Skip to content

pskalbhav1/Nutri.Co_treehacks

 
 

Repository files navigation

Nutri.Co

Inspiration

We were watching Shark Tank India and came across ideas that focused on living the Ayurvedic life. These few episodes made us curious about Ayurveda, and the practices followed by our ancient civilization. We started digging deep into the various doshas and their effects on health. Treehacks provided a perfect opportunity for us to build our own application showcasing the benefits that Ayurveda provides.

What it does

Nutri.Co is an interactive web application that determines an individual's Prakrithi doshas based on quizzes and recommends food choices. We have integrated a creative blinking exercise that helps a user exercise as well as get food recommendations at the same time. We also have a WhatsApp bot that answers queries related to Ayurveda, food choices, calories, and recipes.

We have a tool to determine calorie intake based on live feed/picture upload of nutrition charts. In addition to this, we have a BMI and BMR calculator that predicts your wellbeing and suggests exercises for a healthy life.

How we built it

The entire application is built using:

  • Frontend: HTML, JS, CSS
  • Backend: Python, Flask, OpenCV
  • Whatsapp bot is built using Twillio and Yummly API
  • Live feed is taken using yolov3 for food detection and pytesseract for text analysis

Challenges we ran into

  • We faced an issue in integrating the different functionalities together.
  • Accuracy of the identification models

Accomplishments that we're proud of

  • This is our first time using APIs and glad to have learnt something new.
  • We're very proud of successfully integrating multiple artistic ideas into one project. From ancient history to calorie and food intake, exercising and current lifestyle, we are happy that we were able to connect things together in one.

What we learned

  • As mentioned above, we learnt and used APIs successfully.
  • Each member of the team utilized challenging technology, and as a result, we learnt a lot about Python, Flask during the last 36 hours! We learned to train and test ML models.
  • We also learnt a few tricks about integrating ML models with web applications. We learned so much through this project and from each other, and had a really great time working as a team!

What's next for Nutri.Co

  • Personalized recommendations
  • Using vision API's from Google/Microsoft

Releases

No releases published

Packages

 
 
 

Languages

  • HTML 55.7%
  • Jupyter Notebook 27.0%
  • CSS 13.0%
  • JavaScript 4.3%