Inspiration: Hungry and unsatisfied with entrees Cal Hacks provided, then saw food pics
What it does: Our web application, in a nutshell, is food Shazam. Basically, given an image of food, the application can identify what the name of the food is and possible locations for the food item with a confidence level.
How we built it: We built this by utilizing Google Cloud's Machine Learning API (Vision ), along with various Python libraries such as Pandas, Numpy, Pillow, and more. In addition, we also used Node.js and Express JS along with Mapbox's API.
Challenges we ran into: We've ran into a lot of issues involving Google's API, information gathering and at the end, the realization that the amount of information we had were numerous. It would take over 10 hours to train the model so we have reduced the size of our data for purposes of the hackathon.
Accomplishments that we're proud of: We are proud of just coming out with a finished product after the long hours of just coding and brainstorming.
What's next for Instafoody: Instafoody is a product of great potential, and if given the chance, we are looking forward to furthering the development of Instafoody to cover a vast range of restaurants around the world.
Log in or sign up for Devpost to join the conversation.