AllerEase

Inspiration

AllerEase is an application for individuals’ need to manage the challenges and limitations relating to allergens in daily life. Our ultimate goal was to develop a tool that would enable people to make wise decisions on the go and still enjoy a varied and satisfying diet.

What it does

AllerEase is a revolutionary tool that makes it easier to manage dietary restrictions and allergies. With the help of image recognition technology, customers can quickly and easily identify possible allergens in restaurant menus and packaged foods on the go. With individualized suggestions, AllerEase gives users the power to confidently and easily navigate their particular dietary requirements and make educated decisions in everyday life.

How we built it

We used a number of platforms and technologies during the course of our project, including Python, Tensor Flow, PyTorch, Foundation, Google Cloud DataFlow, EasyOCR, MongoDB Atlas, Pandas, Matplotlib, Clustering, and PyTorch. We explored database administration, machine learning, front-end development, data streaming, and back-end systems, picking up insightful knowledge and useful skills in the process. We gained the skills and information from this intense experience that will enable us to take on challenging problems and create creative software development solutions.

Challenges we ran into

Optimizing the performance of our image recognition algorithms and guaranteeing the dependability of our database presented significant technical obstacles that we had to get past. When working on setting up the database, an issue was finding a suitable database solution for storing allergen information efficiently. We tested multiple implementations to evaluate their compatibility with our project requirements before settling on MongoDB Atlas. Additionally, we faced challenges in designing the user interface (UI) to ensure it was intuitive and user-friendly, also when implementing authentication mechanisms to ensure the security and privacy of user data. Overcoming these challenges not only strengthened our technical skills but also taught us valuable lessons in project management, collaboration, and problem-solving.

Accomplishments that we're proud of

The process of developing AllerEase has been fulfilling, enabling us to use our technological expertise to produce a product that could greatly improve the lives of many people who are coping with dietary restrictions and allergies. We were able to work with multiple different platforms and technologies we have never previously used, including OCR, MongoDB, Swift, and many more, which expanded our skills and enabled us to tackle complex challenges.

What we learned

As novices to Swift, MongoDB, and machine learning, we set out on a voyage of learning and exploration throughout the project. Though we were not familiar with these technologies at first, we quickly picked them up and used different machine learning tools like Pandas, Matplotlib, Clustering, PyTorch, Tensor Flow, and Numpy, as well as Swift UI and Foundation for front-end development and database management. This experience demonstrated our capacity to pick up new ideas quickly and put them to good use. It also gave us insightful knowledge about how to create user-friendly interfaces, effective data processing, reliable database management, and sophisticated machine learning techniques.

What's next for AllerEase

AllerEase hopes to improve its offerings in the future by collaborating with supermarkets to incorporate real-time pricing and product availability data. Furthermore, the platform intends to create a meal planning feature that provides users with customizable recipes based on their allergies and dietary restrictions. AllerEase also plans to extend its allergen detection range to non-food products like pharmaceuticals and personal hygiene items. The platform uses machine learning algorithms in an effort to gradually increase the accuracy of allergen detection. Last but not least, AllerEase intends to work with medical experts to offer users individualized support and educational materials, guaranteeing a thorough approach to handling dietary needs and allergies.

Built With

• clustering
• easyocr
• foundationdb
• google-cloud
• mongodb
• numpy
• python
• swift