This week Devon and Christina came over multiple times this week to work on finalizing the mirror! We got the mirror screen calibration pretty much done. With the reflection of the mirror it looks like the user is actually trying on the clothes. I also went to tech spark on Monday and got a small .75 inch hole cut on the side of the mirror. This way we can have the camera embedded into the mirror creating a more seamless look. I went home on Thursday so we moved the mirror from my house to Devon’s house. At home, I filled in the poster and I am waiting on some detailed pictures of the mirror and the poster will be ready for the demo. We still have some work left to do like enhancing the user interface so that they could try on multiple clothes at once. However, we made great progress so far!
Team Weekly Status Report for May 8
The team is wrapping up on all the deliverables due this week. Judy is working on the poster. Devon and Christina are working on the video. We’re all collaboratively working on the final report based off the design report. Specific to the actual project, Judy has been working out the kinks in the subprocess calls. Christina is working on image calibration to the model. Devon is working on integrating the warping model.
Christina’s Weekly Status Report for May 8
This week I have been working on wrapping up all of the deliverables. Specifically, Devon and I are working on the video. I am refining the appearance of the current UI and calibrating the size and position of the clothing image to fit best true to life (this is for superimposition). One thing to note is that it is really hard to take good images of our project since it’s reflective, but we’re trying our best to show it. Here are some screenshots from our final video.
Judy’s Weekly Status Report Week of May 1st
This week we worked on preparing our final presentation. I worked on the project management slides as well as taking pictures of our mirror and user interface for the slides. In addition to this, I worked on integrating the UI with the matching algorithm with the script. There are still some issues with the display of the matching. When running the script, the matching tkinter screen doesn’t load. Next week, along with preparing the video and demo, I will be working on getting the tkinter screen to load.
Team Weekly Status Report for May 1
This past week we have still been working on finishing up and polishing our different parts where Judy is working on the UI, Christina is working on the matching algorithm and testing script, and Devon is working on integrating the warping model into our project. We laser cut a hole in the mirror so that we can fit the camera through and now our hardware system is officially done. We also worked on the final presentation slides this week and plan to film parts of the final video soon.
Christina’s Weekly Status Report for May 1
This week I’ve been focusing on writing a testing script so that we can have some quantitative metrics for our final presentation next week. We are testing by running the matching algorithm on different models with the same clothing and manually selecting the superimposed images that look passable. This was a suggestion that Marios gave us during our weekly meeting and we all agreed that it made the most sense for testing usability and precision. Currently I have ran the testing script with one shirt on 2032 test images of models from the warping model. We will select visually passable images and include the results and observations in our final presentation. Note this is only for superimposition, not warping since that has yet to be integrated. I’ve included some example outputs below.
Unpassable example:
Passable examples:
Devon’s Weekly Status Report April 24
This week I continued working on our model using our custom data. I ran into some issues with data resizing so I worked mainly on adjusting the code so that it could work with our custom data. As of now, the output of the model is not completely satisfactory, but I will continue working on it this week. In preparation for the demo, we also mounted the mirror on the TV and tested in person.
Team Weekly Status Report for April 24
Last week, the team worked on preparing for the interim demo. This week, we are primarily working on areas of feedback we got from the demo and improving our existing algorithms. The hardware system is basically completed. We used command strips to attach the mirror to the monitor to make it easy to take off and make adjustments. Currently, the camera is taped to the side of the mirror and the Jetson system is attached in a pocket behind the monitor. The one refinement we want to make is making a better camera attachment by laser cutting a hole on the side of the mirror to fit the lens through. Judy has begun working on the tkinter user interface. Christina created a preliminary matching algorithm and is working on improving it. Devon is working on training a model for image warping which we hope to integrate for the final demo. An image of the hardware system is attached below.
Christina’s Weekly Status Report for April 24
Last week I was preparing for the interim demo by displaying the preliminary matching algorithm through tkinter. This isn’t the final matching algorithm since we hope that the ML model Devon is training and working on integrating will be what will be using for the final matching algorithm. The preliminary algorithm takes in the two key point jsons OpenPose generates of the user and the clothing image. These are normalized as a value of 0 to 1 based on the x, y ratio in comparison to the entire image. The center points are matched and the points are created and the clothing image is rendered on top of the user with PIL to register PNG transparency. I’ve attached a picture of the results below. As you can see, it’s not perfect at all. So this week I’ve been working on finding what’s wrong with the normalization process I go through, since visually comparing the jsons, we’re getting a pretty accurate center point position. I’m still working on this, but I suspect it’s because the ratios are calculated from different sizes of picture. I’m not what the right way to go about correcting this is, but probably doing some more math on normalizing the size ratios.
Judy’s Weekly status report Week of April 24
This week, in class we talked about ethics. It was eye opening hearing other classmates discuss the ethics of the smart mirror. Many of the other students brought up many great questions as to how inclusive the mirror is. It gave us a lot to think about as we continue to build the mirror. In addition to this, I worked on creating the user interface for the mirror this week. I used Pkinter to make a simple UI that allows the user to either upload a shirt to try on, or choose from the existing shirts to try on. We are working on connecting the interface with the rest of the mirror.