Posted on

Francesca’s Status Report for Oct 25

This week, what I personally have been working on is testing Tesseract. As our goal is to achieve 99% OCR accuracy, we need to heavily test the software first, as part of our risk mitigation strategy.  I researched data bases online to find appropriate (and a lot of) data to test the software on. So far, I’ve been working with FUNSD (Form Understanding in Noisy Scanned Documents) which should be helpful for scanned or printed text, and Tobacco800 which seems to have greater font variance and even handwritten components. So far, I’ve been working on writing the script to run these, and I would guess that I  should be mainly wrapped up with testing Tesseract by the end of the week.

This week,  I also contacted the CMU Director of the Office of Disability Resources, who has given us helpful advice on the feasibility of our design, and we have confirmed that the Western Pennsylvania School for Blind Children is interested in helping us in our testing.

I believe our progress is about on track. We had some delays in ordering due to the AWS outage, but we feel good otherwise, and are ordering ASAP.  This coming week, I will not be attending class on Monday because I will be in Washington, DC attending the American Institute for Medical and Biological Engineering Public Policy Institute, but I’m able to asynchronously work on my Tesseract testing and will coordinate with my group members to make sure we are still making progress.

Posted on

Francesca’s Status Report for Oct 18

This week, I finished my sections for the design report.  With the entire group, we reworked our design components, and were deciding between a one motor and three motor implementation. We decided to focus on one as our actual plan in the design report, and the other would be a backup contingency plan. We decided that it would be easy to pivot between the two implementations so long as we have the components, so we budgeted for several motors in our plan. We’ll be able to quickly reprint small 3D printed parts on campus on demand, so we are not worried about this part. We are a bit behind on ordering parts, as Abby mentioned. The original plan was to submit this to our TA over fall break, but this ended up not happening. We’ll order the parts in class this upcoming week, and we can still test software like Tesseract or CAD designs in the meantime, so I am not too worried about this. This coming week, I hope to help my teammates with the CAD and 3D print, but on my end, I would like to spend my time testing Tesseract so we know that our OCR software is extremely reliable before we start physically building the device in coming weeks. I’m hopeful we can find a way to automate such testing, which was suggested by a TA during our proposal presentation.

Posted on

Francesca Cain’s Status Report for October 4th

This week, I helped Abby to finalize the slides provided for our design presentation, and we thought further about how we are gong to model and implement our final design. In the days leading up to our design presentation, we decided to not go the route of motorizing a pre-fabricated part bought from Amazon. Instead, we will be using a custom built pin-dropping mechanism, using small motors, to emboss the labels. Since a braille character has two columns with three rows, the mechanism will use only three pins with actuators to print labels. Going forward into next week, since our design is now finalized, the real work is able to begin of interacting with Tesseract and checking its reliability, finalizing hardware orders, and making contact with the Office of Disability Resources and the Western PennsylvaniaSchool for Blind Children

Posted on

Francesca Cain’s Status Report for September 27th

This week, I spent much of my time reflecting upon our presentation from last week, and considering the suggestions for improvement provided to our group by our instructor a TA. Notably, we need to spend time creating a mitigation plan, which we didn’t include last week. We had a meeting with our instructor and TA who provided us with helpful feedback in determining our finalized plan for our project prior to our upcoming design presentation.

I researched materials, their sourcing, and their costs for our project, as well as similar products on the market. In terms of a braille label maker, the closest I was able to find is the LoganTech 6Dot Braille Label Maker, which uses a six key input rather than OCR scanning to determine the text.  It is also very expensive (over $1k+) and inaccessible to most average patients. We found it helpful to see it’s embossing mechanism and tape used to print, though, and we are considering buying its refill tape pack for our own project.

I researched types of Raspberry Pis, and the Raspberry Pi AI HAT, which our TA had suggested we may want to use to help with speed. If we end up having the funds to implement this AI HAT, we may purchase it, but we determined that for now, it’s a non-priority.  As for the Raspberry Pi, we hope to use this as our main microprocessor, and we were able to secure one from the 18-500 Inventory list, which we will pick up on Monday or Tuesday of next week. We still need to purchase a camera– I do not think that ECE has the type of camera we need. I researched the Raspberry Pi High Quality Camera (IMX477R), Raspberry Pi AI Camera with Sony IMX500 (which has an onboard AI vision sensor), and the Module 3 Sensor Assembly (which is said to be goof for external hardware, like we are using). Next week, I should decide which of these to choose so we can order it.

Posted on

Francesca Cain’s Status Report for September 20th

This week, I spent the majority of my time preparing for our final project presentation. After Bella completed the slides, I focused on practicing how to deliver information about our project in a way that would be digestible for people unfamiliar with our project, with OCR, or even with ECE in general. I also spent considerable time preparing for our project proposal presentation and anticipating questions that our classmates might ask.

We were asked many helpful questions by our classmates and TAs. One that stuck with me, and our group in general, was about the automation of testing for our OCR text recognition to braille process. Given the scope and number of texts we hope to test, we realized we need to spend more time determining how to create easy, repeatable, and modular testing for various aspects of our project.

After my in-class presentation that day, I spent time researching ways to automate this testing. I believe there are some viable options involving machine learning that I am excited to explore further next week.

Posted on

Team Status Report for September 20th

This week, our group spent the majority of our time preparing for our final project presentation. Bella prepared our slides and the corresponding Gantt chart, and Francesca spent considerable time preparing for our project proposal presentation and anticipating questions that our classmates might ask.

In hearing these questions, one issue that arose was the automation of testing for our OCR text recognition to braille process. This led us to think critically about modularization across the various components our project relies upon.

Following our Gantt chart, we have been researching available OCR libraries, the actuation method we plan to use, and the cameras and microcontrollers (like Raspberry Pi) we might use. Though our Gantt chart specifies that we should order these tools this week, through research and discussion with other students, we are considering borrowing a camera and repurposing a Raspberry Pi from a prior class. This would reduce waste and help us maximize our $600 budget.

Next week, and further following our Gantt chart, we hope to finalize our tool selection and move on to selecting materials for printing our labels.