- This week, I focused on getting the web app to communicate with the project’s other components and conducting tests of the facial recognition system to see if it meets our design requirements. Once I was able to get facial recognition to work using the web app, I added the code that would allow it to communicate with the rack and complete the process. There were some issues with the wireless transceivers that postponed testing the web app, but it will happen next week. On top of testing the design requirements, I tested both the SVM classifier implementation we had previously with the current Euclidean Distance implementation to see what performed better. Testing shows that the SVM classifier produces a higher accuracy, so I want to put it back in with the main recognition implementation.
- With the issues around the transceivers, Carnival, and increased coursework in other classes I have fallen behind, but plan to use the upcoming week to get fully back on track.
- Next week I want to make sure the web app works well with the rest of the project and iron out any bugs that may come about from that, and fully complete the testing for the facial recognition system. I also want to reintroduce the SVM classifier back into the recognition system, which produces higher accuracies as seen from testing.
- My part of the project involved facial recognition, so I had to familiarize myself with not only OpenCV but with computer vision as a whole. These topics and technologies were completely new to me coming into this project so I had to learn them to implement this part of the project. To learn these new tools and technologies, I mostly read articles and watched videos that described what was going on under the hood of all of the OpenCV methods I used, and I looked at simple examples of what I wanted to do with the recognition system and used that knowledge to help implement the facial recognition system.
Carnegie Mellon ECE Capstone, Spring 2024 | Doreen Valmyr, Ryan Lin, Surafel Tsadik