Posted on

10/29 Team Status Report

This week, Rachana spent time looking at our review from the design report. There are some things we need to figure out including what aspects of the UI we want to display. Currently, we want to just auto add items to the list, give the user the ability to trash the item if need be. We also want to display this list of items with their individual costs, and cumulative cost. I found a grocery POS app that can help me with this.

For last week, Raymond was primarily working on adding new functionality to the design, which is adding a control unit to the controller. Again, I used the skills I learned from 18220 to find the correct motor driver, and I proofread the specification of the size and the material properties of various mechanical components, and read the voltage and amps of different electrical components.

For next week, Raymons is planning to

  1. Drill 8 holes in the wood.
  2. Cut the metal of the shaft.
  3. Cut the belt to make it fit into our design.
  4.  Glue the two wood planks onto the wood base.
  5. order a coupler to connect the motor and the shaft.

 

For this week, Jiyeon worked on testing some images using Tesseract for text detection and planned web app. We are planning to modify the web app framework that was found on web with the features we want to use. For text detection, Jiyeon was able to extract text from the images, but to be used with the retail product, Jiyeon would need some image preprocessing done before using the text detection so that Jiyeon can distinguish the text from the background. So I think Jiyeon is going to work on that for next week.

Posted on

Jiyeon’s Status Report 10/29

For this week, I worked on testing some images using Tesseract for text detection and reviewed the feedbacks from our design report. Also, Rachana and I met on Friday to discuss about our web app plan, and we are planning to modify the web app framework that was found on web with the features we want to use. For text detection, I was able to extract text from the images, but to be used with the retail product images, I would need some image preprocessing done before using the text detection so that I can distinguish the text from the background with multiple colors. So I think I am going to work on that for next week. Since the interim demo is due in about a week, I am planning to more work on the project next week

Posted on

Raymond Yang 10/29 Status Report

So for last week, right, I was primarily working on adding new functionality to the design, which is adding a control unit to the controller. Again, I used the skills I learned from 18220 to find the correct motor driver, and I proofread the specification of the size and the material properties of various mechanical components, and read the voltage and amps of different electrical components.

For next week, I plan to

  1. Drill 8 holes in the wood.
  2. Cut the metal of the shaft.
  3. Cut the belt to make it fit into our design.
  4.  Glue the two wood planks onto the wood base.
  5. order a coupler to connect the motor and the shaft.
Posted on

Rachana Status Report 10/29

This week, I spent time looking at our review from the design report. There are some things we need to figure out including what aspects of the UI we want to display. Currently, we want to just auto add items to the list, give the user the ability to trash the item if need be. We also want to display this list of items with their individual costs, and cumulative cost. I found a grocery POS app that can help me with this.

https://www.sourcecodester.com/python/15210/grocery-point-sales-pos-system-python-django-free-source-code.html

I need to customize this django app to our needs. Furthermore, I have been expanding the CV system to different classes. I still want to be able to better the accuracy rate on the validation set. I think I am on schedule better than I was last week for my parts of the project.

Posted on

Team Status Report 10/22

This week we had our design report due. We had fall break the past week. We came to a conclusion that Jiyeon takes the text detection part of the CV system, and Rachana takes the image classification part of the CV System.  This is a better split as our work is now laid out, and we can get working on our respective parts. Raymond got his parts mostly settled, and now the following week we can look at developing the main hardware portion of the system.  We have not really worked on the UI part of our system extensively. I think it might make more sense for us to maybe make a few wireframes, and see how dynamic we want our UI to be for the upcoming week.

Posted on

Rachana’s Status Report 10/22

This week we had our design report due. While writing out the design report, we were able to resolve many confusions. I mainly worked on training and testing the model with a couple photos. I had to shift from Tensorflow because documentation for Tf was limited, and there were many version conflicts. Upon the recommendation from the TA, I switched the code base to Pytorch tools mainly. I had to spend time removing problematic images as well as they were causing a lot of read errors with the images in the train directory. I am currently able to train and test two classes successfully with a ResNet-50. There are many unused parameters still which is probably eating up a lot of memory that I need to work on fixing. The following week I want to see if I can map out an accuracy vs model test and see which is the optimum model where I optimize the parameters I am using. I also want to figure out a segmentation model where I can create a bounded box around the main object being looked at. I also want to explore how we can best train the model to look at images from both the camera angles -> would it be better to train it with a tuple of images or would it make sense to go for a probability distribution on which camera usually gets the right frame that makes it possible to identify and classify the object. I think I am at a better spot than a week ago. I want to look at having a prototype for UI set up for the website as well by the end of the week.

