PowerPoint Presentation

Real-Time Face Mask Detection System | Neuromation.

Introduction. Coronavirus 2019 has had a big global impact. Wearing masks in public areas is an excellent approach for preventing illness. The main goal of the project is to develop a system to detect whether a person is wearing a mask or not, this can be used at entrances of colleges, airports, hospitals, and offices where chances of spread of COVID-19 through contagion are relatively higher..

MOTIVATION As covid-19 spread throught out the world the need for people to wear masks increased. It became necessary for everyone to wear masks. Wearing face masks is recommended as part of personal protective equipment and as a public health measure to prevent the spread of coronavirus disease 2019 (COVID-19) pandemic. PROBLEM STATEMENT The COVID-19 epidemic is still going strong. Analyzing the current scenario, government and private organizations want to make sure that everyone working or visiting a public or private place is wearing masks throughout the day..

AREA OF APPLICATION It can be used at entrances of colleges, airports, hospitals, and offices where chances of spread of COVID-19 through contagion are relatively higher. DATASET AND INPUT FORMAT The dataset we have used has 5000 images and these images have 3 channels Red Green and Blue) . To augment the dataset we have used certain functions like zoom and rotation to generate images from the existing dataset..

4-1. 4-2. 4-3. 4-4. SWOT ANALYSIS. Need Of The Hour Simple and Effective.

Objective. The main objective of “Face mask recognition” project is to provide an effective technology to detect if a person is wearing a mask or not..

Methodology. Technical Concepts (Algorithms) used.

They have three main types of layers, which are Convolutional layer Pooling layer Fully-connected (FC) layer The convolutional layer is the first layer of a convolutional network. While convolutional layers can be followed by additional convolutional layers or pooling layers, the fully-connected layer is the final layer. With each layer, the CNN increases in its complexity, identifying greater portions of the image..

Design and Implementation Constraints. Design Diagram – Flow Chart.

.1 (arr.-..l') ('Xto•ri:) V1iJiiiJ. l:sst). Output.

File Edit View Insert {x) Face-mask-detection training.ipynb co val_loss: e.142e - val_loss: 0.1288 - val_loss: - Runtime Tools Help Last saved at 17:16 29/29 o Epoch 29/29 Epoch 29/29 - Epoch 29/29 Epoch 29/29 [z Epoch 29/29 Epoch 29/29 Epoch 29/29 - Epoch 29/29 Epoch 29/29 Epoch 29/29 Epoch 29/29 Epoch 29/29 - Epoch 29/29 Epoch 29/29 Epoch 29/29 Epoch 29/29 Epoch 29/29 Epoch 29/29 Epoch 29/29 Epoch 29/29 Epoch 29/29 val eeøee: 41/50 val eeø41 : val eeø42 : eeø43: val_accuracy eøø44 : eeø4S : val eeø47: val eøø49 : eeese : _accuracy _accuracy 3 curacy val_accuracy val_accuracy _accuracy _ac curacy val_accuracy val_accuracy val_accuracy e.1199 - accuracy: e.9542 did rot improve fron e.9é1S4 - S7s 2s/step - loss: e.1199 - accuracy: e.ss-42 - val_loss: 3.1272 - ] - ETA: es - loss: e.1215 - accuracy: 0.9564 improved from e.9é1S4 to e.9éS2é, saving "del to did did did did did not not not not - s7s 2s/step . loss: - accuracy: e.ss€4 - - ETA: es - loss: e.1261 - accuracy: e.9523 not improve 0.96526 - S7s 2s/step - loss: e. 1261 - accuracy: e. 9523 - ] - ETA: os - loss: e.12€e - accuracy: e.ss€4 improve frcr e. 9éS2é ] - S7s 2s/step - loss: e. 12" - accuracy: e. 9364 ] - ETA: es - loss: e.1316 - accuracy: e.SSIS inprove fro" e. 96526 ] - s7s 25/step - loss: 0.1316 - accuracy: e.ssls - ETA: - loss: e.1615 - accuracy: 0.9419 inprove fron e.9éS2é - sss 25/step - loss: e.léls - accuracy: e.9419 - - ETA: os - loss: e.1279 - accuracy: esse improve fron e.9€s2é - 2s/step - loss: e.1279 - accuracy: e.ssze - - ETA: es - loss: e.1328 - accuracy: e.ss48 val_loss: - val loss - val loss: e. 2096 val_loss. e. 1234 - : 0.1179 • 0.1231 - val_accuracy: e. 9516 val_accuracy val_accuracy: - val_accuracy - val_accuracy val_accuracy val_accuracy : e.9653 : e.gssy : e.nø€ : e.ssø4 : e.9578 improved from e.9SS2é to e.9€€se, saving •del to did did did not not not - 2s/step - loss: e. 1328 - accuracy: - - ETA: es - loss: e.1E9 - accuracy: e.ssn improve frcr e. 96éSe ] - s7s 2s/step - loss: 0.1139 - accuracy: e.9592 ] - ETA: es - loss: e.1218 - accuracy: e.ssu inprove fro" e. 96éSe ] - sss 25/step - loss: 0.1218 - accuracy: e.ssu - ETA: - loss: e.1127 - accuracy: e.9€es inprove fron e. 96éSe ] - sss 2s/step - loss: 0.1127 - accuracy: e.sses - - val loss: e. 127 - val loss• val_loss. . 0.1189 - • e.mse - val_accuracy: e.96éS - val_accuracy val_accuracy val_accuracy : e."91 : e.9€ey : e."91.

Assumptions 1.) The Database – The database is evenly spread with optimal variance, low bias and minimal noise. Dependencies 1.) Hardware – We will require hardware suitable for the computation required for the training and testing of the model.

Assumptions 1.) The Database – The database is evenly spread with optimal variance, low bias and minimal noise. Dependencies 1.) Hardware – We will require hardware suitable for the computation required for the training and testing of the model.

Reference. Gupta, P., Saxena , N., Sharma, M., & Tripathi , J. (2018). Deep neural network for human face recognition. International Journal of Engineering and Manufacturing (IJEM) , 8 (1), 63-71. Bhamare , D., & Suryawanshi , P. (2018). Review on reliable pattern recognition with machine learning techniques. Fuzzy Information and Engineering , 10 (3), 362-377. Sethi , S., Kathuria , M., & Kaushik , T. (2021). Face mask detection using deep learning: An approach to reduce risk of Coronavirus spread. Journal of biomedical informatics , 120 , 103848. I. B. Venkateswarlu , J. Kakarla and S. Prakash , "Facemask detection using MobileNet and Global PoolingBlock ," 4 2020 IEEE 4th Conference on Information & Communication Technology (CICT), 2020, pp. 1-5, doi : 10.1109/CICT51604.2020.9312083..

Thank You. A picture containing text, clipart Description automatically generated.