Capstone Research Project: Real Time Mask Control Identification Model for Government Control Enforcement

The required is to write a final report that consist of 15-20 pages in length; single-line spacing; 12 font size; Times New Roman.

The topic is: Real Time Mask Control Identification Model for Government Control Enforcement

Must include:

Abstract (Executive Summary) (1-1.5 pages)

Introduction (1-2 pages)

Review (2-3 pages)

Design Requirements/Details of Project (4-6 pages)

Feasibility Discussion (2-3 pages)

Final Implementation (3-5 pages)

Results (2-3 pages)

Conclusions (1-2 pages)

References

(Look at Project Outline. doc for more details)

Before any thing you need to check:

Project Outline.doc to know what is needed for this work

Research Proposal.doc to know the proposal that has been given for this project and topic question:

Real Time Mask Control Identification Model for Government Control Enforcement

Progress report to understand an update that has been done

Mid Term Presentation to know the mid-way progress done

This project is based on: Balaji Srinivasan

Video break down so that you are able to talk about the practical side of things in the paper (Must be included)

Introduction and Demo: (0:00)

Install Dependencies: (1:18)

Dataset: (2:10)

Data Preprocessing: (2:58)

Training: (9:03)

Run and View Accuracy: (17:09)

Use model in real time Camera: (18:20)

Final Result: (25:30)

Also check the resource: Face tracking using a region-based mean-shift algorithm with adaptive object and background models .pdf for understanding of how things work

I took it as is and now working on enhancing the bias it has over people of the color, it looks like it’s only helping accurately people from East Asia, so we have collected data to not make racist and has an accurate model with people from Africa, India, and Middle East. This has been done through the collection of 6000 pictures to train the DNN machine learning model using a coding library called CAFFE. The dataset is consisting of 2 folders with_mask & without_mask that has the pictures to train the models here is the plot result of the loss:

Here is a way to read it: https://stackoverflow.com/questions/34518656/how-t…

Also, we added audio to the application, the audio is just a sound indicator for alert of change of status and added a third option (Wrong Wear) in orange (check Mid Term presentation for concept) this take into consideration the confidence level of wearing the mask – confidence level of not wearing the mask and reflect a wrong wear status.

Another useful resource found and used:

https://www.youtube.com/watch?v=h6Cy3JK-z6Y

https://www.youtube.com/watch?v=z0aOffHrTac

https://www.google.com/search?safe=strict&biw=1876&bih=940&sxsrf=ALeKk03dz3Y5IlIBugPAHMOWRpEt9HhDbQ%3A1614068587765&ei=a7s0YN-oLt6i1fAP5de7mAk&q=cv2.rectangle+shapes&oq=cv2.rectangle+shapes&gs_lcp=Cgdnd3Mtd2l6EAMyCAghEBYQHRAeOgcIIxCwAxAnOgcIABBHELADOgQIIxAnOgUIABCRAjoHCAAQhwIQFDoCCAA6BggAEBYQHjoHCCEQChCgAVCHnwFY1qcBYPyoAWgBcAJ4AIAB0gKIAZIQkgEFMi00LjOYAQCgAQGqAQdnd3Mtd2l6yAEJwAEB&sclient=gws-wiz&ved=0ahUKEwifisSGyv_uAhVeURUIHeXrDpM4HhDh1QMIDQ&uact=5

https://laptrinhx.com/quick-overview-what-is-ai-artificial-intelligence-ml-machine-learning-and-dl-deep-learning-2305946423/

https://www.pyimagesearch.com/2017/11/06/deep-learning-opencvs-blobfromimage-works/

https://ai.plainenglish.io/blood-face-detector-in-python-part-1-machine-learning-and-deep-learning-classification-project-74aba7067e50

Get more resources as needed but include and cite all what you write from or about

*Do not accept or bid if you do not have the needed expertise to write about this topic, all the resources are available but no extra time will be given*