Posted on

Jiyeon’s Status Report 10/22

For this week, I mainly worked on design report, labeling the dataset, and researching text detection. After discussion with the professor on Monday (10/10), I wrote a script to label the dataset. I extracted class and label from dataset spreadsheet, and changed the filename into the following format: <class>_<label>_<original filename>.jpg. Rachana and I were working on CNN together, but on Wednesday (10/12), we decided to split the computer vision part into two— CNN and text detection. Now that I am taking in charge of text detection, I needed to research about text detection so I started researching this week. From the research, I think I will be using Tesseract and OpenCV. I have tested the library to extract the text from the images. For design report, I have finished summary, architecture (text detection), project management (schedule, responsibilities, risk management, and supply), system implementation (text detection and web app), design trade studies (dataset choice), test & verification (cv, web app, and integration).

Posted on

Mingrui Yang 10/18 Status report

This week I am on the schedule, and I am on track to finish the project. This week I have been primarily working on calculating the specs of the hardware design. For instance, I did some measurement on the height of the camera using my iphone(since I haven’t ordered the parts yet), and figured at approximately at what height will the camera be able to capture the picture of the items.  Also, after knowing the area of the camera, I can project at what speed should the belt move, and this heavily depends on the diameter of the shaft and the speed at the motor rotates. Lastly, I communicated with Rachana and Jiyeon who are in charge of the computer vision part to get an idea of how fast can the recognition algorithms run so that it wouldn’t take too long(otherwise the item may move out of the designated picture-taking area). For next week, I will talk with techspark on how to drill holes into the wood slab, and start assemblying the items, if the parts are delivered to me.

Posted on

Mingrui Yang 10/8 Status Report

This week I am on the proposed schedule. I have been working on a sketch of the hardware layout, including the detailed design and sketch of the size of each component. I am also working on a proposal to convince the staff member that  the  design will work as planned. I have also tried looking into several vendors to compare the most price efficient method for each of the parts. For the upcoming week, I plan to get the parts approved, and receiving them to see if I could assemble them in the way I want.  If not, I am planning to redesgin and filling out the inventory again.

Posted on

Team Status Report 10/8

For this week,  Jiyeon worked on CNN part of the project. She’s testing her code using cat and dog example dataset since our dataset is not labeled yet. In the dataset, there are 12,501 images of test data and 25,001 images of train data. She preprocessed the data by using one hot encoder and it labeled cat as [1,0] and dog as [0,1], and she was able to create npy files for train and test data each. For next week, she will be continue working on labeling the dataset we have, and try training the model using the dataset.

This week Mingrui is on the proposed schedule. He has been working on a sketch of the hardware layout, including the detailed design and sketch of the size of each component. He is also working on a proposal to convince the staff member that  the  design will work as planned. He has also tried looking into several vendors to compare the most price efficient method for each of the parts. For the upcoming week, he plans to get the parts approved, and receiving them to see if he could assemble them in the way he want.  If not, he is planning to redesign and filling out the inventory again.

This week, Rachana worked on generating the CNN part of the project using coke and lays objects downloaded through a google extension for making image directories for the dataset. She ran into problems with iterating through batches of the dataset. She is trying to see if it could be the extensions of the images that might be causing problems in parsing the images when taking batches. Rachana also worked on alot of the design slides and presenting on Wednesday this week. The design slides were challenging to patch up at the last minute because of last minute design changes as well. Efforts to build a team dynamic will be made on her end to make sure the project is more smooth sailing than what it has been.

Since the design report is due on Friday October 14th, we will work on it next week and we hope to finish it by Thursday.  We hope to get the work done as much as before the fall break.