Object Detection Using Neural Networks

This paper presents a novel approach to object detection by combining the strengths of two state- of-the-art models: YOLO (You Only Look Once) and Faster R-CNN (Region-based Convolutional Neural Network). YOLO is known for its real-time object detection capabilities, while Faster R-CNN offers high detection accuracy. By integrating these two models, we aim to achieve a balanced performance in terms of speed and accuracy. The models were trained and tested using the COCO dataset, containing a wide variety of object classes. Our hybrid model demonstrates improved detection performance compared to individual YOLO or Faster R-CNN models.