Tuesday, October 18, 2016

Research Group Presentation

Yesterday Morgan and I presented the progress we made to the rest of the researchers. The discussions about the project, gave us more insights on the direction we can take later after we complete our initial objectives.

Major points taken:

  • Utilize our classifier in a demo security application (for validation)
  • Record Compare the accuracy between multiple races (have african-american, white, asian, etc participants)
  • Improve our classifier to handle participants with higher levels of melanin. (if time permits)

Our Presentation is Below:

Friday, October 14, 2016

Weekly Research Recap Meeting

October 13, 2016 Meeting Breakdown

In our weekly research meeting we discussed preparing for our large research group presentation on the 17th. Morgan and I will prepare slides introduces ourselves, the project, and provide an overview to other researchers on the progress we have made. 

In addition, we were able to talk to the main lab technician to get a dedicated computer to build our classifiers. We also switched from trying to build a haar-cascade classifier on anti-helixes to helixes. Our next objective is to find 20 positive samples from our database of a wide and narrow helix.

For research purposes we're constraining what we consider the helix to be to just the top portion of the ear. We discussed the possibility of using edge detection to distinguish between wide and narrow helixes, but for the moment we will be using visual approximations.

Friday, October 7, 2016

Face Detection Sample Program

Morgan and I met up this evening to go through a OpenCV face detection sample program. We were able to get things working and learn more about OpenCV and Cascades.

The detection program was implemented in python, and the source code with notes are below:

Program Output:

Thursday, October 6, 2016

Weekly Research Recap Meeting

Today we had our weekly research meeting to go over the progress we made over the last few weeks. Dr. Washington discussed different meeting times, schedules, and we agreed upon having weekend check-ins to ensure that we're staying on track and completing our milestones.

At the moment our main goal is to find image examples of skinny and fat anti-helixes and create Haar Cascade classifiers for skinny anti-helixes. If possible Morgan and I would like to complete these objectives and present our findings during large research meeting on the 17th of October.

Wednesday, October 5, 2016

Research Partner Setup

Today I focused on meeting up with my research partner, Morgan so that she could have the proper environment for our project. The primary task we completed together was installing and configuring a python and OpenCV environment. After getting this set up we went through a sample OpenCV python program to verify everything was working properly. The next steps would be to go through a more involved sample, for the purpose of getting more familiar with the library's methods.