Intro-ML-Arts-IMA-F24/04-face-and-hand-models at main · ml5js/Intro-ML-Arts-IMA-F24

Leah’s Assignment 4 :

1. Research and find a project (experiments, websites, art installations, games, etc) that utilizes machine learning in a creative way. Consider the following:
   • What type of machine learning models did the creator use?
   • What data might have been used to train the machine learning model?
   • Why did the creator of the project choose to use this machine learning model?
2. Pick one of the models above (FaceMesh or HandPose), following the examples above and the ml5.js documentation, experiment with controlling elements of a p5.js sketch (color, geometry, sound, text, etc) with the output of the model. Try to create an interaction that is surprising or one that is inspired by the project you find.
3. Document your research, your response, and your p5.js sketch in a blog post. Add a link to the post and your p5.js sketch on the Assignment 4 Wiki page. In your blog post, include visual documentation such as a recorded screen capture / video / GIFs of your sketch.

Task 1: Research and find a project (experiments, websites, art installations, games, etc) that utilizes machine learning in a creative way.

🤖 Morning Mountain: Visual Alarm Clock (check this out)

“A Visual Alarm clock. It's an alarm clock that only turns off when you hold a power pose in front of it for 10 seconds.”

When the alarm clock sketch is loaded, the alarm will go off immediately. Get into the power pose to turn it off, and the clock will ring again in 24 hours.

I found this alarm clock very useful and smart as a tool.

1. What type of machine learning models did the creator use?

   The creator utilized a TensorFlow Lite image classification model specifically designed for embedded systems. This model is suitable for running on low-power devices like the Arduino Nano BLE.

2. What data might have been used to train the machine learning model?

   The data used to train the model likely includes images of various poses that the user would like to use to turn off the alarm. These images can be collected using the OV7670 Camera and would include:

   • Positive examples: Pictures of the desired power poses.
   • Negative examples: Images of other poses or backgrounds to help the model distinguish between the target poses and irrelevant ones.

   The training could be done using Teachable Machine, which allows users to upload images and train a model without extensive programming knowledge.

3. Why did the creator of the project choose to use this machine learning model?

   Using Teachable Machine makes it easier for users to train a custom model based on their preferred poses without requiring deep knowledge of machine learning.