This project aims to demonstrate how to implement AI-powered landmark recognition using TensorFlow Lite and CameraX on Android devices. By leveraging pre-trained models, specifically this model provided by Google, the application can accurately identify landmarks in real-time.
The model utilized in this project is the Google-provided landmark recognition model. It has been trained on various landmarks across Europe to recognize them efficiently. You can find the model here.
These screenshots showcase the application's interface and its functionality in action. The AI-powered landmark recognition feature is prominently displayed, demonstrating its accuracy and real-time processing capabilities.
To use this project, follow these steps:
- Clone the repository to your local machine.
- Open the project in Android Studio.
- Ensure that the necessary dependencies are installed and configured.
- Build and run the application on your Android device.
- Point the camera at various landmarks to see the AI recognition in action.
This project relies on the following dependencies:
- TensorFlow Lite: TensorFlow Lite is used to run the pre-trained model efficiently on Android devices.
- CameraX: CameraX is utilized for camera integration, allowing seamless access to device cameras.
- Google for providing the pre-trained landmark recognition model.
- TensorFlow team for developing TensorFlow Lite.
- Google's CameraX team for creating the CameraX library.
This project is licensed under the MIT License. Feel free to use and modify it according to your needs.
Note: Make sure to download the model and place it in the appropriate directory before running the application.