Smart SOPs serveillance system using deep neural network
In this chapter, we have proposed a face mask detection model namely Smart SOP's Surveillance System Using Deep Neural Networks, which can contribute to public healthcare. The architecture is based on the two main phases which is training face mask detector and implementing the face mask detector. I
2025-06-28 16:35:46 - Adil Khan
Smart SOPs serveillance system using deep neural network
Project Area of Specialization Artificial IntelligenceProject SummaryIn this chapter, we have proposed a face mask detection model namely Smart SOP's Surveillance System Using Deep Neural Networks, which can contribute to public healthcare. The architecture is based on the two main phases which is training face mask detector and implementing the face mask detector. In order to extract large dataset, we used transfer learning technique to trained the model. On the given dataset the system model will monitor the public places and identify if the person is wearing a mask or not. If someone is captured not wearing mask it will automatically generates warning alerts with image of the person to take necessary actions in order to maintain the SOP’s based environment and to prevent the spread of the corona virus. On training the model, we got an accuracy of 90 %. hence can be used in crowded places like railway stations, bus stops, markets, streets, mall entrances, schools, colleges, etc. By monitoring the placement of the face mask on the face, we can make sure that every individual wears it the right way and helps to curb the scope of the virus and pollution.
Project ObjectivesSince the COVID-19 has become the curial health disease and it is transmitting from person to person rapidly, our idea is based on the Aim that we introduced a system model which is trained in a way that it helps the society in preventing the transmission of virus in public places as it is trained in a way that it detects the faces that are not wearing masks in public places by real time monitoring of the people and when it detects the face without mask it will automatically click the picture of the person and send notification to the system and provide the necessary dataset to take actions in order to follow the SOP’s to prevent the further spread of the virus and pollution. Our objective is to use computer vision techniques like image processing, object detection, transfer learning, deep learning to trained the model so that it saves time and detect unmasked faces and also measure temperature of the body automatically by monitoring them . The monitoring is based on the dataset which we will used to trained the model. Our aim is to prevent the spread of the COVID-19 and pollution by using detection of temperature and unmasked faces by image processing assuring that people wear masks in public places to prevent the spread of the COVID-19.
Project Implementation MethodWe have divided the methodology into different phases:
Phase-1
Data Collection:
In phase 1 we will collect the dataset that will help us in training the model that how the system detects if the person is wearing mask and following SOP’s or not. For this purpose, we will take different pictures of people wearing masks and also not wearing masks in order to trained the model on what measures the system will identify that who is wearing masks or who is not wearing mask in public places. Some examples are shown in figure below with masks, without masks, hand masks, with or without masks in one frame and also confusing images without masks.
Phase-II
Model Training:
Due to limited size of dataset of face mask it is difficult for learning algorithms to learn better features. Our proposed system uses transfer learning techniques to trained the system model that on what measures will it detect the person is wearing mask or not. The dataset is loaded into project directory and algorithm is trained on the basis of given images of people with masks, without masks, confusing images without masks etc. All the images form phase 1 creates a baseline for our project it will help the algorithms to learns objects which shows that transfer learning can increase the face detection performance by 3 to 4% and also enhance the accuracy level.
Phase-III
Model Implementation
After training the model we have to implement the algorithm-based system with the camera to automatically track the public areas to prevent the spread of COVID-19. The camera will help the trained model to detect on real time in public places if a person is not wearing masks. The system will also help in maintaining the hygienic environment in public places. Also, it improves the accuracy level by 90%.
Phase-1V
Model Testing:
Once the model is completely trained and is given all the dataset to measures the detection of people not wearing mask, we check the accuracy level of the model based on the dataset given to it by showing the bounding box with green color. If the person in the bounding box is not wearing a mask or the mask is not visible to the camera it will change it color into red and capture its image and will generates a warning and send alert to monitoring authorities with face image. The system accuracy level is approximately 90%.
Benefits of the Project•The proposed system can detect the temperature and unmasked faces by real time monitoring of the people using image processing and data entry.
•The system is user friendly, we can get the data of captured image easily.
•The system monitors the people in the boundary box and if it detects a person having temperature or without mask it will change the color of boundary box into red.
•The system will notify the authorities if it detects temperature or unmasked faces by capturing their pictures automatically.
•Data entry and image processing of large dataset can improve the accuracy level of the system.
•This system with more modification will help the society in future.
Technical Details of Final Deliverable- The proposed system can detect the temperature and unmasked faces by real time monitoring of the people using image processing and data entry.?
- The system is user friendly, we can get the data of captured image easily.?
- The system monitors the people in the boundary box and if it detects a person having temperature or without mask it will change the color of boundary box into red. ?
- The system will notify the authorities if it detects temperature or unmasked faces by capturing their pictures automaticallys.?
- Data entry and image processing of large dataset can improve the accuracy level of the system.?
- This system with more modification will help the society in future.
- system moduling with deep neural network
| Item Name | Type | No. of Units | Per Unit Cost (in Rs) | Total (in Rs) |
|---|---|---|---|---|
| Total in (Rs) | 62380 | |||
| mlx 90614 ir temperature sensor | Equipment | 1 | 3880 | 3880 |
| arduino mega | Equipment | 1 | 1400 | 1400 |
| industrial grade alarming module | Equipment | 1 | 1500 | 1500 |
| raspberry pi 8gb | Equipment | 1 | 14000 | 14000 |
| 5v 3amp supply | Equipment | 1 | 800 | 800 |
| communication cable | Equipment | 1 | 350 | 350 |
| sd card class 10.32gb | Equipment | 1 | 1300 | 1300 |
| camera logitec c3 series | Equipment | 1 | 3800 | 3800 |
| 12v supply | Equipment | 1 | 400 | 400 |
| cmt fatek cloud communication module with ethernet port | Equipment | 1 | 25000 | 25000 |
| 3d printed casing for temperature sensing device | Equipment | 1 | 3000 | 3000 |
| Ttl to usb converter | Equipment | 3 | 650 | 1950 |
| Documentation | Miscellaneous | 500 | 10 | 5000 |