Significant risks for the project we managed this week: It’s almost certain that the originally proposed Bag-of-Words algorithm does not work well on the advanced midi matching task, and we are moving on to another approach that focuses more on the melody of the midi input, instead of the number Read more…
Accomplishments this week 1. Advanced MIDI pattern matching. This week I made several test cases to test the bag-of-words approach by randomly delete some notes from the original slices. The testing procedure is (1) slice the original midi file, called ori_midi, into slices of different lengths, called ori_slice (2) randomly Read more…
Accomplishments this week Try cropping out the title part of images and use MSE to compare Does not work because the accuracy is lower than expected for comparing the titles due to positioning and other reasons Try using Tesseract to find the text in the music score Successfully transformed most Read more…
Accomplishments this week 1.Change M2 from stepper motor to servo When searching for appropriate M2, the limited torque M1 can bring is my big consideration. A searched for many stepper motor models, but all has large dimension (around 40mm * 40mm) and large weight (around 350g). In order to flip Read more…
Significant risks for the project we managed this week: Using natural language processing for finding the title of music score input and matching it with database might have two risks in the future For music scores that are not in the database, it will be harder to match because for Read more…
Accomplishments this week 1. Receive MIDI signals from the digital keyboard on Mac with Python 3.5. The final implementation used Pygame’s built-in MIDI module with python 3.5. Important documentation for Pygame’s MIDI module can be found here https://www.pygame.org/docs/ref/display.html. It’s not trivial to correctly install the Python 3 version Pygame on Mac. Read more…
Accomplishments this week Finished the basic setup for the code for image processing Wrote code to get the scores from database used for matching, currently the files are stored locally in a folder that mimics database Used os.walk to walk through and get the pdf files from the static folder, Read more…
Accomplishment this week: 1. Design of mechanical system For the mechanical flipper, M1 needs to have high power to flip the shaft and motor, M2 need to be very light weighted to make the flipping easier for M1. M3 needs to be small to fit between M1 and the music Read more…
Significant risks for the project we managed this week: The Adafruit stepper motor driver is ordered but the part shipment will take three weeks. Even though we ordered one extra, but if all drivers are down, it will take another three weeks to get the hardware up again. We didn’t Read more…
Accomplishments this week: Studied midi protocol; useful midi protocol info can be found here https://www.midi.org/specifications-old/item/table-1-summary-of-midi-message. Studied python libraries for handling midi files; decided to work with Mido. Documentation can be found here https://mido.readthedocs.io/en/latest/index.html. Researched midi matching algorithms; useful paper describing a status-to-art approach can be found here https://www.ml.cmu.edu/research/dap-papers/dap_xia.pdf. Programmed basic midi matching Read more…