Posted on

Team Status Report for 4/30

This week, our team presented our final presentation in class. Following a good presentation, we continued to focus our efforts on bringing together the various parts of our project. After struggling to integrate certain pieces of the mirror together, we changed focus, and decided to create a server that allows us to access parts of our project through the internet. This allows both the mirror and the application we are creating to access the server and relay information accordingly. We also worked on integrating the mirror UI to be able to activate the mirror and connect to the other parts of the project.

As we are coming closer to the end of the project, we find ourselves more in need of connecting the final pieces of the project. In the next week we will focus on getting our mirror fully prepared and functional, and also finishing our final poster and final report. Overall we are on track as we enter the final stretch to get the various parts of the mirror together and test them for success.

Posted on

Ramzi’s Status Report for 4/30

This week I worked on connecting the outfit recommendation algorithms with our Google Spreadsheets API that we are using as a database for our user’s wardrobe. This allows the our application and device to connect to the same server for our wardrobe.  I also tested the full outfit recommendation time, and found that we were way over the mark of where we want to be in recommendation time. I think otherwise we are on schedule, and this next week we will be focusing on connecting all the parts together and wrapping everything up in preparation for our final report and demo.

Posted on

Ramzi’s Status Report for 4/23

This week, I improved the weather tags recommendation algorithm, and put together the outfit recommendation algorithm. I altered the weather algorithm and its tags to accommodate a wider variety of clothing, mainly formal clothing, such as suits and dresses, and synchronized it to the format of the database and the user’s input form. We now have an outfit recommendation algorithm that takes in various outputs, and provides the user with the 5 best options for them to pick and choose from based on a weighted point system. It also has an internal system for analyzing what accessories would be appropriate depending on weather conditions.

As we are coming closer to the final presentation and demo, I think we are on track with what we need to be getting done. Next week I will be focusing on putting together our final report, and integrating what remaining parts of our prototype are still waiting to be put together.

Posted on

Ramzi’s Status Report for 4/16

This week I put together a recommendation system to recommend new outfits for the user depending on the color of what they are wearing, and the current weather conditions based in python. Using the webcolors python module, I was able to categorize the colors and come up with the best recommended colors to match based on a given rgb value.

Example of code and output of color/weather recommendations

I think we are catching back up to our planned schedule, and should be able to put together the modules we have each individually worked on in the near future.

Moving forward, I will be continuing to improve these algorithms, and integrating them together to create a system that can recommend an entire outfit for the user. I will also be assisting in integrating these algorithms into the rest of the project.

Posted on

Ramzi’s Status Report for 4/20

I was ill for most of the week, and was unable to put aside much time to work on the project. As such, most of my time was spent ruminating how to put together the remaining portions of the project. Since we are a little behind, I came up with a few ideas on how to expedite and implement the database for the user’s wardrobe, and connect it to our torso and color detection programs, which I intend to discuss with my teammates in the upcoming week. Additionally, I have been preparing for the interim demo where I intend to present the frame that I designed, and put together with my teammates.

Posted on

Ramzi’s Status Report for 4/2

Unfortunately, I was preoccupied with illnesses throughout the week which greatly hampered my progress. I brought forth concerns with my teammates about support for the bluetooth components of the project, and we ultimately decided to switch over to utilizing a wifi system in order to transfer data to and from the mirror. This is bound to create a multitude of security concerns, however we think it should be fine as long as we will address aforementioned security concerns in the future.

Posted on

Team Status Report for 4/2

Early on in the week, we finished creating the frame for the mirror, and attaching the mirror itself to its frame. Jeremy and Wonho decided to use tape to hold the four mirrors of the frame in order to compensate for the flexibility of the mirror, which is made of acrylic. We were able to see the background through the mirror, which was not our objective, so we also used a cardboard box as a back to the frame to block any excess light from coming through, and the result is that only the monitor is visible through the mirror.

Jeremy and Wonho Posing with the Mirror

As such, we have moved on to the most significant challenge to the project, our software components. To be specific, we mostly worked on the Openpose troubles and getting the Nvidia Xavier and trtpose to work as we want it too. Unfortunately due to some team members being preoccupied, we were not able to approach the other software components this week. We switched from utilizing bluetooth to using a wifi connection for our application and mirror to communicate, which may provide a few security concerns to address, but will ultimately be easier to implement due to the additional support provided.

We seem to be a little behind schedule, but in the coming weeks we hope to make more progress on the software components, such as trtpose and the application, in order to be able to present them at the interim demo.

Posted on

Ramzi’s Status report for 3/26

This week I reviewed the system we are using for our application, and tried to learn more of its functions so that we could integrate the application thoroughly. We want to find a way to upload images through the app to our mirror. We also spent a large amount of time working on our physical mirror, as we have been trying to get access to a woodshop and create a frame that would work for a while. I created a diagram that thoroughly detailed how we would design the physical dimensions of our mirror.

Myflection_Mirror_Frame_Dimensions

We went to home depot, and purchased two 2″x10″x8′ pieces of wood, before heading over to the woodshop at techspark to have the pieces properly cut into what we needed. We screwed together the pieces together, and managed to create the completed frame below:

For next week, we will be resuming working on the software components of our project, as we try to bring together the application and the video analysis software to create a coherent system.

Posted on

Ramzi’s Status Report 3/19

This week I worked on getting down the fundamentals of our coding language and the systems that we are using to set up our database and our analysis systems. With assistance from Yun and Jeremy I managed to figure out the basic setup and access our git deposit to begin working on our application framework, which I have included a code snippet from in figure 1.

Figure 1: small code snippet

We have begun to make progress and get ourselves back on track to our schedule. We have been attempting to contact TechSpark for the sake of using their woodshop, but are facing delays and communication issues. We have set our short term goals of getting the information we want from our Arducam OpenPose Live Feed torso detection, and our ColorThief color detection, while setting up the necessary framework for our application to interact with the mirror and the user.

Posted on

Ramzi’s Status Report for 2/26

This week, my time was mainly spent on designing the slides for our design presentation, as well as preparing our design report. As of now we have a system figured out on how we are going to complete our design report as a team, and we gave our design presentation earlier this week. We requested space in TechSpark to put together and test our smart mirror, and our group ordered the parts, so we are waiting on the parts to arrive before we begin putting our project together. We are a little behind our planned schedule, but hopefully we will be able to catch up when the parts deliver. For the next week we are focusing our efforts on the design report until our parts arrive, then we may be able to begin setting up the hardware and software components of our project.