Inspiration
The inspiration behind creating this kind of lens was the difficulty that a student faces in a classroom where there is a single skeleton among 40 to 50 students and the teacher is explaining each part one by one. Usually, as a student one can not learn everything in one go so this can help them in revising their concepts and getting to know each part in detail with a personal skeleton in hand with a mobile device in hand.
What it does
It places a Human Skeleton in the user environment and with one click (Start Experience) the experience gets triggered one by one all the body parts are highlighted and their details are spoken by the virtual agent. The Virtual Agent explains the part and describes their importance in the body and moves to another part. This Lens is a combination of plane tracking and visual description with a layer of Text To Speech module of Machine Learning where the Description of a part is interpreted in real-time and speaks the body part description in real-time with an audio component.
How we built it
It is a combination of plane tracking and visual description with a layer of Text To Speech module of Machine Learning where the Description of a part is interpreted in real-time and speaks the body part description in real-time with an audio component.
Challenges we ran into
The biggest challenge was to overcome the problem statement ("How to empower learning experiences with the use of AR). We identified the problems that we use to face as students and tried to reach out to a few juniors and got to know this is one of the biggest problems in the medical field. 1)Created our own 3d model and annotated it using Blender & Maya in spite of not being a pro at 3d modeling we learn and created the 3d model on our own. 2)Explored the true scale modules and scripts and customized them which detect the surface and place the object in the center of the screen where it's not getting cut in from the screen also adjusted the placement with a drag. 3)Creating a custom UI Button that starts the experience and enables the virtual agent to explain the Human Anatomy in detail this was the most challenging part where our goal was to explain 32 parts of the body in detail and all of this was done under 3.63 MB of size.
Accomplishments that we're proud of
We are proud that we have pulled this off with and wonderful outcome where the students can easily learn Human anatomy using this Lens Experience and all of this was done under 3.63 MB which was our biggest accomplishments
What we learned
We learned and explored a new module of Machine learning and Audio component where we can convert our text string into a speech signal and pass it as output audio to the experience.
What's next for Human Anatomy
Next, we are coming up soon with an advanced version of this experience where we will give the user control to speak the part name that they want to learn and the virtual agent will explain that part in detail. Here we will use ML's Speech recognition module to recognize the user's speech and interpret it as input.
Built With
- blender
- canva
- javascript
- lensstudio
- maya
- snapml
- vn


Log in or sign up for Devpost to join the conversation.