Week 4

Hello everyone!

The start of the week, I had to meet with Professor Crandall to help me debug my code. The harris corner detector was not accurate enough to match the right images so we had to ask for help in other ways to address the problem. We had a nice long talk in which he explained what harris corner detector does and why it fails compared to other algorithms out there. I decided to continue searching the computer visions library for anything out there that might lead my on the right path.

Tuesday, we had our lab meeting as usual. However, this one went by pretty quick since nobody had much to update since last week. I took the opportunity to ask around if people knew of better ways to match images but no luck. Nonetheless, I met with Professor Crandall after the meeting to show him how poorly the SIFT detector did. He advised us to continue trying and looking for better ways to improve accuracy.

On Wednesday, Professor Crandall emailed us and recommended us to go to the IARPA talk with Stacey Dixon. In this talk, she explained what IARPA does and the projects it funds. Surprisingly, one of the projects she mentioned was in the works, has a lot to do with our current research project. It made me feel confident that what we are working on will one day make a difference for big companies who need more secure hardware as the grow. I would also like to thank Dr. Siek for giving us the opportunity to have professional pictures taken for us, I have been meaning to get some and you made it easier for me.

Thursday, I arranged another meeting with Professor Crandall to show him the new algorithm we found that has been the most accurate one to date. It is called Flann SIFT and it has so far accurately been able to match the ICs from an image with multiple ones. If the image did not match, it would tell you otherwise.
download_6
Screen_Shot_2018_06_15_at_11_19_15_AM

I decided to come home this Friday for the weekend for Father’s Day. However, the next step to continue to improve the accuracy of this program is to create multiple data sets. These data sets will varies in size in order to create difficult tasks for the program to match. This method would allow us to determine the accuracy and how effective this program may work depending on the circumstance.

I hope you enjoy your weekend.

Happy Father’s Day!

G