ElhoubeBrahim/Moroccam

Experience Morocco like a local with Moroccam, the ultimate travel companion app for capturing the essence of Morocco through its language and culture. - Think AI Hackathon # Moroccam Experience Morocco like a local with Moroccam, the ultimate travel companion app for capturing the essence of Morocco through its language and culture. ## Table of Contents - About the Project - Our Team - The Architecture - General Overview - Used APIs - Used Technologies - How to Use - Usage - Screenshots - Limitations - Roadmap - Contact ## About the Project Moroccam is a mobile application that aims to enhance the travel experience for tourists visiting Morocco. With Moroccam, tourists can take pictures of objects and landmarks and get instant translations and information in Moroccan darija, the local dialect. Moroccam is designed with a simple and user-friendly interface, making it easy for tourists to navigate and use the app. ## Our Team We are a passionate team with diverse backgrounds and a shared goal of making a positive impact through innovative technology. As participants in a hackathon, we are excited to bring our skills together to create Moroccam. ## The Architecture ### General Overview The Moroccam app architecture is designed to efficiently handle the different functionalities of the app. The backend of the app consists of two endpoints. - The first endpoint is responsible for detecting the location of the image provided by the user using Teachable Machine models trained on images of different locations in Morocco, along with the Google Maps API and OpenAI API. - The second endpoint is used for object detection using Azure Cognitive Services and OpenAI API. This design allows for faster and more accurate processing of user requests, resulting in an enhanced user experience. ### Used APIs We utilized Azure Cognitive Services API to enhance the user experience by incorporating features like object detection and text-to-speech. Object detection allowed us to identify objects present in an image taken by the user, while text-to-speech was used to convert the object's name into an audio file that could be playe …