided Generative Implicit Model for Shape-Accurate 3D-Aware Image Synthesis

A hybrid framework (neural mass model + ML) for SC-to-FC prediction

ANEA: Distant Supervision for Low-Resource Named Entity Recognition

BADet: Boundary-Aware 3D Object Detection from Point Clouds (Pattern Recognition 2022)

Monify: an Expense tracker Program implemented in a Graphical User Interface that allows users to keep track of their expenses

Keras Implementation of The One Hundred Layers Tiramisu: Fully Convolutional DenseNets for Semantic Segmentation by (Simon Jégou, Michal Drozdzal, David Vazquez, Adriana Romero, Yoshua Bengio)