Inspiration
Calories in - Calories out provides the basis for weight loss. So what happens when the calories are ambiguous? Benson nutritional information can be highly suspicious and oftentimes doesn’t provide any information at all.
What it does
Our solution, CalPal, looks to resolve any nutritional ambiguity when dieting to make sure that you reach your weight management goals.
How we built it
CalPal is uses a Next.JS to provide users with an easy to use and intuitive front end. Users upload an image of food that is then processed by an AI model on AWS's Bedrock on our backend to estimate caloric and macronutrient contents.
Accomplishments that we're proud of
CalPal is able to effectively harness AI's expansive and dynamic processing power while simultaneously controlling its responses to consistently output formatted data
What's next for CalPal
Implementing the app to be used on mobile phones with a built-in camera would improve convenience + accessibility. Furthermore, creating our own annotated data sets and training custom models would improve accuracy and consistency
Built With
- amazon-web-services
- bedrock
- claude
- next.js
- python
Log in or sign up for Devpost to join the conversation.