This project focuses on the design and implementation of a computer vision application designed to utilize object detection algorithms to recognize objects in real-life scenarios, the main goal is to create a versatile Android application capable of accurately detecting and identifying objects from images or video streams captured by the device's camera, the project begins by exploring various object detection algorithms and their suitability for mobile platforms. Pre-trained models, such as YOLO (You Only Look Once), SSD (Single Shot Detector), and Faster R-CNN (Region-based Convolutional Neural Network), and after checking accuracy, speed, and memory requirements. After careful analysis, the most appropriate object detection model is selected and integrated into the Android application.
- Python
- Tensorflow
- TensorFlowLite
- Android Studio