This week I have been designing the user interface for our system. The challenge has been creating an interface that doesn’t need direct interaction. I have been drafting interfaces with wireframe. This week we are looking forward to completing a design presentation, planning integration, and finishing our design.
Aneek’s Status Update for 4/4
- This week I was focused on getting finger detection in OpenCV working. The issue of various phantom ‘fingers’ being detected in the background was mitigated by using a plain, consistent background for the images (I tested on a white table and a black blanket). While that demonstrated that the approach I was using was working, the background will not be so consistent when puzzle pieces are laid out on the surface below the hand, so my next steps were to test out various methods of improving the detection on more complex backgrounds. The approach that seems the most promising is using a color mask to isolate the hand before running the edge detection to determine the fingertip. However, the color of the hands surface is drastically different depending on skin tone and lighting conditions, so my next steps to improve this are to continue research on alternative methods and/or ways to broaden the color mask to function across a broad spectrum of hands.
A0 Team Status Update for 4/4
Overall our team has been working on making our project ready for the midsemester demo on Monday. We are hoping to have all of our individual pieces of our project put together enough so that we can focus a majority of our efforts on piecing together our final project before the time comes to complete our additional trade studies.
Andrew’s Status Update for 4/4
This week I solved a major problem that was blocking me for a while. I am now able to do a very major part of my project that I was having a lot of trouble with for the last few weeks. I am able to match a piece of an image within the larger image, without using a very naiive approach of doing a simple subtraction of the image block from the overall image.
This is one of 6 methods. 5 of those 6 methods that use the template image among some that convolve the image and find the features and match them among the original image. I am still working on ways of making this as robust to rotations as possible. I need to do more testing to ensure that this is possible and I can meld this with previous research. This is my largest contribution for this week, the rest has been touching up previous pieces of code and working on the overall pieces of the pipeline.